<html><body>
<style>
body, h1, h2, h3, div, span, p, pre, a {
margin: 0;
padding: 0;
border: 0;
font-weight: inherit;
font-style: inherit;
font-size: 100%;
font-family: inherit;
vertical-align: baseline;
}
body {
font-size: 13px;
padding: 1em;
}
h1 {
font-size: 26px;
margin-bottom: 1em;
}
h2 {
font-size: 24px;
margin-bottom: 1em;
}
h3 {
font-size: 20px;
margin-bottom: 1em;
margin-top: 1em;
}
pre, code {
line-height: 1.5;
font-family: Monaco, 'DejaVu Sans Mono', 'Bitstream Vera Sans Mono', 'Lucida Console', monospace;
}
pre {
margin-top: 0.5em;
}
h1, h2, h3, p {
font-family: Arial, sans serif;
}
h1, h2, h3 {
border-bottom: solid #CCC 1px;
}
.toc_element {
margin-top: 0.5em;
}
.firstline {
margin-left: 2 em;
}
.method {
margin-top: 1em;
border: solid 1px #CCC;
padding: 1em;
background: #EEE;
}
.details {
font-weight: bold;
font-size: 14px;
}
</style>
<h1><a href="vision_v1.html">Google Cloud Vision API</a> . <a href="vision_v1.images.html">images</a></h1>
<h2>Instance Methods</h2>
<p class="toc_element">
<code><a href="#annotate">annotate(body, x__xgafv=None)</a></code></p>
<p class="firstline">Run image detection and annotation for a batch of images.</p>
<h3>Method Details</h3>
<div class="method">
<code class="details" id="annotate">annotate(body, x__xgafv=None)</code>
<pre>Run image detection and annotation for a batch of images.
Args:
body: object, The request body. (required)
The object takes the form of:
{ # Multiple image annotation requests are batched into a single service call.
"requests": [ # Individual image annotation requests for this batch.
{ # Request for performing Google Cloud Vision API tasks over a user-provided
# image, with user-requested features.
"imageContext": { # Image context and/or feature-specific parameters. # Additional context that may accompany the image.
"latLongRect": { # Rectangle determined by min and max `LatLng` pairs. # lat/long rectangle that specifies the location of the image.
"minLatLng": { # An object representing a latitude/longitude pair. This is expressed as a pair # Min lat/long pair.
# of doubles representing degrees latitude and degrees longitude. Unless
# specified otherwise, this must conform to the
# <a href="http://www.unoosa.org/pdf/icg/2012/template/WGS_84.pdf">WGS84
# standard</a>. Values must be within normalized ranges.
#
# Example of normalization code in Python:
#
# def NormalizeLongitude(longitude):
# """Wraps decimal degrees longitude to [-180.0, 180.0]."""
# q, r = divmod(longitude, 360.0)
# if r > 180.0 or (r == 180.0 and q <= -1.0):
# return r - 360.0
# return r
#
# def NormalizeLatLng(latitude, longitude):
# """Wraps decimal degrees latitude and longitude to
# [-90.0, 90.0] and [-180.0, 180.0], respectively."""
# r = latitude % 360.0
# if r <= 90.0:
# return r, NormalizeLongitude(longitude)
# elif r >= 270.0:
# return r - 360, NormalizeLongitude(longitude)
# else:
# return 180 - r, NormalizeLongitude(longitude + 180.0)
#
# assert 180.0 == NormalizeLongitude(180.0)
# assert -180.0 == NormalizeLongitude(-180.0)
# assert -179.0 == NormalizeLongitude(181.0)
# assert (0.0, 0.0) == NormalizeLatLng(360.0, 0.0)
# assert (0.0, 0.0) == NormalizeLatLng(-360.0, 0.0)
# assert (85.0, 180.0) == NormalizeLatLng(95.0, 0.0)
# assert (-85.0, -170.0) == NormalizeLatLng(-95.0, 10.0)
# assert (90.0, 10.0) == NormalizeLatLng(90.0, 10.0)
# assert (-90.0, -10.0) == NormalizeLatLng(-90.0, -10.0)
# assert (0.0, -170.0) == NormalizeLatLng(-180.0, 10.0)
# assert (0.0, -170.0) == NormalizeLatLng(180.0, 10.0)
# assert (-90.0, 10.0) == NormalizeLatLng(270.0, 10.0)
# assert (90.0, 10.0) == NormalizeLatLng(-270.0, 10.0)
"latitude": 3.14, # The latitude in degrees. It must be in the range [-90.0, +90.0].
"longitude": 3.14, # The longitude in degrees. It must be in the range [-180.0, +180.0].
},
"maxLatLng": { # An object representing a latitude/longitude pair. This is expressed as a pair # Max lat/long pair.
