Object Recognition by Combining Binary Local Invariant Features and Color Histogram

In this paper, we propose an approach for object recognition using binary local invariant features and color information. In our approach, we use a fast detector for key point detection and binary local features descriptor for key point description. For local feature matching, the Fast library for Approximated Nearest Neighbors (FLANN) is applied to match the query image and reference image in data set. A homography matrix which represents transformation of object in scene image and reference image is estimated from matching pairs by using the Optimized Random Sample Consensus Algorithm (ORSA). Then, we detect object location in the image, and remove background of image. Next, significant color feature is used to calculate global color histogram since it reflects main content of primitive image and also ignores noises. Similarity of query image and reference object image is a linear combination of color histogram correlation and number of feature matches. As a result, the proposed method can overcome drawbacks of object recognition method using only local features or global features. In addition, the use of binary feature makes feature description as well as feature matching faster to meet the requirement of a real time system. For evaluation, we experiment with two well-known and latest local invariant features including the Oriented Fast and Rotated Binary Robust Independent Elementary Features (ORB) and Fast Retina Key point (FREAK) and a planar object data set. According to the result, ORB feature shows that it is powerful as our system obtained the higher accuracy and fast processing time. The experimental results also proved that combination of binary local invariant feature and significant color is effective for planar object recognition.