package google.cloud.vision.v1p3beta1
Get desktop application:
View/edit binary Protocol Buffers messages
Service that performs Google Cloud Vision API detection tasks over client images, such as face, landmark, logo, label, and text detection. The ImageAnnotator service returns detected entities from the images.
Run image detection and annotation for a batch of images.
message
image_annotator.proto:652Multiple image annotation requests are batched into a single service call.
repeated requests = 1
Individual image annotation requests for this batch.
message
image_annotator.proto:658Response to a batch image annotation request.
repeated responses = 1
Individual responses to image annotation requests within the batch.
Run asynchronous image detection and annotation for a list of generic files, such as PDF files, which may contain multiple pages and multiple images per page. Progress and results can be retrieved through the `google.longrunning.Operations` interface. `Operation.metadata` contains `OperationMetadata` (metadata). `Operation.response` contains `AsyncBatchAnnotateFilesResponse` (results).
message
image_annotator.proto:686Multiple async file annotation requests are batched into a single service call.
repeated requests = 1
Individual async file annotation requests for this batch.
Manages Products and ProductSets of reference images for use in product search. It uses the following resource model: - The API has a collection of [ProductSet][google.cloud.vision.v1p3beta1.ProductSet] resources, named `projects/*/locations/*/productSets/*`, which acts as a way to put different products into groups to limit identification. In parallel, - The API has a collection of [Product][google.cloud.vision.v1p3beta1.Product] resources, named `projects/*/locations/*/products/*` - Each [Product][google.cloud.vision.v1p3beta1.Product] has a collection of [ReferenceImage][google.cloud.vision.v1p3beta1.ReferenceImage] resources, named `projects/*/locations/*/products/*/referenceImages/*`
Creates and returns a new ProductSet resource. Possible errors: * Returns INVALID_ARGUMENT if display_name is missing, or is longer than 4096 characters.
message
product_search_service.proto:508Request message for the `CreateProductSet` method.
string parent = 1
The project in which the ProductSet should be created. Format is `projects/PROJECT_ID/locations/LOC_ID`.
optional product_set = 2
The ProductSet to create.
string product_set_id = 3
A user-supplied resource id for this ProductSet. If set, the server will attempt to use this value as the resource id. If it is already in use, an error is returned with code ALREADY_EXISTS. Must be at most 128 characters long. It cannot contain the character `/`.
Lists ProductSets in an unspecified order. Possible errors: * Returns INVALID_ARGUMENT if page_size is greater than 100, or less than 1.
message
product_search_service.proto:525Request message for the `ListProductSets` method.
string parent = 1
The project from which ProductSets should be listed. Format is `projects/PROJECT_ID/locations/LOC_ID`.
int32 page_size = 2
The maximum number of items to return. Default 10, maximum 100.
string page_token = 3
The next_page_token returned from a previous List request, if any.
message
product_search_service.proto:539Response message for the `ListProductSets` method.
repeated product_sets = 1
List of ProductSets.
string next_page_token = 2
Token to retrieve the next page of results, or empty if there are no more results in the list.
Gets information associated with a ProductSet. Possible errors: * Returns NOT_FOUND if the ProductSet does not exist.
message
product_search_service.proto:549Request message for the `GetProductSet` method.
string name = 1
Resource name of the ProductSet to get. Format is: `projects/PROJECT_ID/locations/LOG_ID/productSets/PRODUCT_SET_ID`
Makes changes to a ProductSet resource. Only display_name can be updated currently. Possible errors: * Returns NOT_FOUND if the ProductSet does not exist. * Returns INVALID_ARGUMENT if display_name is present in update_mask but missing from the request or longer than 4096 characters.
message
product_search_service.proto:558Request message for the `UpdateProductSet` method.
optional product_set = 1
The ProductSet resource which replaces the one on the server.
optional update_mask = 2
The [FieldMask][google.protobuf.FieldMask] that specifies which fields to update. If update_mask isn't specified, all mutable fields are to be updated. Valid mask path is `display_name`.
Permanently deletes a ProductSet. All Products and ReferenceImages in the ProductSet will be deleted. The actual image files are not deleted from Google Cloud Storage. Possible errors: * Returns NOT_FOUND if the ProductSet does not exist.
message
product_search_service.proto:570Request message for the `DeleteProductSet` method.
string name = 1
Resource name of the ProductSet to delete. Format is: `projects/PROJECT_ID/locations/LOC_ID/productSets/PRODUCT_SET_ID`
Creates and returns a new product resource. Possible errors: * Returns INVALID_ARGUMENT if display_name is missing or longer than 4096 characters. * Returns INVALID_ARGUMENT if description is longer than 4096 characters. * Returns INVALID_ARGUMENT if product_category is missing or invalid.
message
product_search_service.proto:433Request message for the `CreateProduct` method.
string parent = 1
The project in which the Product should be created. Format is `projects/PROJECT_ID/locations/LOC_ID`.
optional product = 2
The product to create.
string product_id = 3
A user-supplied resource id for this Product. If set, the server will attempt to use this value as the resource id. If it is already in use, an error is returned with code ALREADY_EXISTS. Must be at most 128 characters long. It cannot contain the character `/`.
Lists products in an unspecified order. Possible errors: * Returns INVALID_ARGUMENT if page_size is greater than 100 or less than 1.
message
product_search_service.proto:451Request message for the `ListProducts` method.
string parent = 1
The project OR ProductSet from which Products should be listed. Format: `projects/PROJECT_ID/locations/LOC_ID`
int32 page_size = 2
The maximum number of items to return. Default 10, maximum 100.
string page_token = 3
The next_page_token returned from a previous List request, if any.
message
product_search_service.proto:466Response message for the `ListProducts` method.
repeated products = 1
List of products.
string next_page_token = 2
Token to retrieve the next page of results, or empty if there are no more results in the list.