# of doubles representing degrees latitude and degrees longitude. Unless
# specified otherwise, this must conform to the
# <a href="http://www.unoosa.org/pdf/icg/2012/template/WGS_84.pdf">WGS84
# standard</a>. Values must be within normalized ranges.
#
# Example of normalization code in Python:
#
# def NormalizeLongitude(longitude):
# """Wraps decimal degrees longitude to [-180.0, 180.0]."""
# q, r = divmod(longitude, 360.0)
# if r > 180.0 or (r == 180.0 and q <= -1.0):
# return r - 360.0
# return r
#
# def NormalizeLatLng(latitude, longitude):
# """Wraps decimal degrees latitude and longitude to
# [-90.0, 90.0] and [-180.0, 180.0], respectively."""
# r = latitude % 360.0
# if r <= 90.0:
# return r, NormalizeLongitude(longitude)
# elif r >= 270.0:
# return r - 360, NormalizeLongitude(longitude)
# else:
# return 180 - r, NormalizeLongitude(longitude + 180.0)
#
# assert 180.0 == NormalizeLongitude(180.0)
# assert -180.0 == NormalizeLongitude(-180.0)
# assert -179.0 == NormalizeLongitude(181.0)
# assert (0.0, 0.0) == NormalizeLatLng(360.0, 0.0)
# assert (0.0, 0.0) == NormalizeLatLng(-360.0, 0.0)
# assert (85.0, 180.0) == NormalizeLatLng(95.0, 0.0)
# assert (-85.0, -170.0) == NormalizeLatLng(-95.0, 10.0)
# assert (90.0, 10.0) == NormalizeLatLng(90.0, 10.0)
# assert (-90.0, -10.0) == NormalizeLatLng(-90.0, -10.0)
# assert (0.0, -170.0) == NormalizeLatLng(-180.0, 10.0)
# assert (0.0, -170.0) == NormalizeLatLng(180.0, 10.0)
# assert (-90.0, 10.0) == NormalizeLatLng(270.0, 10.0)
# assert (90.0, 10.0) == NormalizeLatLng(-270.0, 10.0)
"latitude": 3.14, # The latitude in degrees. It must be in the range [-90.0, +90.0].
"longitude": 3.14, # The longitude in degrees. It must be in the range [-180.0, +180.0].
},
},
"languageHints": [ # 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).
"A String",
],
"cropHintsParams": { # Parameters for crop hints annotation request. # Parameters for crop hints annotation request.
"aspectRatios": [ # 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.
3.14,
],
},
},
"image": { # Client image to perform Google Cloud Vision API tasks over. # The image to be processed.
"content": "A String", # 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.
"source": { # External image source (Google Cloud Storage image location). # Google Cloud Storage image location. If both `content` and `source`
# are provided for an image, `content` takes precedence and is
# used to perform the image annotation request.
"gcsImageUri": "A String", # NOTE: For new code `image_uri` below is preferred.
# Google Cloud Storage image URI, which must be in the following form:
# `gs://bucket_name/object_name` (for details, see
# [Google Cloud Storage Request
# URIs](https://cloud.google.com/storage/docs/reference-uris)).
# NOTE: Cloud Storage object versioning is not supported.
"imageUri": "A String", # Image URI which supports:
# 1) Google Cloud Storage image URI, which must be in the following form:
# `gs://bucket_name/object_name` (for details, see
# [Google Cloud Storage Request
# URIs](https://cloud.google.com/storage/docs/reference-uris)).
# NOTE: Cloud Storage object versioning is not supported.
# 2) Publicly accessible image HTTP/HTTPS URL.
# This is preferred over the legacy `gcs_image_uri` above. When both
# `gcs_image_uri` and `image_uri` are specified, `image_uri` takes
# precedence.
},
},
"features": [ # Requested features.
{ # Users describe the type of Google Cloud Vision API tasks to perform over
# images by using *Feature*s. Each Feature indicates a type of image
# detection task to perform. Features encode the Cloud Vision API
# vertical to operate on and the number of top-scoring results to return.
"type": "A String", # The feature type.
"maxResults": 42, # Maximum number of results of this type.
},
],
},
],
}
x__xgafv: string, V1 error format.
Allowed values
1 - v1 error format
2 - v2 error format
Returns:
An object of the form:
{ # Response to a batch image annotation request.
"responses": [ # Individual responses to image annotation requests within the batch.
{ # Response to an image annotation request.
"safeSearchAnnotation": { # Set of features pertaining to the image, computed by computer vision # If present, safe-search annotation has completed successfully.
# methods over safe-search verticals (for example, adult, spoof, medical,
# violence).
"medical": "A String", # Likelihood that this is a medical image.
"spoof": "A String", # Spoof likelihood. The likelihood that an modification
# was made to the image's canonical version to make it appear
# funny or offensive.
"violence": "A String", # Violence likelihood.
"adult": "A String", # Represents the adult content likelihood for the image.
},
"textAnnotations": [ # If present, text (OCR) detection has completed successfully.
{ # Set of detected entity features.
"confidence": 3.14, # 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].
"description": "A String", # Entity textual description, expressed in its `locale` language.
"locale": "A String", # The language code for the locale in which the entity textual
# `description` is expressed.
"topicality": 3.14, # 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].
"mid": "A String", # Opaque entity ID. Some IDs may be available in
# [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).
"locations": [ # 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.
{ # Detected entity location information.
