Run dense text document OCR. Takes precedence when both
DOCUMENT_TEXT_DETECTION and TEXT_DETECTION are present.
FaceDetection
Run face detection.
ImageProperties
Compute a set of image properties, such as the
image's dominant colors.
LabelDetection
Run label detection.
LandmarkDetection
Run landmark detection.
LogoDetection
Run logo detection.
ObjectLocalization
Run localizer for object detection.
ProductSearch
Run Product Search.
SafeSearchDetection
Run Safe Search to detect potentially unsafe
or undesirable content.
TextDetection
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.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Missing the information I need","missingTheInformationINeed","thumb-down"],["Too complicated / too many steps","tooComplicatedTooManySteps","thumb-down"],["Out of date","outOfDate","thumb-down"],["Samples / code issue","samplesCodeIssue","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-07 UTC."],[[["\u003cp\u003eThe latest version of the Google Cloud Vision API feature documentation is 3.7.0, with previous versions ranging from 3.6.0 down to 2.3.0 available for reference.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eType\u003c/code\u003e enum specifies the type of Google Cloud Vision API feature to be extracted, with options such as \u003ccode\u003eFaceDetection\u003c/code\u003e, \u003ccode\u003eLabelDetection\u003c/code\u003e, and \u003ccode\u003eWebDetection\u003c/code\u003e.\u003c/p\u003e\n"],["\u003cp\u003eThe \u003ccode\u003eDocumentTextDetection\u003c/code\u003e feature takes precedence over \u003ccode\u003eTextDetection\u003c/code\u003e when both are present, optimizing for dense text within documents.\u003c/p\u003e\n"],["\u003cp\u003eThere are various functions available within this resource, including crop hints, image properties, landmark detection, logo detection, object localization, product search, and safe search.\u003c/p\u003e\n"],["\u003cp\u003eEach feature listed within the resource has a clear description, allowing developers to quickly understand the functionality of the various features in the API.\u003c/p\u003e\n"]]],[],null,[]]