Gets information associated with a Product. Possible errors: * Returns NOT_FOUND if the Product does not exist.
message
product_search_service.proto:476Request message for the `GetProduct` method.
string name = 1
Resource name of the Product to get. Format is: `projects/PROJECT_ID/locations/LOC_ID/products/PRODUCT_ID`
Makes changes to a Product resource. Only display_name, description and labels can be updated right now. If labels are updated, the change will not be reflected in queries until the next index time. Possible errors: * Returns NOT_FOUND if the Product does not exist. * Returns INVALID_ARGUMENT if display_name is present in update_mask but is missing from the request or longer than 4096 characters. * Returns INVALID_ARGUMENT if description is present in update_mask but is longer than 4096 characters. * Returns INVALID_ARGUMENT if product_category is present in update_mask.
message
product_search_service.proto:485Request message for the `UpdateProduct` method.
optional product = 1
The Product resource which replaces the one on the server. product.name is immutable.
optional update_mask = 2
The [FieldMask][google.protobuf.FieldMask] that specifies which fields to update. If update_mask isn't specified, all mutable fields are to be updated. Valid mask paths include `product_labels`, `display_name` and `description`.
Permanently deletes a product and its reference images. Metadata of the product and all its images will be deleted right away, but search queries against ProductSets containing the product may still work until all related caches are refreshed. Possible errors: * Returns NOT_FOUND if the product does not exist.
message
product_search_service.proto:499Request message for the `DeleteProduct` method.
string name = 1
Resource name of product to delete. Format is: `projects/PROJECT_ID/locations/LOC_ID/products/PRODUCT_ID`
Creates and returns a new ReferenceImage resource. The `bounding_poly` field is optional. If `bounding_poly` is not specified, the system will try to detect regions of interest in the image that are compatible with the product_category on the parent product. If it is specified, detection is ALWAYS skipped. The system converts polygons into non-rotated rectangles. Note that the pipeline will resize the image if the image resolution is too large to process (above 50MP). Possible errors: * Returns INVALID_ARGUMENT if the image_uri is missing or longer than 4096 characters. * Returns INVALID_ARGUMENT if the product does not exist. * Returns INVALID_ARGUMENT if bounding_poly is not provided, and nothing compatible with the parent product's product_category is detected. * Returns INVALID_ARGUMENT if bounding_poly contains more than 10 polygons.
message
product_search_service.proto:579Request message for the `CreateReferenceImage` method.
string parent = 1
Resource name of the product in which to create the reference image. Format is `projects/PROJECT_ID/locations/LOC_ID/products/PRODUCT_ID`.
optional reference_image = 2
The reference image to create. If an image ID is specified, it is ignored.
string reference_image_id = 3
A user-supplied resource id for the ReferenceImage to be added. If set, the server will attempt to use this value as the resource id. If it is already in use, an error is returned with code ALREADY_EXISTS. Must be at most 128 characters long. It cannot contain the character `/`.
Permanently deletes a reference image. The image metadata will be deleted right away, but search queries against ProductSets containing the image may still work until all related caches are refreshed. The actual image files are not deleted from Google Cloud Storage. Possible errors: * Returns NOT_FOUND if the reference image does not exist.
message
product_search_service.proto:638Request message for the `DeleteReferenceImage` method.
string name = 1
The resource name of the reference image to delete. Format is: `projects/PROJECT_ID/locations/LOC_ID/products/PRODUCT_ID/referenceImages/IMAGE_ID`
Lists reference images. Possible errors: * Returns NOT_FOUND if the parent product does not exist. * Returns INVALID_ARGUMENT if the page_size is greater than 100, or less than 1.
message
product_search_service.proto:598Request message for the `ListReferenceImages` method.
string parent = 1
Resource name of the product containing the reference images. Format is `projects/PROJECT_ID/locations/LOC_ID/products/PRODUCT_ID`.
int32 page_size = 2
The maximum number of items to return. Default 10, maximum 100.
string page_token = 3
A token identifying a page of results to be returned. This is the value of `nextPageToken` returned in a previous reference image list request. Defaults to the first page if not specified.
message
product_search_service.proto:616Response message for the `ListReferenceImages` method.
repeated reference_images = 1
The list of reference images.
int32 page_size = 2
The maximum number of items to return. Default 10, maximum 100.
string next_page_token = 3
The next_page_token returned from a previous List request, if any.
Gets information associated with a ReferenceImage. Possible errors: * Returns NOT_FOUND if the specified image does not exist.
message
product_search_service.proto:628Request message for the `GetReferenceImage` method.
string name = 1
The resource name of the ReferenceImage to get. Format is: `projects/PROJECT_ID/locations/LOC_ID/products/PRODUCT_ID/referenceImages/IMAGE_ID`.
Adds a Product to the specified ProductSet. If the Product is already present, no change is made. One Product can be added to at most 100 ProductSets. Possible errors: * Returns NOT_FOUND if the Product or the ProductSet doesn't exist.
message
product_search_service.proto:648Request message for the `AddProductToProductSet` method.
string name = 1
The resource name for the ProductSet to modify. Format is: `projects/PROJECT_ID/locations/LOC_ID/productSets/PRODUCT_SET_ID`
string product = 2
The resource name for the Product to be added to this ProductSet. Format is: `projects/PROJECT_ID/locations/LOC_ID/products/PRODUCT_ID`
Removes a Product from the specified ProductSet. Possible errors: * Returns NOT_FOUND If the Product is not found under the ProductSet.
message
product_search_service.proto:663Request message for the `RemoveProductFromProductSet` method.
string name = 1
The resource name for the ProductSet to modify. Format is: `projects/PROJECT_ID/locations/LOC_ID/productSets/PRODUCT_SET_ID`
string product = 2
The resource name for the Product to be removed from this ProductSet. Format is: `projects/PROJECT_ID/locations/LOC_ID/products/PRODUCT_ID`
Lists the Products in a ProductSet, in an unspecified order. If the ProductSet does not exist, the products field of the response will be empty. Possible errors: * Returns INVALID_ARGUMENT if page_size is greater than 100 or less than 1.
message
product_search_service.proto:678Request message for the `ListProductsInProductSet` method.
string name = 1
The ProductSet resource for which to retrieve Products. Format is: `projects/PROJECT_ID/locations/LOC_ID/productSets/PRODUCT_SET_ID`
int32 page_size = 2
The maximum number of items to return. Default 10, maximum 100.
string page_token = 3
The next_page_token returned from a previous List request, if any.
message
product_search_service.proto:693Response message for the `ListProductsInProductSet` method.
repeated products = 1
The list of Products.
string next_page_token = 2
Token to retrieve the next page of results, or empty if there are no more results in the list.
