Contact emails [email protected], [email protected], [email protected]
Explainer https://github.com/WICG/shape-detection-api/blob/main/text_detection_explainer.md Specification https://wicg.github.io/shape-detection-api/text.html Summary The Text Detection API enables web applications to detect and recognize text within images, video frames, canvas elements, and camera streams. As part of the WICG Shape Detection API family, it exposes a modern asynchronous interface (`TextDetector.create()` and `detect()`) that returns recognized text along with enclosing bounding boxes and oriented corner coordinates. This provides web developers with fast, zero-payload optical character recognition directly within the browser while keeping user image data private. Blink component Blink>ShapeDetection Web Feature ID No information provided Motivation Web applications increasingly need to extract text from images, camera feeds, and video frames for use cases such as document and receipt scanning, real-time sign and menu translation, form autofill, and accessibility tools that make text inside images readable for screen readers. Today, web developers face significant tradeoffs between two approaches: 1. Cloud vision services: Uploading images over the network introduces latency, recurring server and API costs, failure in offline or low-connectivity environments, and data privacy concerns when handling sensitive documents. 2. Client-side libraries (eg WebAssembly): Shipping full OCR runtimes and models adds megabytes of payload to web page downloads, slows initial load times, and heavily taxes device CPU, memory, and battery. Providing a native Text Detection API directly in the browser resolves these tradeoffs. It eliminates the need for web applications to distribute heavy OCR models over the network and protects user privacy by processing images directly within the browser boundary without transmitting media to third-party endpoints. Initial public proposal https://github.com/WICG/shape-detection-api/issues/109 Goals for experimentation Requires code in //chrome? True Tracking bug https://bugs.chromium.org/p/chromium/issues/detail?id=556760835 Estimated milestones Shipping on desktop 168 Link to entry on the Chrome Platform Status https://chromestatus.com/feature/5644087665360896?gate=5114716158951424 This intent message was generated by Chrome Platform Status. -- You received this message because you are subscribed to the Google Groups "blink-dev" group. To unsubscribe from this group and stop receiving emails from it, send an email to [email protected]. To view this discussion visit https://groups.google.com/a/chromium.org/d/msgid/blink-dev/6abc89ca.7ebe5f11.106463.00a4.GAE%40google.com.
