Abstract. This paper describes a method of producing segmentation point candidates for on-line handwritten Japanese text by a support vector machine (SVM) to improve text recogniti...
Language models used in current automatic speech recognition systems are trained on general-purpose corpora and are therefore not relevant to transcribe spoken documents dealing w...
The performance of face recognition is greatly affected by illumination changes because intra-person variation of the captured images under different lighting conditions can be mu...
Insect species recognition is a typical application of image categorization and object recognition. Unlike generic image categorization datasets (such as the Caltech 101 dataset) ...
Abstract. In speech recognition, phonemes have demonstrated their efficacy to model the words of a language. While they are well defined for languages, their extension to human act...
Kaustubh Kulkarni, Edmond Boyer, Radu Horaud, Amit...