"latLng": { # An object representing a latitude/longitude pair. This is expressed as a pair # lat/long location coordinates.
# of doubles representing degrees latitude and degrees longitude. Unless
# specified otherwise, this must conform to the
# <a href="http://www.unoosa.org/pdf/icg/2012/template/WGS_84.pdf">WGS84
# standard</a>. Values must be within normalized ranges.
#
# Example of normalization code in Python:
#
# def NormalizeLongitude(longitude):
# """Wraps decimal degrees longitude to [-180.0, 180.0]."""
# q, r = divmod(longitude, 360.0)
# if r > 180.0 or (r == 180.0 and q <= -1.0):
# return r - 360.0
# return r
#
# def NormalizeLatLng(latitude, longitude):
# """Wraps decimal degrees latitude and longitude to
# [-90.0, 90.0] and [-180.0, 180.0], respectively."""
# r = latitude % 360.0
# if r <= 90.0:
# return r, NormalizeLongitude(longitude)
# elif r >= 270.0:
# return r - 360, NormalizeLongitude(longitude)
# else:
# return 180 - r, NormalizeLongitude(longitude + 180.0)
#
# assert 180.0 == NormalizeLongitude(180.0)
# assert -180.0 == NormalizeLongitude(-180.0)
# assert -179.0 == NormalizeLongitude(181.0)
# assert (0.0, 0.0) == NormalizeLatLng(360.0, 0.0)
# assert (0.0, 0.0) == NormalizeLatLng(-360.0, 0.0)
# assert (85.0, 180.0) == NormalizeLatLng(95.0, 0.0)
# assert (-85.0, -170.0) == NormalizeLatLng(-95.0, 10.0)
# assert (90.0, 10.0) == NormalizeLatLng(90.0, 10.0)
# assert (-90.0, -10.0) == NormalizeLatLng(-90.0, -10.0)
# assert (0.0, -170.0) == NormalizeLatLng(-180.0, 10.0)
# assert (0.0, -170.0) == NormalizeLatLng(180.0, 10.0)
# assert (-90.0, 10.0) == NormalizeLatLng(270.0, 10.0)
# assert (90.0, 10.0) == NormalizeLatLng(-270.0, 10.0)
"latitude": 3.14, # The latitude in degrees. It must be in the range [-90.0, +90.0].
"longitude": 3.14, # The longitude in degrees. It must be in the range [-180.0, +180.0].
},
},
],
"score": 3.14, # Overall score of the result. Range [0, 1].
"boundingPoly": { # A bounding polygon for the detected image annotation. # Image region to which this entity belongs. Currently not produced
# for `LABEL_DETECTION` features. For `TEXT_DETECTION` (OCR), `boundingPoly`s
# are produced for the entire text detected in an image region, followed by
# `boundingPoly`s for each word within the detected text.
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image.
# NOTE: the vertex coordinates are in the same scale as the original image.
"y": 42, # Y coordinate.
"x": 42, # X coordinate.
},
],
},
"properties": [ # Some entities may have optional user-supplied `Property` (name/value)
# fields, such a score or string that qualifies the entity.
{ # A `Property` consists of a user-supplied name/value pair.
"uint64Value": "A String", # Value of numeric properties.
"name": "A String", # Name of the property.
"value": "A String", # Value of the property.
},
],
},
],
"webDetection": { # Relevant information for the image from the Internet. # If present, web detection has completed successfully.
"webEntities": [ # Deduced entities from similar images on the Internet.
{ # Entity deduced from similar images on the Internet.
"entityId": "A String", # Opaque entity ID.
"score": 3.14, # Overall relevancy score for the entity.
# Not normalized and not comparable across different image queries.
"description": "A String", # Canonical description of the entity, in English.
},
],
"pagesWithMatchingImages": [ # Web pages containing the matching images from the Internet.
{ # Metadata for web pages.
"url": "A String", # The result web page URL.
"score": 3.14, # Overall relevancy score for the web page.
# Not normalized and not comparable across different image queries.
},
],
"visuallySimilarImages": [ # The visually similar image results.
{ # Metadata for online images.
"url": "A String", # The result image URL.
"score": 3.14, # Overall relevancy score for the image.
# Not normalized and not comparable across different image queries.
},
],
"partialMatchingImages": [ # 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.
{ # Metadata for online images.
"url": "A String", # The result image URL.
"score": 3.14, # Overall relevancy score for the image.
# Not normalized and not comparable across different image queries.
},
],
"fullMatchingImages": [ # Fully matching images from the Internet.
# Can include resized copies of the query image.
{ # Metadata for online images.
"url": "A String", # The result image URL.
"score": 3.14, # Overall relevancy score for the image.
# Not normalized and not comparable across different image queries.
},
],
},
"fullTextAnnotation": { # TextAnnotation contains a structured representation of OCR extracted text. # If present, text (OCR) detection or document (OCR) text detection has
# completed successfully.
# This annotation provides the structural hierarchy for the OCR detected
# 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 google.cloud.vision.v1.TextAnnotation.TextProperty message
# definition below for more detail.
"text": "A String", # UTF-8 text detected on the pages.
