Object recognition and content-based image retrieval systems rely heavily on the accurate and efficient identification of shapes. A fundamental requirement in the shape analysis ...
Dragomir Yankov, Eamonn J. Keogh, Li Wei, Xiaopeng...
Abstract. An approach to symbolic contour extraction will be described that consists of three stages: enhancement, detection, and extraction of edges and corners. Edges and corners...
Tino Lourens, Kazuhiro Nakadai, Hiroshi G. Okuno, ...
To find out how the representations of structured visual objects depend on the co-occurrence statistics of their constituents, we exposed subjects to a set of composite images wit...
Shimon Edelman, Benjamin P. Hiles, Hwajin Yang, Na...
A new technique to locate content-representing words for a given document image using representation of character shapes is described. A character shape code representation define...
In discriminative training, such as Maximum Mutual Information Estimation (MMIE) training, a word lattice is usually used as a compact representation of many different sentence hy...