Asynchronous API that imports a list of reference images to specified product sets based on a list of image information. The [google.longrunning.Operation][google.longrunning.Operation] API can be used to keep track of the progress and results of the request. `Operation.metadata` contains `BatchOperationMetadata`. (progress) `Operation.response` contains `ImportProductSetsResponse`. (results) The input source of this method is a csv file on Google Cloud Storage. For the format of the csv file please see [ImportProductSetsGcsSource.csv_file_uri][google.cloud.vision.v1p3beta1.ImportProductSetsGcsSource.csv_file_uri].
message
product_search_service.proto:776Request message for the `ImportProductSets` method.
string parent = 1
The project in which the ProductSets should be imported. Format is `projects/PROJECT_ID/locations/LOC_ID`.
optional input_config = 2
The input content for the list of requests.
message
image_annotator.proto:643Response to a single file annotation request. A file may contain one or more images, which individually have their own responses.
optional input_config = 1
Information about the file for which this response is generated.
repeated responses = 2
Individual responses to images found within the file.
message
image_annotator.proto:566Request for performing Google Cloud Vision API tasks over a user-provided image, with user-requested features.
Used in:
optional image = 1
The image to be processed.
repeated features = 2
Requested features.
optional image_context = 3
Additional context that may accompany the image.
message
image_annotator.proto:589Response to an image annotation request.
Used in: ,
repeated face_annotations = 1
If present, face detection has completed successfully.
repeated landmark_annotations = 2
If present, landmark detection has completed successfully.
repeated logo_annotations = 3
If present, logo detection has completed successfully.
repeated label_annotations = 4
If present, label detection has completed successfully.
repeated localized_object_annotations = 22
If present, localized object detection has completed successfully. This will be sorted descending by confidence score.
repeated text_annotations = 5
If present, text (OCR) detection has completed successfully.
optional full_text_annotation = 12
If present, text (OCR) detection or document (OCR) text detection has completed successfully. This annotation provides the structural hierarchy for the OCR detected text.
optional safe_search_annotation = 6
If present, safe-search annotation has completed successfully.
optional image_properties_annotation = 8
If present, image properties were extracted successfully.
optional crop_hints_annotation = 11
If present, crop hints have completed successfully.
optional web_detection = 13
If present, web detection has completed successfully.
optional product_search_results = 14
If present, product search has completed successfully.
optional error = 9
If set, represents the error message for the operation. Note that filled-in image annotations are guaranteed to be correct, even when `error` is set.
optional context = 21
If present, contextual information is needed to understand where this image comes from.
message
image_annotator.proto:664An offline file annotation request.
Used in:
optional input_config = 1
Required. Information about the input file.
repeated features = 2
Required. Requested features.
optional image_context = 3
Additional context that may accompany the image(s) in the file.
optional output_config = 4
Required. The desired output location and metadata (e.g. format).
message
image_annotator.proto:679The response for a single offline file annotation request.
Used in:
optional output_config = 1
The output location and metadata from AsyncAnnotateFileRequest.
message
image_annotator.proto:692Response to an async batch file annotation request.
repeated responses = 1
The list of file annotation responses, one for each request in AsyncBatchAnnotateFilesRequest.
message
product_search_service.proto:810Metadata for the batch operations such as the current state. This is included in the `metadata` field of the `Operation` returned by the `GetOperation` call of the `google::longrunning::Operations` service.
BatchOperationMetadata.State state = 1
The current state of the batch operation.
optional submit_time = 2
The time when the batch request was submitted to the server.
optional end_time = 3
The time when the batch request is finished and [google.longrunning.Operation.done][google.longrunning.Operation.done] is set to true.
Enumerates the possible states that the batch request can be in.
Used in:
STATE_UNSPECIFIED = 0
Invalid.
PROCESSING = 1
Request is actively being processed.
SUCCESSFUL = 2
The request is done and at least one item has been successfully processed.
FAILED = 3
The request is done and no item has been successfully processed.
CANCELLED = 4
The request is done after the longrunning.Operations.CancelOperation has been called by the user. Any records that were processed before the cancel command are output as specified in the request.
message
text_annotation.proto:116Logical element on the page.
Used in:
optional property = 1
Additional information detected for the block.
optional bounding_box = 2
The bounding box for the block. The vertices are in the order of top-left, top-right, bottom-right, bottom-left. When a rotation of the bounding box is detected the rotation is represented as around the top-left corner as defined when the text is read in the 'natural' orientation. For example: * when the text is horizontal it might look like: 0----1 | | 3----2 * when it's rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertice order will still be (0, 1, 2, 3).
repeated paragraphs = 3
List of paragraphs in this block (if this blocks is of type text).
Block.BlockType block_type = 4
Detected block type (text, image etc) for this block.
float confidence = 5
Confidence of the OCR results on the block. Range [0, 1].
Type of a block (text, image etc) as identified by OCR.
Used in:
UNKNOWN = 0
Unknown block type.
TEXT = 1
Regular text block.
TABLE = 2
Table block.
PICTURE = 3
Image block.
RULER = 4
Horizontal/vertical line box.
BARCODE = 5
Barcode block.
message
geometry.proto:49A bounding polygon for the detected image annotation.
Used in: , , , , , , , , ,
repeated vertices = 1
The bounding polygon vertices.
repeated normalized_vertices = 2
The bounding polygon normalized vertices.
message
image_annotator.proto:478Color information consists of RGB channels, score, and the fraction of the image that the color occupies in the image.
Used in:
optional color = 1
RGB components of the color.
float score = 2
Image-specific score for this color. Value in range [0, 1].
float pixel_fraction = 3
The fraction of pixels the color occupies in the image. Value in range [0, 1].
message
image_annotator.proto:503Single crop hint that is used to generate a new crop when serving an image.
Used in:
optional bounding_poly = 1
The bounding polygon for the crop region. The coordinates of the bounding box are in the original image's scale, as returned in `ImageParams`.
float confidence = 2
Confidence of this being a salient region. Range [0, 1].
float importance_fraction = 3
Fraction of importance of this salient region with respect to the original image.
message
image_annotator.proto:517Set of crop hints that are used to generate new crops when serving images.
Used in:
repeated crop_hints = 1
Crop hint results.
message
image_annotator.proto:523Parameters for crop hints annotation request.
