作者: N. Pérez de la Blanca , J. M. Fuertes , M. Lucena
DOI: 10.1007/978-3-540-30074-8_16
关键词:
摘要: This paper presents a technique to enable deformable objects be matched throughout video sequences based on the information provided by multi-scale local histograms of images. We shall show that this is robust enough for viewpoint changes, lighting large motions object and small changes in rotation scale. Unlike other well-known color-based techniques, only uses gray level values image. The proposed algorithm mainly definition particular template model similarity measure histogram matching.