ImageContext

Image context and/or feature-specific parameters.

JSON representation
{
  "latLongRect": {
    object (LatLongRect)
  },
  "languageHints": [
    string
  ],
  "cropHintsParams": {
    object (CropHintsParams)
  },
  "faceRecognitionParams": {
    object (FaceRecognitionParams)
  },
  "productSearchParams": {
    object (ProductSearchParams)
  },
  "webDetectionParams": {
    object (WebDetectionParams)
  },
  "textDetectionParams": {
    object (TextDetectionParams)
  }
}
Fields
latLongRect

object (LatLongRect)

Not used.

languageHints[]

string

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 languageHints 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.

cropHintsParams

object (CropHintsParams)

Parameters for crop hints annotation request.

faceRecognitionParams

object (FaceRecognitionParams)

Parameters for face recognition.

productSearchParams

object (ProductSearchParams)

Parameters for product search.

webDetectionParams

object (WebDetectionParams)

Parameters for web detection.

textDetectionParams

object (TextDetectionParams)

Parameters for text detection and document text detection.

LatLongRect

Rectangle determined by min and max LatLng pairs.

JSON representation
{
  "minLatLng": {
    object (LatLng)
  },
  "maxLatLng": {
    object (LatLng)
  }
}
Fields
minLatLng

object (LatLng)

Min lat/long pair.

maxLatLng

object (LatLng)

Max lat/long pair.

CropHintsParams

Parameters for crop hints annotation request.

JSON representation
{
  "aspectRatios": [
    number
  ]
}
Fields
aspectRatios[]

number

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.

FaceRecognitionParams

Parameters for a celebrity recognition request.

JSON representation
{
  "celebritySet": [
    string
  ]
}
Fields
celebritySet[]

string

The resource names for one or more CelebritySets. A celebrity set is preloaded and can be specified as "builtin/default". If this is specified, the algorithm will try to match the faces detected in the input image to the Celebrities in the CelebritySets.

ProductSearchParams

Parameters for a product search request.

JSON representation
{
  "boundingPoly": {
    object (BoundingPoly)
  },
  "productSet": string,
  "productCategories": [
    string
  ],
  "filter": string
}
Fields
boundingPoly

object (BoundingPoly)

The bounding polygon around the area of interest in the image. If it is not specified, system discretion will be applied.

productSet

string

The resource name of a ProductSet to be searched for similar images.

Format is: projects/PROJECT_ID/locations/LOC_ID/productSets/PRODUCT_SET_ID.

productCategories[]

string

The list of product categories to search in. Currently, we only consider the first category, and either "homegoods-v2", "apparel-v2", "toys-v2", "packagedgoods-v1", or "general-v1" should be specified. The legacy categories "homegoods", "apparel", and "toys" are still supported but will be deprecated. For new products, please use "homegoods-v2", "apparel-v2", or "toys-v2" for better product search accuracy. It is recommended to migrate existing products to these categories as well.

filter

string

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. An '=' should be used to connect the key and value.

For example, "(color = red OR color = blue) AND brand = Google" is acceptable, but "(color = red OR brand = Google)" is not acceptable. "color: red" is not acceptable because it uses a ':' instead of an '='.

WebDetectionParams

Parameters for web detection request.

JSON representation
{
  "includeGeoResults": boolean
}
Fields
includeGeoResults

boolean

Whether to include results derived from the geo information in the image.

TextDetectionParams

Parameters for text detections. This is used to control TEXT_DETECTION and DOCUMENT_TEXT_DETECTION features.

JSON representation
{
  "disableOrientationDetection": boolean,
  "disableTextAnnotations": boolean,
  "pageFilter": string,
  "blockFilter": string,
  "paragraphFilter": string,
  "lineFilter": string,
  "wordFilter": string,
  "symbolFilter": string,
  "enableTextDetectionConfidenceScore": boolean
}
Fields
disableOrientationDetection

boolean

Disables orientation detection such that rotated text will not be detected. This is only supported for DOCUMENT_TEXT_DETECTION.

disableTextAnnotations

boolean

Disables the old textAnnotations field. Only full_text_annotations will be returned.

pageFilter

string (FieldMask format)

Controls what data is returned at the page level in fullTextAnnotation.

Example: "pageFilter": { "paths": ["confidence", "mergedText"] }

The above will return Page objects with only the "confidence" and "mergedText" fields populated. This can save bandwidth and storage for unnecessary data.

Default when unset: All fields are included

A comma-separated list of fully qualified names of fields. Example: "user.displayName,photo".

blockFilter

string (FieldMask format)

Controls what data is returned at the block level in fullTextAnnotation.

Example: "blockFilter": { "paths": ["confidence", "mergedText"] }

The above will return Block objects with only the "confidence" and "mergedText" fields populated. This can save bandwidth and storage for unnecessary data.

Default when unset: All fields are included except mergedText.

A comma-separated list of fully qualified names of fields. Example: "user.displayName,photo".

paragraphFilter

string (FieldMask format)

Controls what data is returned at the paragraph level in fullTextAnnotation.

Example: "paragraphFilter": { "paths": ["confidence", "mergedText"] }

The above will return Paragraph objects with only the "confidence" and "mergedText" fields populated. This can save bandwidth and storage for unnecessary data.

Default when unset: All fields are included except mergedText and lines

A comma-separated list of fully qualified names of fields. Example: "user.displayName,photo".

lineFilter

string (FieldMask format)

Controls what data is returned at the line level in fullTextAnnotation. If this field is specified, the lines field instead of the words field will be populated in Paragraph.

Example: "lineFilter": { "paths": ["boundingBox", "words"] }

The above will return Line objects with only the "boundingBox" and "words" fields populated. This can save bandwidth and storage for unnecessary data.

Default when unset: No lines are returned in paragraphs.

A comma-separated list of fully qualified names of fields. Example: "user.displayName,photo".

wordFilter

string (FieldMask format)

Controls what data is returned at the word level in fullTextAnnotation.

Example: "wordFilter": { "paths": ["confidence", "mergedText"] }

The above will return Word objects with only the "confidence" and "mergedText" fields populated. This can save bandwidth and storage for unnecessary data.

Default when unset: All fields are included except mergedText

A comma-separated list of fully qualified names of fields. Example: "user.displayName,photo".

symbolFilter

string (FieldMask format)

Controls what data is returned at the symbol level in fullTextAnnotation.

Example: "symbolFilter": { "paths": ["confidence", "text"] }

The above will return Symbol objects with only the "confidence" and "text" fields populated. This can save bandwidth and storage for unnecessary data.

Default when unset: All fields are included except boundingBox

A comma-separated list of fully qualified names of fields. Example: "user.displayName,photo".

enableTextDetectionConfidenceScore

boolean

By default, Cloud Vision API only includes confidence score for DOCUMENT_TEXT_DETECTION result. Set the flag to true to include confidence score for TEXT_DETECTION as well.