Used in:
repeated float aspect_ratios = 1
Aspect ratios in floats, representing the ratio of the width to the height of the image. For example, if the desired aspect ratio is 4/3, the corresponding float value should be 1.33333. If not specified, the best possible crop is returned. The number of provided aspect ratios is limited to a maximum of 16; any aspect ratios provided after the 16th are ignored.
message
image_annotator.proto:491Set of dominant colors and their corresponding scores.
Used in:
repeated colors = 1
RGB color values with their score and pixel fraction.
message
image_annotator.proto:374Set of detected entity features.
Used in:
string mid = 1
Opaque entity ID. Some IDs may be available in [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).
string locale = 2
The language code for the locale in which the entity textual `description` is expressed.
string description = 3
Entity textual description, expressed in its `locale` language.
float score = 4
Overall score of the result. Range [0, 1].
float confidence = 5
**Deprecated. Use `score` instead.** The accuracy of the entity detection in an image. For example, for an image in which the "Eiffel Tower" entity is detected, this field represents the confidence that there is a tower in the query image. Range [0, 1].
float topicality = 6
The relevancy of the ICA (Image Content Annotation) label to the image. For example, the relevancy of "tower" is likely higher to an image containing the detected "Eiffel Tower" than to an image containing a detected distant towering building, even though the confidence that there is a tower in each image may be the same. Range [0, 1].
optional bounding_poly = 7
Image region to which this entity belongs. Not produced for `LABEL_DETECTION` features.
repeated locations = 8
The location information for the detected entity. Multiple `LocationInfo` elements can be present because one location may indicate the location of the scene in the image, and another location may indicate the location of the place where the image was taken. Location information is usually present for landmarks.
repeated properties = 9
Some entities may have optional user-supplied `Property` (name/value) fields, such a score or string that qualifies the entity.
message
image_annotator.proto:172A face annotation object contains the results of face detection.
Used in:
optional bounding_poly = 1
The bounding polygon around the face. The coordinates of the bounding box are in the original image's scale, as returned in `ImageParams`. The bounding box is computed to "frame" the face in accordance with human expectations. It is based on the landmarker results. Note that one or more x and/or y coordinates may not be generated in the `BoundingPoly` (the polygon will be unbounded) if only a partial face appears in the image to be annotated.
optional fd_bounding_poly = 2
The `fd_bounding_poly` bounding polygon is tighter than the `boundingPoly`, and encloses only the skin part of the face. Typically, it is used to eliminate the face from any image analysis that detects the "amount of skin" visible in an image. It is not based on the landmarker results, only on the initial face detection, hence the <code>fd</code> (face detection) prefix.
repeated landmarks = 3
Detected face landmarks.
float roll_angle = 4
Roll angle, which indicates the amount of clockwise/anti-clockwise rotation of the face relative to the image vertical about the axis perpendicular to the face. Range [-180,180].
float pan_angle = 5
Yaw angle, which indicates the leftward/rightward angle that the face is pointing relative to the vertical plane perpendicular to the image. Range [-180,180].
float tilt_angle = 6
Pitch angle, which indicates the upwards/downwards angle that the face is pointing relative to the image's horizontal plane. Range [-180,180].
float detection_confidence = 7
Detection confidence. Range [0, 1].
float landmarking_confidence = 8
Face landmarking confidence. Range [0, 1].
Likelihood joy_likelihood = 9
Joy likelihood.
Likelihood sorrow_likelihood = 10
Sorrow likelihood.
Likelihood anger_likelihood = 11
Anger likelihood.
Likelihood surprise_likelihood = 12
Surprise likelihood.
Likelihood under_exposed_likelihood = 13
Under-exposed likelihood.
Likelihood blurred_likelihood = 14
Blurred likelihood.
Likelihood headwear_likelihood = 15
Headwear likelihood.
message
image_annotator.proto:174A face-specific landmark (for example, a face feature).
Used in:
Landmark.Type type = 3
Face landmark type.
optional position = 4
Face landmark position.
Face landmark (feature) type. Left and right are defined from the vantage of the viewer of the image without considering mirror projections typical of photos. So, `LEFT_EYE`, typically, is the person's right eye.
Used in:
UNKNOWN_LANDMARK = 0
Unknown face landmark detected. Should not be filled.
LEFT_EYE = 1
Left eye.
RIGHT_EYE = 2
Right eye.
LEFT_OF_LEFT_EYEBROW = 3
Left of left eyebrow.
RIGHT_OF_LEFT_EYEBROW = 4
Right of left eyebrow.
LEFT_OF_RIGHT_EYEBROW = 5
Left of right eyebrow.
RIGHT_OF_RIGHT_EYEBROW = 6
Right of right eyebrow.
MIDPOINT_BETWEEN_EYES = 7
Midpoint between eyes.
NOSE_TIP = 8
Nose tip.
UPPER_LIP = 9
Upper lip.
LOWER_LIP = 10
Lower lip.
MOUTH_LEFT = 11
Mouth left.
MOUTH_RIGHT = 12
Mouth right.
MOUTH_CENTER = 13
Mouth center.
NOSE_BOTTOM_RIGHT = 14
Nose, bottom right.
NOSE_BOTTOM_LEFT = 15
Nose, bottom left.
NOSE_BOTTOM_CENTER = 16
Nose, bottom center.
LEFT_EYE_TOP_BOUNDARY = 17
Left eye, top boundary.
LEFT_EYE_RIGHT_CORNER = 18
Left eye, right corner.
LEFT_EYE_BOTTOM_BOUNDARY = 19
Left eye, bottom boundary.
LEFT_EYE_LEFT_CORNER = 20
Left eye, left corner.
RIGHT_EYE_TOP_BOUNDARY = 21
Right eye, top boundary.
RIGHT_EYE_RIGHT_CORNER = 22
Right eye, right corner.
RIGHT_EYE_BOTTOM_BOUNDARY = 23
Right eye, bottom boundary.
RIGHT_EYE_LEFT_CORNER = 24
Right eye, left corner.
LEFT_EYEBROW_UPPER_MIDPOINT = 25
Left eyebrow, upper midpoint.
RIGHT_EYEBROW_UPPER_MIDPOINT = 26
Right eyebrow, upper midpoint.
LEFT_EAR_TRAGION = 27
Left ear tragion.
RIGHT_EAR_TRAGION = 28
Right ear tragion.
LEFT_EYE_PUPIL = 29
Left eye pupil.
RIGHT_EYE_PUPIL = 30
Right eye pupil.
