Vision API lets you use the following features:

| All feature types ||
|---|---|
| ### [Text detection](https://docs.cloud.google.com/vision/docs/ocr) ![Road sign image](https://docs.cloud.google.com/static/vision/docs/images/sign_text.png) | - Optical character recognition (OCR) for an image; text recognition and conversion to machine-coded text. Identifies and extracts UTF-8 text in an image. - **Images** : Optimized for ***sparse*** areas of text within a larger image. - **Response** : Returns both a list of words identified with text, bounding boxes, and `textAnnotations`, as well as the structural hierarchy for the OCR detected text (`fullTextAnnotation`). - Hierarchy of extracted text structure: - TextAnnotation -\> Page -\> Block -\> Paragraph -\> Word -\> Symbol. - Each structural component from Page on may further have their own properties such as detected languages, breaks, etc. - **Languages supported** : Works with currently [supported, mapped, and experimental](https://docs.cloud.google.com/vision/docs/languages) languages. - Feature enum value: `TEXT_DETECTION`. |
| ### [Document text detection (dense text / handwriting)](https://docs.cloud.google.com/vision/docs/pdf) ![Dense image with annotations](https://docs.cloud.google.com/static/vision/docs/images/document_text_highlighted.png) ![handwriting image](https://docs.cloud.google.com/static/vision/docs/images/detect_handwriting_OCR-detect-handwriting_SMALL.png) | - Optical character recognition (OCR) for a file (PDF/TIFF) or dense text image; dense text recognition and conversion to machine-coded text. - **Files**: Optimized for document files (PDF/TIFF). - **Images** : Optimized for ***dense*** areas of text in an image (images that are documents), and images that contain handwriting. - **Response** : Returns the structural hierarchy for the OCR detected text (`fullTextAnnotation`). - Hierarchy of extracted text structure: - TextAnnotation -\> Page -\> Block -\> Paragraph -\> Word -\> Symbol. - Each structural component from Page on may further have their own properties such as detected languages, breaks, etc. - **Languages supported** : Works with currently [supported, mapped, and experimental](https://docs.cloud.google.com/vision/docs/languages) languages. - Feature enum value: `DOCUMENT_TEXT_DETECTION`. - Takes precedence when both `DOCUMENT_TEXT_DETECTION` and `TEXT_DETECTION` are requested. > [!NOTE] > If you are detecting text in scanned documents, try [Document AI](https://docs.cloud.google.com/document-ai/docs/overview) for optical character recognition, structured form parsing, and entity extraction. You can use the [Document AI Toolbox](https://docs.cloud.google.com/document-ai/docs/handle-response#toolbox) to convert output from the Document AI format to the Cloud Vision format. |
| ### [Landmark detection](https://docs.cloud.google.com/vision/docs/detecting-landmarks) ^[1](https://docs.cloud.google.com/vision/docs/features-list#fn1)^ ![St Basil's Cathedral image](https://docs.cloud.google.com/static/vision/docs/images/moscow.png) | - Provides the name of the landmark, a confidence score and a bounding box in the image for the landmark. - Gives coordinates for the detected entity. |
| ### [Logo detection](https://docs.cloud.google.com/vision/docs/detecting-logos) ^[2](https://docs.cloud.google.com/vision/docs/features-list#fn2)^ ![annotated logo](https://docs.cloud.google.com/static/vision/docs/images/logo_annotated.png) | - Provides a textual description of the entity identified, a confidence score, and a bounding polygon for the logo in the file. |
| ### [Label detection](https://docs.cloud.google.com/vision/docs/labels) ^[3](https://docs.cloud.google.com/vision/docs/features-list#fn3)^ ![Shanghai street image](https://docs.cloud.google.com/static/vision/docs/images/shanghai_labels.png) | - Provides generalized labels for an image. - For each label returns a textual description, confidence score, and topicality rating. |
| ### [Image properties](https://docs.cloud.google.com/vision/docs/detecting-properties) ^[4](https://docs.cloud.google.com/vision/docs/features-list#fn4)^ ![Bali image with properties](https://docs.cloud.google.com/static/vision/docs/images/bali_small_w_properties.jpeg) | - Returns dominant colors in an image. - Each color is represented in the RGBA color space, has a confidence score, and displays the fraction of pixels occupied by the color \[0, 1\]. |
| ### [Object localization](https://docs.cloud.google.com/vision/docs/object-localizer) ^[5](https://docs.cloud.google.com/vision/docs/features-list#fn5)^ ![image with bounding boxes](https://docs.cloud.google.com/static/vision/docs/images/bicycle.jpg) | - Provides general label and bounding box annotations for multiple objects recognized in a single image. - For each object detected the following elements are returned: a textual description, a confidence score, and normalized vertices \[0,1\] for the bounding polygon around the object. > [!NOTE] > Need customized object detection? > With > [AutoML Vision > Object Detection](https://docs.cloud.google.com/vision/automl/object-detection/docs) > you can create a custom machine learning model for your specific image > object detection use case. |
| ### [Crop hint detection](https://docs.cloud.google.com/vision/docs/detecting-crop-hints) ^[6](https://docs.cloud.google.com/vision/docs/features-list#fn6)^ ![image with cropped version](https://docs.cloud.google.com/static/vision/docs/images/crop_both.jpeg) | - Provides a bounding polygon for the cropped image, a confidence score, and an importance fraction of this salient region with respect to the original image for each request. - You can provide up to 16 image ratio values (width:height) for a single image. |
| ### [Web entities and pages](https://docs.cloud.google.com/vision/docs/detecting-web) ^[7](https://docs.cloud.google.com/vision/docs/features-list#fn7)^ ![image with web entities table](https://docs.cloud.google.com/static/vision/docs/images/web_entities.png) | - Provides a series of related Web content to an image. - Returns the following information: - **Web entities**: Inferred entities (labels/descriptions) from similar images on the Web. - **Full matching images**: A list of URLs for fully matching images of any size on the Internet. - **Partial matching images**: A list of URLs for images that share key-point features, such as a cropped version of the original image. - **Pages with matching images**: A list of Webpages (identified by page URL, page title, matching image URL) with an image that satisfies the conditions described above. - **Visually similar images**: A list of URLs for images that share some features with the original image. - **Best guess label**: A best guess as to the topic of the requested image inferred from similar images on the Internet. |
| ### [Explicit content detection (SafeSearch)](https://docs.cloud.google.com/vision/docs/detecting-safe-search) | - Provides likelihood ratings for the following explicit content categories: `adult`, `spoof`, `medical`, `violence`, and `racy`. - Likelihoods ratings are expressed as 6 different values: `UNKNOWN`, `VERY_UNLIKELY`, `UNLIKELY`, `POSSIBLE`, `LIKELY`, or `VERY_LIKELY`. |
| ### [Face detection](https://docs.cloud.google.com/vision/docs/detecting-faces) ![sample image with face detection](https://docs.cloud.google.com/static/vision-ai/docs/images/face_detection2x.png) | - Locates faces with bounding polygons, and identifies specific facial "landmarks" such as eyes, ears, nose, mouth, etc. along with their corresponding confidence values. - Returns likelihood ratings for general image properties (underexposed, blurred, headwear present). - Likelihoods ratings are expressed as 6 different values: `UNKNOWN`, `VERY_UNLIKELY`, `UNLIKELY`, `POSSIBLE`, `LIKELY`, or `VERY_LIKELY`. - **Specific individual [Facial Recognition](https://en.wikipedia.org/wiki/Facial_recognition_system) is not supported.** |