"pages": [ # List of pages detected by OCR.
{ # Detected page from OCR.
"width": 42, # Page width in pixels.
"property": { # Additional information detected on the structural component. # Additional information detected on the page.
"detectedBreak": { # Detected start or end of a structural component. # Detected start or end of a text segment.
"isPrefix": True or False, # True if break prepends the element.
"type": "A String", # Detected break type.
},
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"languageCode": "A String", # 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.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
},
],
},
"blocks": [ # List of blocks of text, images etc on this page.
{ # Logical element on the page.
"boundingBox": { # A bounding polygon for the detected image annotation. # 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).
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image.
# NOTE: the vertex coordinates are in the same scale as the original image.
"y": 42, # Y coordinate.
"x": 42, # X coordinate.
},
],
},
"blockType": "A String", # Detected block type (text, image etc) for this block.
"property": { # Additional information detected on the structural component. # Additional information detected for the block.
"detectedBreak": { # Detected start or end of a structural component. # Detected start or end of a text segment.
"isPrefix": True or False, # True if break prepends the element.
"type": "A String", # Detected break type.
},
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"languageCode": "A String", # 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.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
},
],
},
"paragraphs": [ # List of paragraphs in this block (if this blocks is of type text).
{ # Structural unit of text representing a number of words in certain order.
"boundingBox": { # A bounding polygon for the detected image annotation. # 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).
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image.
# NOTE: the vertex coordinates are in the same scale as the original image.
"y": 42, # Y coordinate.
"x": 42, # X coordinate.
},
],
},
"property": { # Additional information detected on the structural component. # Additional information detected for the paragraph.
"detectedBreak": { # Detected start or end of a structural component. # Detected start or end of a text segment.
"isPrefix": True or False, # True if break prepends the element.
"type": "A String", # Detected break type.
},
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"languageCode": "A String", # 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.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
},
],
},
"words": [ # List of words in this paragraph.
{ # A word representation.
"boundingBox": { # A bounding polygon for the detected image annotation. # 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).
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image.
# NOTE: the vertex coordinates are in the same scale as the original image.
"y": 42, # Y coordinate.
"x": 42, # X coordinate.
},
],
},
"symbols": [ # List of symbols in the word.
# The order of the symbols follows the natural reading order.
{ # A single symbol representation.
"boundingBox": { # A bounding polygon for the detected image annotation. # 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).
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image.
# NOTE: the vertex coordinates are in the same scale as the original image.
"y": 42, # Y coordinate.
"x": 42, # X coordinate.
},
],
},
"text": "A String", # The actual UTF-8 representation of the symbol.
"property": { # Additional information detected on the structural component. # Additional information detected for the symbol.
"detectedBreak": { # Detected start or end of a structural component. # Detected start or end of a text segment.
"isPrefix": True or False, # True if break prepends the element.
"type": "A String", # Detected break type.
},
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"languageCode": "A String", # 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.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
},
],
},
},
],
"property": { # Additional information detected on the structural component. # Additional information detected for the word.
"detectedBreak": { # Detected start or end of a structural component. # Detected start or end of a text segment.
"isPrefix": True or False, # True if break prepends the element.
"type": "A String", # Detected break type.
},
"detectedLanguages": [ # A list of detected languages together with confidence.
{ # Detected language for a structural component.
"languageCode": "A String", # 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.
"confidence": 3.14, # Confidence of detected language. Range [0, 1].
},
],
},
},
],
},
],
},
],
"height": 42, # Page height in pixels.
},
],
},
"labelAnnotations": [ # If present, label detection has completed successfully.
{ # Set of detected entity features.
"confidence": 3.14, # 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].
"description": "A String", # Entity textual description, expressed in its `locale` language.
"locale": "A String", # The language code for the locale in which the entity textual
# `description` is expressed.
"topicality": 3.14, # 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].
"mid": "A String", # Opaque entity ID. Some IDs may be available in
# [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).
"locations": [ # 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.
{ # Detected entity location information.
"latLng": { # An object representing a latitude/longitude pair. This is expressed as a pair # lat/long location coordinates.
