Day 5/60 Reviewing AI & Machine Learning: AI & ML for On-Device Development

AI & ML for On-Device Development

Has developing AI for a mobile application been a challenge for you? Let me introduce you to Google’s machine learning kit.?

What is ML Kit?

https://developers.google.com/ml-kit

ML Kit is a platform that brings Google’s machine-learning capabilities to mobile developers in a powerful and easy-to-use package. It can be integrated seamlessly with Android and iOS apps.?

It offers a large number of vision and natural language APIs. I have attached the links to read their official documentation to get started on your preferred platform.?

Note: some APIs are not support for both platforms

Vision

  • Barcode scanning: Scan and process barcodes. Supports most standard 1D and 2D format
  • Face detection: Detect faces and facial landmarks.
  • Face mesh detection (New): Detect face mesh info on close-range images.
  • Text recognition v2: Recognize and extract text from images.
  • Image labeling: Identify objects, locations, activities, animal species, products, and more. Use a general-purpose base model or tailor to your use case with a custom TensorFlow Lite model.
  • Object detection and tracking: Localize and track in real time one or more objects in the live camera feed.
  • Digital ink recognition: Recognizes handwritten text and handdrawn shapes on a digital surface, such as a touch screen. Recognizes 300+ languages, emojis and basic shapes.
  • Pose detection: Detect the position of the human body in real time.
  • Selfie segmentation: Separate the background from users within a scene and focus on what matters.
  • Subject segmentation (New): Separate subjects (people, pets, or objects) from the background in a picture.
  • Document scanner (New): Digitize physical documents from pictures.

Natural Language

  • Language identification: Determine the language of a string of text with only a few words.
  • Translation: Translate text between 58 languages, entirely on device.
  • Smart reply: Generate reply suggestions in text conversations.
  • Entity extraction: Detect and locate entities (such as addresses, date/time, phone numbers, and more) and take action based on those entities. Works in 15 languages.

要查看或添加评论,请登录

Tom Zhang的更多文章

社区洞察

其他会员也浏览了