FOREHEAD_GLABELLA = 31
Forehead glabella.
CHIN_GNATHION = 32
Chin gnathion.
CHIN_LEFT_GONION = 33
Chin left gonion.
CHIN_RIGHT_GONION = 34
Chin right gonion.
message
image_annotator.proto:67The type of Google Cloud Vision API detection to perform, and the maximum number of results to return for that type. Multiple `Feature` objects can be specified in the `features` list.
Used in: ,
Feature.Type type = 1
The feature type.
int32 max_results = 2
Maximum number of results of this type. Does not apply to `TEXT_DETECTION`, `DOCUMENT_TEXT_DETECTION`, or `CROP_HINTS`.
string model = 3
Model to use for the feature. Supported values: "builtin/stable" (the default if unset) and "builtin/latest".
Type of Google Cloud Vision API feature to be extracted.
Used in:
TYPE_UNSPECIFIED = 0
Unspecified feature type.
FACE_DETECTION = 1
Run face detection.
LANDMARK_DETECTION = 2
Run landmark detection.
LOGO_DETECTION = 3
Run logo detection.
LABEL_DETECTION = 4
Run label detection.
TEXT_DETECTION = 5
Run text detection / optical character recognition (OCR). Text detection is optimized for areas of text within a larger image; if the image is a document, use `DOCUMENT_TEXT_DETECTION` instead.
DOCUMENT_TEXT_DETECTION = 11
Run dense text document OCR. Takes precedence when both `DOCUMENT_TEXT_DETECTION` and `TEXT_DETECTION` are present.
SAFE_SEARCH_DETECTION = 6
Run Safe Search to detect potentially unsafe or undesirable content.
IMAGE_PROPERTIES = 7
Compute a set of image properties, such as the image's dominant colors.
CROP_HINTS = 9
Run crop hints.
WEB_DETECTION = 10
Run web detection.
PRODUCT_SEARCH = 12
Run Product Search.
OBJECT_LOCALIZATION = 19
Run localizer for object detection.
message
image_annotator.proto:735The Google Cloud Storage location where the output will be written to.
Used in:
string uri = 1
Google Cloud Storage URI where the results will be stored. Results will be in JSON format and preceded by its corresponding input URI. This field can either represent a single file, or a prefix for multiple outputs. Prefixes must end in a `/`. Examples: * File: gs://bucket-name/filename.json * Prefix: gs://bucket-name/prefix/here/ * File: gs://bucket-name/prefix/here If multiple outputs, each response is still AnnotateFileResponse, each of which contains some subset of the full list of AnnotateImageResponse. Multiple outputs can happen if, for example, the output JSON is too large and overflows into multiple sharded files.
message
image_annotator.proto:728The Google Cloud Storage location where the input will be read from.
Used in:
string uri = 1
Google Cloud Storage URI for the input file. This must only be a Google Cloud Storage object. Wildcards are not currently supported.
message
image_annotator.proto:159Client image to perform Google Cloud Vision API tasks over.
Used in:
bytes content = 1
Image content, represented as a stream of bytes. Note: As with all `bytes` fields, protobuffers use a pure binary representation, whereas JSON representations use base64.
optional source = 2
Google Cloud Storage image location, or publicly-accessible image URL. If both `content` and `source` are provided for an image, `content` takes precedence and is used to perform the image annotation request.
message
image_annotator.proto:579If an image was produced from a file (e.g. a PDF), this message gives information about the source of that image.
Used in:
string uri = 1
The URI of the file used to produce the image.
int32 page_number = 2
If the file was a PDF or TIFF, this field gives the page number within the file used to produce the image.
message
image_annotator.proto:540Image context and/or feature-specific parameters.
Used in: ,
optional lat_long_rect = 1
Not used.
repeated string language_hints = 2
List of languages to use for TEXT_DETECTION. In most cases, an empty value yields the best results since it enables automatic language detection. For languages based on the Latin alphabet, setting `language_hints` is not needed. In rare cases, when the language of the text in the image is known, setting a hint will help get better results (although it will be a significant hindrance if the hint is wrong). Text detection returns an error if one or more of the specified languages is not one of the [supported languages](/vision/docs/languages).
optional crop_hints_params = 4
Parameters for crop hints annotation request.
optional product_search_params = 5
Parameters for product search.
optional web_detection_params = 6
Parameters for web detection.
message
image_annotator.proto:497Stores image properties, such as dominant colors.
Used in:
optional dominant_colors = 1
If present, dominant colors completed successfully.
message
image_annotator.proto:129External image source (Google Cloud Storage or web URL image location).
Used in:
string gcs_image_uri = 1
**Use `image_uri` instead.** The Google Cloud Storage URI of the form `gs://bucket_name/object_name`. Object versioning is not supported. See [Google Cloud Storage Request URIs](https://cloud.google.com/storage/docs/reference-uris) for more info.
string image_uri = 2
The URI of the source image. Can be either: 1. A Google Cloud Storage URI of the form `gs://bucket_name/object_name`. Object versioning is not supported. See [Google Cloud Storage Request URIs](https://cloud.google.com/storage/docs/reference-uris) for more info. 2. A publicly-accessible image HTTP/HTTPS URL. When fetching images from HTTP/HTTPS URLs, Google cannot guarantee that the request will be completed. Your request may fail if the specified host denies the request (e.g. due to request throttling or DOS prevention), or if Google throttles requests to the site for abuse prevention. You should not depend on externally-hosted images for production applications. When both `gcs_image_uri` and `image_uri` are specified, `image_uri` takes precedence.
message
product_search_service.proto:704The Google Cloud Storage location for a csv file which preserves a list of ImportProductSetRequests in each line.