# of doubles representing degrees latitude and degrees longitude. Unless
# specified otherwise, this must conform to the
# <a href="http://www.unoosa.org/pdf/icg/2012/template/WGS_84.pdf">WGS84
# standard</a>. Values must be within normalized ranges.
#
# Example of normalization code in Python:
#
# def NormalizeLongitude(longitude):
# """Wraps decimal degrees longitude to [-180.0, 180.0]."""
# q, r = divmod(longitude, 360.0)
# if r > 180.0 or (r == 180.0 and q <= -1.0):
# return r - 360.0
# return r
#
# def NormalizeLatLng(latitude, longitude):
# """Wraps decimal degrees latitude and longitude to
# [-90.0, 90.0] and [-180.0, 180.0], respectively."""
# r = latitude % 360.0
# if r <= 90.0:
# return r, NormalizeLongitude(longitude)
# elif r >= 270.0:
# return r - 360, NormalizeLongitude(longitude)
# else:
# return 180 - r, NormalizeLongitude(longitude + 180.0)
#
# assert 180.0 == NormalizeLongitude(180.0)
# assert -180.0 == NormalizeLongitude(-180.0)
# assert -179.0 == NormalizeLongitude(181.0)
# assert (0.0, 0.0) == NormalizeLatLng(360.0, 0.0)
# assert (0.0, 0.0) == NormalizeLatLng(-360.0, 0.0)
# assert (85.0, 180.0) == NormalizeLatLng(95.0, 0.0)
# assert (-85.0, -170.0) == NormalizeLatLng(-95.0, 10.0)
# assert (90.0, 10.0) == NormalizeLatLng(90.0, 10.0)
# assert (-90.0, -10.0) == NormalizeLatLng(-90.0, -10.0)
# assert (0.0, -170.0) == NormalizeLatLng(-180.0, 10.0)
# assert (0.0, -170.0) == NormalizeLatLng(180.0, 10.0)
# assert (-90.0, 10.0) == NormalizeLatLng(270.0, 10.0)
# assert (90.0, 10.0) == NormalizeLatLng(-270.0, 10.0)
"latitude": 3.14, # The latitude in degrees. It must be in the range [-90.0, +90.0].
"longitude": 3.14, # The longitude in degrees. It must be in the range [-180.0, +180.0].
},
},
],
"score": 3.14, # Overall score of the result. Range [0, 1].
"boundingPoly": { # A bounding polygon for the detected image annotation. # Image region to which this entity belongs. Currently not produced
# for `LABEL_DETECTION` features. For `TEXT_DETECTION` (OCR), `boundingPoly`s
# are produced for the entire text detected in an image region, followed by
# `boundingPoly`s for each word within the detected text.
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image.
# NOTE: the vertex coordinates are in the same scale as the original image.
"y": 42, # Y coordinate.
"x": 42, # X coordinate.
},
],
},
"properties": [ # Some entities may have optional user-supplied `Property` (name/value)
# fields, such a score or string that qualifies the entity.
{ # A `Property` consists of a user-supplied name/value pair.
"uint64Value": "A String", # Value of numeric properties.
"name": "A String", # Name of the property.
"value": "A String", # Value of the property.
},
],
},
],
"imagePropertiesAnnotation": { # Stores image properties, such as dominant colors. # If present, image properties were extracted successfully.
"dominantColors": { # Set of dominant colors and their corresponding scores. # If present, dominant colors completed successfully.
"colors": [ # RGB color values with their score and pixel fraction.
{ # Color information consists of RGB channels, score, and the fraction of
# the image that the color occupies in the image.
"color": { # Represents a color in the RGBA color space. This representation is designed # RGB components of the color.
