In computer vision and image processing feature detection includes methods for computing abstractions of image information and making local decisions at every image point whether there is an image feature of a given type at that point or not. The resulting features will be subsets of the image domain, often in the form of isolated points, continuous curves or connected regions.
- Neural Structured Learning (NSL)
Google Tensorflow Blog have some content about "Neural Structured Learning in TensorFlow".
Visualizing ML training using TensorFlow.js and Baseball data.
Face Detection & Recognition
- Haar-cascade Detection
Check this video from Youtube and see how Haar working.
- Detect Feeling
- Video Human emotions detection
Web verification base on face recognition
Some idea for using case
Face recognition can use on many verification case.