Used in:
string csv_file_uri = 1
The Google Cloud Storage URI of the input csv file. The URI must start with gs:// The format of the input csv file should be one image per line. In each line, there are 6 columns. 1. image_uri 2, image_id 3. product_set_id 4. product_id 5, product_category 6, product_display_name 7, labels 8. bounding_poly Columns 1, 3, 4, and 5 are required, other columns are optional. A new ProductSet/Product with the same id will be created on the fly if the ProductSet/Product specified by product_set_id/product_id does not exist. The image_id field is optional but has to be unique if provided. If it is empty, we will automatically assign an unique id to the image. The product_display_name field is optional. If it is empty, a space (" ") is used as the place holder for the product display_name, which can be updated later through the realtime API. If the Product with product_id already exists, the fields product_display_name, product_category and labels are ignored. If a Product doesn't exist and needs to be created on the fly, the product_display_name field refers to [Product.display_name][google.cloud.vision.v1p3beta1.Product.display_name], the product_category field refers to [Product.product_category][google.cloud.vision.v1p3beta1.Product.product_category], and the labels field refers to [Product.labels][]. Labels (optional) should be a line containing a list of comma-separated key-value pairs, with the format "key_1=value_1,key_2=value_2,...,key_n=value_n". The bounding_poly (optional) field is used to identify one region of interest from the image in the same manner as CreateReferenceImage. If no bounding_poly is specified, the system will try to detect regions of interest automatically. Note that the pipeline will resize the image if the image resolution is too large to process (above 20MP). Also note that at most one bounding_poly is allowed per line. If the image contains multiple regions of interest, the csv should contain one line per region of interest. The bounding_poly column should contain an even number of comma-separated numbers, with the format "p1_x,p1_y,p2_x,p2_y,...,pn_x,pn_y". Nonnegative integers should be used for absolute bounding polygons, and float values in [0, 1] should be used for normalized bounding polygons.
message
product_search_service.proto:766The input content for the `ImportProductSets` method.
Used in:
oneof source
The source of the input.
gcs_source = 1
The Google Cloud Storage location for a csv file which preserves a list of ImportProductSetRequests in each line.
message
product_search_service.proto:793Response message for the `ImportProductSets` method. This message is returned by the [google.longrunning.Operations.GetOperation][google.longrunning.Operations.GetOperation] method in the returned [google.longrunning.Operation.response][google.longrunning.Operation.response] field.
repeated reference_images = 1
The list of reference_images that are imported successfully.
repeated statuses = 2
The rpc status for each ImportProductSet request, including both successes and errors. The number of statuses here matches the number of lines in the csv file, and statuses[i] stores the success or failure status of processing the i-th line of the csv, starting from line 0.
message
image_annotator.proto:699The desired input location and metadata.
Used in: ,
optional gcs_source = 1
The Google Cloud Storage location to read the input from.
string mime_type = 2
The type of the file. Currently only "application/pdf" and "image/tiff" are supported. Wildcards are not supported.
message
image_annotator.proto:468Rectangle determined by min and max `LatLng` pairs.
Used in:
optional min_lat_lng = 1
Min lat/long pair.
optional max_lat_lng = 2
Max lat/long pair.
A bucketized representation of likelihood, which is intended to give clients highly stable results across model upgrades.
Used in: ,
UNKNOWN = 0
Unknown likelihood.
VERY_UNLIKELY = 1
It is very unlikely that the image belongs to the specified vertical.
UNLIKELY = 2
It is unlikely that the image belongs to the specified vertical.
POSSIBLE = 3
It is possible that the image belongs to the specified vertical.
LIKELY = 4
It is likely that the image belongs to the specified vertical.
VERY_LIKELY = 5
It is very likely that the image belongs to the specified vertical.
message
image_annotator.proto:421Set of detected objects with bounding boxes.
Used in:
string mid = 1
Object ID that should align with EntityAnnotation mid.
string language_code = 2
The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
string name = 3
Object name, expressed in its `language_code` language.
float score = 4
Score of the result. Range [0, 1].
optional bounding_poly = 5
Image region to which this object belongs. This must be populated.
message
image_annotator.proto:356Detected entity location information.
Used in:
optional lat_lng = 1
lat/long location coordinates.
message
geometry.proto:58A normalized bounding polygon around a portion of an image.
Used in:
repeated vertices = 1
Normalized vertices of the bounding polygon.
message
geometry.proto:40A vertex represents a 2D point in the image. NOTE: the normalized vertex coordinates are relative to the original image and range from 0 to 1.
Used in: ,
float x = 1
X coordinate.
float y = 2
Y coordinate.
message
image_annotator.proto:777Contains metadata for the BatchAnnotateImages operation.
OperationMetadata.State state = 1
Current state of the batch operation.
optional create_time = 5
The time when the batch request was received.
optional update_time = 6
The time when the operation result was last updated.
Batch operation states.
Used in:
STATE_UNSPECIFIED = 0
Invalid.
CREATED = 1
Request is received.
RUNNING = 2
Request is actively being processed.
DONE = 3
The batch processing is done.
CANCELLED = 4
The batch processing was cancelled.
message
image_annotator.proto:709The desired output location and metadata.
Used in: ,
optional gcs_destination = 1
The Google Cloud Storage location to write the output(s) to.
int32 batch_size = 2
The max number of response protos to put into each output JSON file on Google Cloud Storage. The valid range is [1, 100]. If not specified, the default value is 20. For example, for one pdf file with 100 pages, 100 response protos will be generated. If `batch_size` = 20, then 5 json files each containing 20 response protos will be written under the prefix `gcs_destination`.`uri`. Currently, batch_size only applies to GcsDestination, with potential future support for other output configurations.
message
text_annotation.proto:96Detected page from OCR.
Used in:
optional property = 1
Additional information detected on the page.
int32 width = 2
Page width. For PDFs the unit is points. For images (including TIFFs) the unit is pixels.
int32 height = 3
Page height. For PDFs the unit is points. For images (including TIFFs) the unit is pixels.
repeated blocks = 4
List of blocks of text, images etc on this page.
float confidence = 5
Confidence of the OCR results on the page. Range [0, 1].
message
text_annotation.proto:174Structural unit of text representing a number of words in certain order.
Used in:
optional property = 1
Additional information detected for the paragraph.
optional bounding_box = 2
The bounding box for the paragraph. The vertices are in the order of top-left, top-right, bottom-right, bottom-left. When a rotation of the bounding box is detected the rotation is represented as around the top-left corner as defined when the text is read in the 'natural' orientation. For example: * when the text is horizontal it might look like: 0----1 | | 3----2 * when it's rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertice order will still be (0, 1, 2, 3).
repeated words = 3
List of words in this paragraph.
float confidence = 4
Confidence of the OCR results for the paragraph. Range [0, 1].
message
geometry.proto:66A 3D position in the image, used primarily for Face detection landmarks. A valid Position must have both x and y coordinates. The position coordinates are in the same scale as the original image.