# for simplicity of conversion to/from color representations in various
# languages over compactness; for example, the fields of this representation
# can be trivially provided to the constructor of "java.awt.Color" in Java; it
# can also be trivially provided to UIColor's "+colorWithRed:green:blue:alpha"
# method in iOS; and, with just a little work, it can be easily formatted into
# a CSS "rgba()" string in JavaScript, as well. Here are some examples:
#
# Example (Java):
#
# import com.google.type.Color;
#
# // ...
# public static java.awt.Color fromProto(Color protocolor) {
# float alpha = protocolor.hasAlpha()
# ? protocolor.getAlpha().getValue()
# : 1.0;
#
# return new java.awt.Color(
# protocolor.getRed(),
# protocolor.getGreen(),
# protocolor.getBlue(),
# alpha);
# }
#
# public static Color toProto(java.awt.Color color) {
# float red = (float) color.getRed();
# float green = (float) color.getGreen();
# float blue = (float) color.getBlue();
# float denominator = 255.0;
# Color.Builder resultBuilder =
# Color
# .newBuilder()
# .setRed(red / denominator)
# .setGreen(green / denominator)
# .setBlue(blue / denominator);
# int alpha = color.getAlpha();
# if (alpha != 255) {
# result.setAlpha(
# FloatValue
# .newBuilder()
# .setValue(((float) alpha) / denominator)
# .build());
# }
# return resultBuilder.build();
# }
# // ...
#
# Example (iOS / Obj-C):
#
# // ...
# static UIColor* fromProto(Color* protocolor) {
# float red = [protocolor red];
# float green = [protocolor green];
# float blue = [protocolor blue];
# FloatValue* alpha_wrapper = [protocolor alpha];
# float alpha = 1.0;
# if (alpha_wrapper != nil) {
# alpha = [alpha_wrapper value];
# }
# return [UIColor colorWithRed:red green:green blue:blue alpha:alpha];
# }
#
# static Color* toProto(UIColor* color) {
# CGFloat red, green, blue, alpha;
# if (![color getRed:&red green:&green blue:&blue alpha:&alpha]) {
# return nil;
# }
# Color* result = [Color alloc] init];
# [result setRed:red];
# [result setGreen:green];
# [result setBlue:blue];
# if (alpha <= 0.9999) {
# [result setAlpha:floatWrapperWithValue(alpha)];
# }
# [result autorelease];
# return result;
# }
# // ...
#
# Example (JavaScript):
#
# // ...
#
# var protoToCssColor = function(rgb_color) {
# var redFrac = rgb_color.red || 0.0;
# var greenFrac = rgb_color.green || 0.0;
# var blueFrac = rgb_color.blue || 0.0;
# var red = Math.floor(redFrac * 255);
# var green = Math.floor(greenFrac * 255);
# var blue = Math.floor(blueFrac * 255);
#
# if (!('alpha' in rgb_color)) {
# return rgbToCssColor_(red, green, blue);
# }
#
# var alphaFrac = rgb_color.alpha.value || 0.0;
# var rgbParams = [red, green, blue].join(',');
# return ['rgba(', rgbParams, ',', alphaFrac, ')'].join('');
# };
#
# var rgbToCssColor_ = function(red, green, blue) {
# var rgbNumber = new Number((red << 16) | (green << 8) | blue);
# var hexString = rgbNumber.toString(16);
# var missingZeros = 6 - hexString.length;
# var resultBuilder = ['#'];
# for (var i = 0; i < missingZeros; i++) {
# resultBuilder.push('0');
# }
# resultBuilder.push(hexString);
# return resultBuilder.join('');
# };
#
# // ...
"blue": 3.14, # The amount of blue in the color as a value in the interval [0, 1].
"alpha": 3.14, # The fraction of this color that should be applied to the pixel. That is,
# the final pixel color is defined by the equation:
#
# pixel color = alpha * (this color) + (1.0 - alpha) * (background color)
#
# This means that a value of 1.0 corresponds to a solid color, whereas
# a value of 0.0 corresponds to a completely transparent color. This
# uses a wrapper message rather than a simple float scalar so that it is
# possible to distinguish between a default value and the value being unset.
# If omitted, this color object is to be rendered as a solid color
# (as if the alpha value had been explicitly given with a value of 1.0).
"green": 3.14, # The amount of green in the color as a value in the interval [0, 1].
"red": 3.14, # The amount of red in the color as a value in the interval [0, 1].
},
"pixelFraction": 3.14, # The fraction of pixels the color occupies in the image.
# Value in range [0, 1].
"score": 3.14, # Image-specific score for this color. Value in range [0, 1].
},
],
},
},
"faceAnnotations": [ # If present, face detection has completed successfully.
{ # A face annotation object contains the results of face detection.
"sorrowLikelihood": "A String", # Sorrow likelihood.
"landmarkingConfidence": 3.14, # Face landmarking confidence. Range [0, 1].
"underExposedLikelihood": "A String", # Under-exposed likelihood.
"detectionConfidence": 3.14, # Detection confidence. Range [0, 1].
"joyLikelihood": "A String", # Joy likelihood.
"landmarks": [ # Detected face landmarks.
{ # A face-specific landmark (for example, a face feature).
# Landmark positions may fall outside the bounds of the image
# if the face is near one or more edges of the image.
# Therefore it is NOT guaranteed that `0 <= x < width` or
# `0 <= y < height`.
"position": { # A 3D position in the image, used primarily for Face detection landmarks. # Face landmark position.
# A valid Position must have both x and y coordinates.
# The position coordinates are in the same scale as the original image.
"y": 3.14, # Y coordinate.
"x": 3.14, # X coordinate.
"z": 3.14, # Z coordinate (or depth).
},
"type": "A String", # Face landmark type.
},
],
"surpriseLikelihood": "A String", # Surprise likelihood.
"blurredLikelihood": "A String", # Blurred likelihood.
"tiltAngle": 3.14, # Pitch angle, which indicates the upwards/downwards angle that the face is
# pointing relative to the image's horizontal plane. Range [-180,180].
"angerLikelihood": "A String", # Anger likelihood.
"boundingPoly": { # A bounding polygon for the detected image annotation. # 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.
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image.
# NOTE: the vertex coordinates are in the same scale as the original image.
"y": 42, # Y coordinate.
"x": 42, # X coordinate.
},
],
},
"rollAngle": 3.14, # 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].
"panAngle": 3.14, # 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].
"headwearLikelihood": "A String", # Headwear likelihood.
"fdBoundingPoly": { # A bounding polygon for the detected image annotation. # 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.
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image.
# NOTE: the vertex coordinates are in the same scale as the original image.
"y": 42, # Y coordinate.
"x": 42, # X coordinate.
},
],
},
},
],
"logoAnnotations": [ # If present, logo detection has completed successfully.
{ # Set of detected entity features.
"confidence": 3.14, # 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].
"description": "A String", # Entity textual description, expressed in its `locale` language.
"locale": "A String", # The language code for the locale in which the entity textual
# `description` is expressed.
"topicality": 3.14, # 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].
"mid": "A String", # Opaque entity ID. Some IDs may be available in
# [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).
"locations": [ # 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.
{ # Detected entity location information.
"latLng": { # An object representing a latitude/longitude pair. This is expressed as a pair # lat/long location coordinates.
