[go: nahoru, domu]
Google Git
Sign in
chromium / chromium / src / b70c6743a427cc48ebb2e835ef92c9c24e068c22 / . / services / screen_ai
tree: ec6c1f74526993ccf38e110b2636868a43186791 [path history] [tgz]
  1. buildflags/
  2. proto/
  3. public/
  4. sandbox/
  5. BUILD.gn
  6. DEPS
  7. DIR_METADATA
  8. OWNERS
  9. README.md
  10. screen_ai_library_wrapper.h
  11. screen_ai_library_wrapper_fake.cc
  12. screen_ai_library_wrapper_fake.h
  13. screen_ai_library_wrapper_impl.cc
  14. screen_ai_library_wrapper_impl.h
  15. screen_ai_ocr_perf_test.cc
  16. screen_ai_service_impl.cc
  17. screen_ai_service_impl.h
  18. screen_ai_service_impl_unittest.cc
services/screen_ai/README.md

Chrome Screen AI Library

Purpose

Chrome Screen AI library provides two on-device functionalities for Chrome and ChromeOS:

  • Main Content Extraction: Intelligently isolates the main content of a web page, improving its readability by stripping distracting elements (based on the accessibility tree).
  • Optical Character Recognition: Extracts text from image.

These functionalities are entirely on device and do not send any data to network or store on disk.

Development and Deployment

  • Source: Developed within Google's internal source code repository (google3).
  • Platforms: Built for ChromeOS, Linux, Mac, and Windows.
  • Distribution:
    • ChromeOS: Distributed via DLC (Dynamic Link Component).
    • Linux, Mac, Windows: Delivered on-demand through the component updater.

How to Use

See: chrome/browser/screen_ai/README.md

Bugs Component:

Chromium > UI > Accessibility > MachineIntelligence