A Review on Fuzzy Logic Based Object Recognition Techniques
Sanjay Arora · International Journal for Research in Applied Science and Engineering Technology · 2017
this paper discussed about various object recognition techniques such as text detection and recognition system based on a scalable feature learning algorithm and applied it to images of text in natural scenes.We demonstrated that with larger banks of features we are able to achieve increasing accuracy with top performance comparable to other systems, similar to results observed in other areas of computer vision and machine learning.A novel approach to learning shape prior models from images annotated with bounding boxes.Based on the shape representation of oriented edge points, our learning process is robust to clutter.In Scale Invariant Feature Transform (SIFT) feature matching was adopted to distinguish text characters in different languages, and a voting and geometric verification algorithm was presented to filter out false positive matches.