# of doubles representing degrees latitude and degrees longitude. Unless
# specified otherwise, this must conform to the
# <a href="http://www.unoosa.org/pdf/icg/2012/template/WGS_84.pdf">WGS84
# standard</a>. Values must be within normalized ranges.
#
# Example of normalization code in Python:
#
# def NormalizeLongitude(longitude):
# """Wraps decimal degrees longitude to [-180.0, 180.0]."""
# q, r = divmod(longitude, 360.0)
# if r > 180.0 or (r == 180.0 and q <= -1.0):
# return r - 360.0
# return r
#
# def NormalizeLatLng(latitude, longitude):
# """Wraps decimal degrees latitude and longitude to
# [-90.0, 90.0] and [-180.0, 180.0], respectively."""
# r = latitude % 360.0
# if r <= 90.0:
# return r, NormalizeLongitude(longitude)
# elif r >= 270.0:
# return r - 360, NormalizeLongitude(longitude)
# else:
# return 180 - r, NormalizeLongitude(longitude + 180.0)
#
# assert 180.0 == NormalizeLongitude(180.0)
# assert -180.0 == NormalizeLongitude(-180.0)
# assert -179.0 == NormalizeLongitude(181.0)
# assert (0.0, 0.0) == NormalizeLatLng(360.0, 0.0)
# assert (0.0, 0.0) == NormalizeLatLng(-360.0, 0.0)
# assert (85.0, 180.0) == NormalizeLatLng(95.0, 0.0)
# assert (-85.0, -170.0) == NormalizeLatLng(-95.0, 10.0)
# assert (90.0, 10.0) == NormalizeLatLng(90.0, 10.0)
# assert (-90.0, -10.0) == NormalizeLatLng(-90.0, -10.0)
# assert (0.0, -170.0) == NormalizeLatLng(-180.0, 10.0)
# assert (0.0, -170.0) == NormalizeLatLng(180.0, 10.0)
# assert (-90.0, 10.0) == NormalizeLatLng(270.0, 10.0)
# assert (90.0, 10.0) == NormalizeLatLng(-270.0, 10.0)
"latitude": 3.14, # The latitude in degrees. It must be in the range [-90.0, +90.0].
"longitude": 3.14, # The longitude in degrees. It must be in the range [-180.0, +180.0].
},
},
],
"score": 3.14, # Overall score of the result. Range [0, 1].
"boundingPoly": { # A bounding polygon for the detected image annotation. # Image region to which this entity belongs. Currently not produced
# for `LABEL_DETECTION` features. For `TEXT_DETECTION` (OCR), `boundingPoly`s
# are produced for the entire text detected in an image region, followed by
# `boundingPoly`s for each word within the detected text.
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image.
# NOTE: the vertex coordinates are in the same scale as the original image.
"y": 42, # Y coordinate.
"x": 42, # X coordinate.
},
],
},
"properties": [ # Some entities may have optional user-supplied `Property` (name/value)
# fields, such a score or string that qualifies the entity.
{ # A `Property` consists of a user-supplied name/value pair.
"uint64Value": "A String", # Value of numeric properties.
"name": "A String", # Name of the property.
"value": "A String", # Value of the property.
},
],
},
],
"landmarkAnnotations": [ # If present, landmark detection has completed successfully.
{ # Set of detected entity features.
"confidence": 3.14, # 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].
"description": "A String", # Entity textual description, expressed in its `locale` language.
"locale": "A String", # The language code for the locale in which the entity textual
# `description` is expressed.
"topicality": 3.14, # 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].
"mid": "A String", # Opaque entity ID. Some IDs may be available in
# [Google Knowledge Graph Search API](https://developers.google.com/knowledge-graph/).
"locations": [ # 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.
{ # Detected entity location information.
"latLng": { # An object representing a latitude/longitude pair. This is expressed as a pair # lat/long location coordinates.
