Vision Kit integrates visual AI capabilities, including face liveness detection (interactiveLiveness), card recognition (CardRecognition), document scanning (DocumentScanner), and AI image recognition control (visionImageAnalyzer). The face liveness detection capability checks whether a user is a real live person by enabling users to interact with devices. The card recognition capability enables structured recognition for certificates such as ID cards, vehicle licenses, driver's licenses, passports, and bank cards. The document scanning capability takes photos of documents and converts them into high-definition scanned copies. The AI image recognition control enables scenario-specific text recognition, subject segmentation, and image search. The interactive liveness detection and card recognition capabilities are free of charge during the trial period by December 31, 2026. Before starting to charge these capabilities, Huawei will publish a formal charging adjustment notice in advance.
Vision Kit provides the following capabilities:
Face liveness detection: checks whether a user is a real live person based on interactions with the user.
Card recognition: structured recognition of different certificates.
Document scanning: takes photos of documents and converts them into high-definition scanned copies.
AI image recognition: enables scenario-specific text recognition, subject segmentation, and image search.
| Capability | Supported Device |
|---|---|
| Face liveness detection | Phones and tablets |
| Card recognition | Phones and tablets |
| Document scanning | Phones and tablets |
| AI image recognition | Phones, tablets, and PCs/2-in-1 devices |
| AI Capability | Constraint |
|---|---|
| Face liveness detection | - Languages supported for text: simplified Chinese, traditional Chinese, English, Uyghur, and Tibetan - Languages supported for voice broadcast: simplified Chinese and English - Currently, this capability does not support the landscape mode or split-screen mode. |
| Card recognition | - Supported languages: simplified Chinese and English - Currently, this capability supports only 2nd-generation ID cards, bank cards, passports, driver's licenses, and vehicle licenses issued by the Chinese mainland (not including cards issued by Hong Kong (China), Macao (China), Taiwan (China), and other countries or regions). - The aspect ratio of a card must be the same as that of the actual card. The card must not be deformed. The shooting angle must be less than 30 degrees. - The card image must be clear and complete. There is no moire, block, reflection, or card cover. - This control should not be blocked by another component or window. |
| Document scanning | - Supported languages: simplified Chinese and English - Currently, document scanning supports only phones and tablets. - This control should not be blocked by another component or window. |
| AI image recognition | - Languages supported for text: simplified Chinese, traditional Chinese, English, Uyghur, and Tibetan - The minimum image resolution is 100 x 100. - Image analysis supports only static non-vector images, which means that SVG and GIF images cannot be analyzed. The image PixelMap can be passed for analysis. Currently, only RGBA_8888 images are supported. - The minimum aspect ratio is 1:3 (the height must be less than 3 times of the width) for images to be translated and 1:7 (the height must be less than 7 times of the width) for images to have their text recognized. - For details about the supported devices, see Constraints. |