A feature descriptor based on the local patch clustering distribution for illumination-robust image matching

• Published in: Pattern recognition letters 2017-07, Vol.94, p.46-54
• Main Authors: Wang, Han, Yoon, Sang Min, Han, David K., Ko, Hanseok
• Format: Article
• Language: English
• Subjects: Clustering; Feature descriptor illumination change; Feature extraction; Illumination; Image matching; Image processing systems; Local patch clustering distribution; Luminance distribution; Pattern recognition
• ISSN: 0167-8655; 1872-7344
• DOI: 10.1016/j.patrec.2017.05.010

•Local patch clustering distribution is proposed for use in illumination-robust image matching.•A dual codebook is proposed to generate local patch clustering distributions.•A saliency detection response increases the effectiveness of the proposed LPCD. This paper proposes a feature descriptor based on the local patch clustering distribution (LPCD), which preserves the salient features of a given image following changes in illumination. To mitigate the effects of illumination change, the proposed LPCD methodology consists of two steps. First, a local patch clustering assignment map is constructed by pairing the source image with a reference image. To resolve the quantization problem caused by an illumination change, a dual-codebook clustering method is employed so that an effective local patch clustering feature space can be constructed. Second, in the feature encoding process, the impact of the informative local patches that contain textural information is enhanced when using a saliency detection response as a method of weighting every local patch when the histogram feature is extracted. Experimental results show that the proposed local patch clustering space is more robust than the conventional intensity order-based space in response to changes in illumination.