# of doubles representing degrees latitude and degrees longitude. Unless
# specified otherwise, this must conform to the
# <a href="http://www.unoosa.org/pdf/icg/2012/template/WGS_84.pdf">WGS84
# standard</a>. Values must be within normalized ranges.
#
# Example of normalization code in Python:
#
# def NormalizeLongitude(longitude):
# """Wraps decimal degrees longitude to [-180.0, 180.0]."""
# q, r = divmod(longitude, 360.0)
# if r > 180.0 or (r == 180.0 and q <= -1.0):
# return r - 360.0
# return r
#
# def NormalizeLatLng(latitude, longitude):
# """Wraps decimal degrees latitude and longitude to
# [-90.0, 90.0] and [-180.0, 180.0], respectively."""
# r = latitude % 360.0
# if r <= 90.0:
# return r, NormalizeLongitude(longitude)
# elif r >= 270.0:
# return r - 360, NormalizeLongitude(longitude)
# else:
# return 180 - r, NormalizeLongitude(longitude + 180.0)
#
# assert 180.0 == NormalizeLongitude(180.0)
# assert -180.0 == NormalizeLongitude(-180.0)
# assert -179.0 == NormalizeLongitude(181.0)
# assert (0.0, 0.0) == NormalizeLatLng(360.0, 0.0)
# assert (0.0, 0.0) == NormalizeLatLng(-360.0, 0.0)
# assert (85.0, 180.0) == NormalizeLatLng(95.0, 0.0)
# assert (-85.0, -170.0) == NormalizeLatLng(-95.0, 10.0)
# assert (90.0, 10.0) == NormalizeLatLng(90.0, 10.0)
# assert (-90.0, -10.0) == NormalizeLatLng(-90.0, -10.0)
# assert (0.0, -170.0) == NormalizeLatLng(-180.0, 10.0)
# assert (0.0, -170.0) == NormalizeLatLng(180.0, 10.0)
# assert (-90.0, 10.0) == NormalizeLatLng(270.0, 10.0)
# assert (90.0, 10.0) == NormalizeLatLng(-270.0, 10.0)
"latitude": 3.14, # The latitude in degrees. It must be in the range [-90.0, +90.0].
"longitude": 3.14, # The longitude in degrees. It must be in the range [-180.0, +180.0].
},
},
],
"score": 3.14, # Overall score of the result. Range [0, 1].
"boundingPoly": { # A bounding polygon for the detected image annotation. # Image region to which this entity belongs. Currently not produced
# for `LABEL_DETECTION` features. For `TEXT_DETECTION` (OCR), `boundingPoly`s
# are produced for the entire text detected in an image region, followed by
# `boundingPoly`s for each word within the detected text.
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image.
# NOTE: the vertex coordinates are in the same scale as the original image.
"y": 42, # Y coordinate.
"x": 42, # X coordinate.
},
],
},
"properties": [ # Some entities may have optional user-supplied `Property` (name/value)
# fields, such a score or string that qualifies the entity.
{ # A `Property` consists of a user-supplied name/value pair.
"uint64Value": "A String", # Value of numeric properties.
"name": "A String", # Name of the property.
"value": "A String", # Value of the property.
},
],
},
],
"error": { # The `Status` type defines a logical error model that is suitable for different # 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.
# programming environments, including REST APIs and RPC APIs. It is used by
# [gRPC](https://github.com/grpc). The error model is designed to be:
#
# - Simple to use and understand for most users
# - Flexible enough to meet unexpected needs
#
# # Overview
#
# The `Status` message contains three pieces of data: error code, error message,
# and error details. The error code should be an enum value of
# google.rpc.Code, but it may accept additional error codes if needed. The
# error message should be a developer-facing English message that helps
# developers *understand* and *resolve* the error. If a localized user-facing
# error message is needed, put the localized message in the error details or
# localize it in the client. The optional error details may contain arbitrary
# information about the error. There is a predefined set of error detail types
# in the package `google.rpc` that can be used for common error conditions.
#
# # Language mapping
#
# The `Status` message is the logical representation of the error model, but it
# is not necessarily the actual wire format. When the `Status` message is
# exposed in different client libraries and different wire protocols, it can be
# mapped differently. For example, it will likely be mapped to some exceptions
# in Java, but more likely mapped to some error codes in C.
#
# # Other uses
#
# The error model and the `Status` message can be used in a variety of
# environments, either with or without APIs, to provide a
# consistent developer experience across different environments.
#
# Example uses of this error model include:
#
# - Partial errors. If a service needs to return partial errors to the client,
# it may embed the `Status` in the normal response to indicate the partial
# errors.
#
# - Workflow errors. A typical workflow has multiple steps. Each step may
# have a `Status` message for error reporting.
#
# - Batch operations. If a client uses batch request and batch response, the
# `Status` message should be used directly inside batch response, one for
# each error sub-response.
#
# - Asynchronous operations. If an API call embeds asynchronous operation
# results in its response, the status of those operations should be
# represented directly using the `Status` message.
#
# - Logging. If some API errors are stored in logs, the message `Status` could
# be used directly after any stripping needed for security/privacy reasons.
"message": "A String", # A developer-facing error message, which should be in English. Any
# user-facing error message should be localized and sent in the
# google.rpc.Status.details field, or localized by the client.
"code": 42, # The status code, which should be an enum value of google.rpc.Code.
"details": [ # A list of messages that carry the error details. There will be a
# common set of message types for APIs to use.
{
"a_key": "", # Properties of the object. Contains field @type with type URL.
},
],
},
"cropHintsAnnotation": { # Set of crop hints that are used to generate new crops when serving images. # If present, crop hints have completed successfully.
"cropHints": [ # Crop hint results.
{ # Single crop hint that is used to generate a new crop when serving an image.
"confidence": 3.14, # Confidence of this being a salient region. Range [0, 1].
"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the crop region. The coordinates of the bounding
# box are in the original image's scale, as returned in `ImageParams`.
"vertices": [ # The bounding polygon vertices.
{ # A vertex represents a 2D point in the image.
# NOTE: the vertex coordinates are in the same scale as the original image.
"y": 42, # Y coordinate.
"x": 42, # X coordinate.
},
],
},
"importanceFraction": 3.14, # Fraction of importance of this salient region with respect to the original
# image.
},
],
},
},
],
}</pre>
</div>
</body></html>