Used in:
float x = 1
X coordinate.
float y = 2
Y coordinate.
float z = 3
Z coordinate (or depth).
message
product_search_service.proto:326A Product contains ReferenceImages.
Used as response type in: ProductSearch.CreateProduct, ProductSearch.GetProduct, ProductSearch.UpdateProduct
Used as field type in: , , , ,
string name = 1
The resource name of the product. Format is: `projects/PROJECT_ID/locations/LOC_ID/products/PRODUCT_ID`. This field is ignored when creating a product.
string display_name = 2
The user-provided name for this Product. Must not be empty. Must be at most 4096 characters long.
string description = 3
User-provided metadata to be stored with this product. Must be at most 4096 characters long.
string product_category = 4
The category for the product identified by the reference image. This should be either "homegoods" or "apparel". This field is immutable.
repeated product_labels = 5
Key-value pairs that can be attached to a product. At query time, constraints can be specified based on the product_labels. Note that integer values can be provided as strings, e.g. "1199". Only strings with integer values can match a range-based restriction which is to be supported soon. Multiple values can be assigned to the same key. One product may have up to 100 product_labels.
message
product_search_service.proto:328A product label represented as a key-value pair.
Used in:
string key = 1
The key of the label attached to the product. Cannot be empty and cannot exceed 128 bytes.
string value = 2
The value of the label attached to the product. Cannot be empty and cannot exceed 128 bytes.
Supported product search categories.
Used in: ,
PRODUCT_SEARCH_CATEGORY_UNSPECIFIED = 0
Default value used when a category is not specified.
SHOES = 1
Shoes category.
BAGS = 2
Bags category.
message
product_search.proto:31Parameters for a product search request.
Used in:
string catalog_name = 1
The resource name of the catalog to search. Format is: `productSearch/catalogs/CATALOG_NAME`.
ProductSearchCategory category = 2
The category to search in. Optional. It is inferred by the system if it is not specified. [Deprecated] Use `product_category`.
string product_category = 5
The product category to search in. Optional. It is inferred by the system if it is not specified. Supported values are `bag`, `shoe`, `sunglasses`, `dress`, `outerwear`, `skirt`, `top`, `shorts`, and `pants`.
optional normalized_bounding_poly = 3
The bounding polygon around the area of interest in the image. Optional. If it is not specified, system discretion will be applied. [Deprecated] Use `bounding_poly`.
optional bounding_poly = 9
The bounding polygon around the area of interest in the image. Optional. If it is not specified, system discretion will be applied.
ProductSearchResultsView view = 4
Specifies the verbosity of the product search results. Optional. Defaults to `BASIC`.
string product_set = 6
The resource name of a [ProductSet][google.cloud.vision.v1p3beta1.ProductSet] to be searched for similar images. Format is: `projects/PROJECT_ID/locations/LOC_ID/productSets/PRODUCT_SET_ID`.
repeated string product_categories = 7
The list of product categories to search in. Currently, we only consider the first category, and either "homegoods" or "apparel" should be specified.
string filter = 8
The filtering expression. This can be used to restrict search results based on Product labels. We currently support an AND of OR of key-value expressions, where each expression within an OR must have the same key. For example, "(color = red OR color = blue) AND brand = Google" is acceptable, but not "(color = red OR brand = Google)" or "color: red".
message
product_search.proto:84Results for a product search request.
Used in:
ProductSearchCategory category = 1
Product category. [Deprecated] Use `product_category`.
string product_category = 4
Product category. Supported values are `bag` and `shoe`. [Deprecated] `product_category` is provided in each Product.
optional index_time = 2
Timestamp of the index which provided these results. Changes made after this time are not reflected in the current results.
repeated products = 3
List of detected products.
repeated results = 5
List of results, one for each product match.
message
product_search.proto:86Information about a product.
Used in:
string product_id = 1
Product ID.
string image_uri = 2
The URI of the image which matched the query image. This field is returned only if `view` is set to `FULL` in the request.
float score = 3
A confidence level on the match, ranging from 0 (no confidence) to 1 (full confidence). This field is returned only if `view` is set to `FULL` in the request.
message
product_search.proto:105Information about a product.
Used in:
optional product = 1
The Product.
float score = 2
A confidence level on the match, ranging from 0 (no confidence) to 1 (full confidence). This field is returned only if `view` is set to `FULL` in the request.
string image = 3
The resource name of the image from the product that is the closest match to the query.
Specifies the fields to include in product search results.
Used in:
BASIC = 0
Product search results contain only `product_category` and `product_id`. Default value.
FULL = 1
Product search results contain `product_category`, `product_id`, `image_uri`, and `score`.
message
product_search_service.proto:375A ProductSet contains Products. A ProductSet can contain a maximum of 1 million reference images. If the limit is exceeded, periodic indexing will fail.
Used as response type in: ProductSearch.CreateProductSet, ProductSearch.GetProductSet, ProductSearch.UpdateProductSet
Used as field type in: , ,
string name = 1
The resource name of the ProductSet. Format is: `projects/PROJECT_ID/locations/LOC_ID/productSets/PRODUCT_SET_ID`. This field is ignored when creating a ProductSet.
string display_name = 2
The user-provided name for this ProductSet. Must not be empty. Must be at most 4096 characters long.
optional index_time = 3
Output only. The time at which this ProductSet was last indexed. Query results will reflect all updates before this time. If this ProductSet has never been indexed, this field is 0. This field is ignored when creating a ProductSet.
optional index_error = 4
Output only. If there was an error with indexing the product set, the field is populated. This field is ignored when creating a ProductSet.
message
image_annotator.proto:362A `Property` consists of a user-supplied name/value pair.
Used in:
string name = 1
Name of the property.
string value = 2
Value of the property.
uint64 uint64_value = 3
Value of numeric properties.
message
product_search_service.proto:404A `ReferenceImage` represents a product image and its associated metadata, such as bounding boxes.
