A user-augmented object query system using color and shape features for Taiwan wild birds photos

This paper proposes a user-augmented object query system based on the color and shape feature of Taiwan wild bird photos. 1,726 photos were collected from the Internet as the training and testing corpora. The color feature is the 32 dimensional HMMD color structure descriptors and, the shape feature is the width and height information about the beak and head of the target bird. A decision tree is built to determine the target species of the query photo. The experimental results show an 84% correct rate, which encourages us that the proposed method is feasible for image-based query of Taiwan wild birds. An ongoing study is conducted to combine more features and adopt more intelligent algorithm to improve the correct rate.