The extraction of optimal features, in a classification sense, is still quite challenging in the context of large-scale classification problems (such as visual recognition), inv...
This article proposes a method for learning object templates
composed of local sketches and local textures, and
investigates the relative importance of the sketches and textures
...
Haifeng Gong, Song Chun Zhu, Ying Nian Wu, Zhangzh...
Current feature-based object recognition methods use information derived from local image patches. For robustness, features are engineered for invariance to various transformation...
Color object recognition methods that are based on image retrieval algorithms can handle changes of illumination via image normalization, e.g. simple color-channel-normalization1 ...
This paper presents a semi-supervised learning (SSL) approach to find similarities of images using statistics of local matches. SSL algorithms are well known for leveraging a larg...