Used as response type in: ProductSearch.CreateReferenceImage, ProductSearch.GetReferenceImage
Used as field type in: , ,
string name = 1
The resource name of the reference image. Format is: `projects/PROJECT_ID/locations/LOC_ID/products/PRODUCT_ID/referenceImages/IMAGE_ID`. This field is ignored when creating a reference image.
string uri = 2
The Google Cloud Storage URI of the reference image. The URI must start with `gs://`. Required.
repeated bounding_polys = 3
Bounding polygons around the areas of interest in the reference image. Optional. If this field is empty, the system will try to detect regions of interest. At most 10 bounding polygons will be used. The provided shape is converted into a non-rotated rectangle. Once converted, the small edge of the rectangle must be greater than or equal to 300 pixels. The aspect ratio must be 1:4 or less (i.e. 1:3 is ok; 1:5 is not).
message
image_annotator.proto:443Set of features pertaining to the image, computed by computer vision methods over safe-search verticals (for example, adult, spoof, medical, violence).
Used in:
Likelihood adult = 1
Represents the adult content likelihood for the image. Adult content may contain elements such as nudity, pornographic images or cartoons, or sexual activities.
Likelihood spoof = 2
Spoof likelihood. The likelihood that an modification was made to the image's canonical version to make it appear funny or offensive.
Likelihood medical = 3
Likelihood that this is a medical image.
Likelihood violence = 4
Likelihood that this image contains violent content.
Likelihood racy = 9
Likelihood that the request image contains racy content. Racy content may include (but is not limited to) skimpy or sheer clothing, strategically covered nudity, lewd or provocative poses, or close-ups of sensitive body areas.
message
text_annotation.proto:233A single symbol representation.
Used in:
optional property = 1
Additional information detected for the symbol.
optional bounding_box = 2
The bounding box for the symbol. The vertices are in the order of top-left, top-right, bottom-right, bottom-left. When a rotation of the bounding box is detected the rotation is represented as around the top-left corner as defined when the text is read in the 'natural' orientation. For example: * when the text is horizontal it might look like: 0----1 | | 3----2 * when it's rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertice order will still be (0, 1, 2, 3).
string text = 3
The actual UTF-8 representation of the symbol.
float confidence = 4
Confidence of the OCR results for the symbol. Range [0, 1].
message
text_annotation.proto:36TextAnnotation contains a structured representation of OCR extracted text. The hierarchy of an OCR extracted text structure is like this: TextAnnotation -> Page -> Block -> Paragraph -> Word -> Symbol Each structural component, starting from Page, may further have their own properties. Properties describe detected languages, breaks etc.. Please refer to the [TextAnnotation.TextProperty][google.cloud.vision.v1p3beta1.TextAnnotation.TextProperty] message definition below for more detail.
Used in:
repeated pages = 1
List of pages detected by OCR.
string text = 2
UTF-8 text detected on the pages.
message
text_annotation.proto:49Detected start or end of a structural component.
Used in:
DetectedBreak.BreakType type = 1
Detected break type.
bool is_prefix = 2
True if break prepends the element.
Enum to denote the type of break found. New line, space etc.
Used in:
UNKNOWN = 0
Unknown break label type.
SPACE = 1
Regular space.
SURE_SPACE = 2
Sure space (very wide).
EOL_SURE_SPACE = 3
Line-wrapping break.
HYPHEN = 4
End-line hyphen that is not present in text; does not co-occur with `SPACE`, `LEADER_SPACE`, or `LINE_BREAK`.
LINE_BREAK = 5
Line break that ends a paragraph.
message
text_annotation.proto:38Detected language for a structural component.
Used in:
string language_code = 1
The BCP-47 language code, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
float confidence = 2
Confidence of detected language. Range [0, 1].
message
text_annotation.proto:80Additional information detected on the structural component.
Used in: , , , ,
repeated detected_languages = 1
A list of detected languages together with confidence.
optional detected_break = 2
Detected start or end of a text segment.
message
geometry.proto:29A vertex represents a 2D point in the image. NOTE: the vertex coordinates are in the same scale as the original image.
Used in:
int32 x = 1
X coordinate.
int32 y = 2
Y coordinate.
message
web_detection.proto:28Relevant information for the image from the Internet.
Used in:
repeated web_entities = 1
Deduced entities from similar images on the Internet.
repeated full_matching_images = 2
Fully matching images from the Internet. Can include resized copies of the query image.
repeated partial_matching_images = 3
Partial matching images from the Internet. Those images are similar enough to share some key-point features. For example an original image will likely have partial matching for its crops.
repeated pages_with_matching_images = 4
Web pages containing the matching images from the Internet.
repeated visually_similar_images = 6
The visually similar image results.
repeated best_guess_labels = 8
Best guess text labels for the request image.
message
web_detection.proto:30Entity deduced from similar images on the Internet.
Used in:
string entity_id = 1
Opaque entity ID.
float score = 2
Overall relevancy score for the entity. Not normalized and not comparable across different image queries.
string description = 3
Canonical description of the entity, in English.
message
web_detection.proto:43Metadata for online images.
Used in: ,
string url = 1
The result image URL.
float score = 2
(Deprecated) Overall relevancy score for the image.
message
web_detection.proto:74Label to provide extra metadata for the web detection.
Used in:
string label = 1
Label for extra metadata.
string language_code = 2
The BCP-47 language code for `label`, such as "en-US" or "sr-Latn". For more information, see http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.
message
web_detection.proto:52Metadata for web pages.
Used in:
string url = 1
The result web page URL.
float score = 2
(Deprecated) Overall relevancy score for the web page.
string page_title = 3
Title for the web page, may contain HTML markups.
repeated full_matching_images = 4
Fully matching images on the page. Can include resized copies of the query image.
repeated partial_matching_images = 5
Partial matching images on the page. Those images are similar enough to share some key-point features. For example an original image will likely have partial matching for its crops.
message
image_annotator.proto:534Parameters for web detection request.
Used in:
bool include_geo_results = 2
Whether to include results derived from the geo information in the image.
message
text_annotation.proto:203A word representation.
Used in:
optional property = 1
Additional information detected for the word.
optional bounding_box = 2
The bounding box for the word. The vertices are in the order of top-left, top-right, bottom-right, bottom-left. When a rotation of the bounding box is detected the rotation is represented as around the top-left corner as defined when the text is read in the 'natural' orientation. For example: * when the text is horizontal it might look like: 0----1 | | 3----2 * when it's rotated 180 degrees around the top-left corner it becomes: 2----3 | | 1----0 and the vertice order will still be (0, 1, 2, 3).
repeated symbols = 3
List of symbols in the word. The order of the symbols follows the natural reading order.
float confidence = 4
Confidence of the OCR results for the word. Range [0, 1].