Multimodal image matching via dual-codebook-based self-similarity hypercube feature descriptor and voting strategy

• Published in: Electronics letters Vol. 50; no. 21; pp. 1518 - 1520
• Main Authors: Wang, H, Han, D.K, Ko, H
• Format: Journal Article
• Language: English
• Published: Stevenage The Institution of Engineering and Technology 09.10.2014; John Wiley & Sons, Inc
• Subjects: Clustering; dual codebook clustering; dual codebook‐based self‐similarity hypercube feature descriptor; feature extraction; Hypercubes; Image and vision processing and display technology; image matching; k‐means clustering index; Matching; multimodal image matching; multimodal image quantisation problem; multimodal local image patch matching; pattern clustering; Self-similarity; Similarity; similarity family function; SSH; Strategy; thermal image patches; Voting; voting strategy; multimodal local image patch matching; dual codebook-based self-similarity hypercube feature descriptor; thermal image patches; multimodal image quantisation problem; similarity family function; SSH; dual codebook clustering; image matching; k-means clustering index; pattern clustering; voting strategy; feature extraction; multimodal image matching
• ISSN: 0013-5194; 1350-911X; 1350-911X
• DOI: 10.1049/el.2014.1802

An effective feature descriptor is proposed for multimodal local-image patch matching. The conventional self-similarity hypercube (SSH) fails in multimodal image matching due to different intensities of multimodal images. To mitigate this problem, a dual-codebook clustering is proposed for generating the descriptors. It is based on extracting a codebook, respectively, from visible and thermal images but sharing the same k-means clustering index of the local features of visible and thermal image patches. The experimental results show that the proposed approach effectively solves the multimodal image quantisation problem. Moreover, a voting strategy based on the proposed similarity family function facilitates the multimodal image matching more robustly compared with the conventional state-of-the-art methods.