^1.
*Image credit*:
[Nikolay Vorobyev](https://unsplash.com/photos/jaH3QF46gAY) on
[Unsplash](https://unsplash.com/) (*annotations added*).
[↩](https://docs.cloud.google.com/vision/docs/features-list#ref1 "Go to image.")^

^2.
*Image credit*:
[Robert Scoble](https://www.flickr.com/photos/scobleizer/4249731778/)
([CC BY 2.0](https://creativecommons.org/licenses/by/2.0/), *annotation added*).
[↩](https://docs.cloud.google.com/vision/docs/features-list#ref2 "Go to image.")^

^3.
*Image credit*:
[Alex Knight](https://unsplash.com/photos/wfwUpfVqrKU) on [Unsplash](https://unsplash.com/).
[↩](https://docs.cloud.google.com/vision/docs/features-list#ref3 "Go to image.")^

^4.
*Image credit*:
[Jeremy Bishop](https://unsplash.com/photos/QUwLZNchflk) on [Unsplash](https://unsplash.com/).
[↩](https://docs.cloud.google.com/vision/docs/features-list#ref4 "Go to image.")^

^5.
*Image credit:*
[Bogdan Dada](https://unsplash.com/photos/J9cBJjlpYKU) on [Unsplash](https://unsplash.com/)
(*annotations added*).
[↩](https://docs.cloud.google.com/vision/docs/features-list#ref5 "Go to image.")^

^6.
*Image credit*:
[Yasmin Dangor](https://images.unsplash.com/photo-1526398018-f9ee0723f228?ixlib=rb-1.2.1&auto=format&fit=crop&w=1400&q=80) on [Unsplash](https://unsplash.com/) (*original and cropped image shown*).
[↩](https://docs.cloud.google.com/vision/docs/features-list#ref6 "Go to image.")^

^7.
*Image credit*:
[Quinten de Graaf](https://unsplash.com/photos/KB0Ipylp7dc) on
[Unsplash](https://unsplash.com/).
[↩](https://docs.cloud.google.com/vision/docs/features-list#ref7 "Go to image.")^