Gabor-based kernel self-optimization Fisher discriminant for optical character segmentation from text-image-mixed document
Optik, 2015•Elsevier
Recognizing optical character from document image of text mixed by figure has its wide
applications such as document auto-reading. Segmenting the document region from text-
mixed is a crucial step of this system. The segmentation procedure includes two stages, one
is to extract the texture features of each block based on Gabor filter, and second is to classify
the texture features for segmentation based kernel self-optimization Fisher classifier. Some
experiments are implemented to testify the performance of the proposed method.
applications such as document auto-reading. Segmenting the document region from text-
mixed is a crucial step of this system. The segmentation procedure includes two stages, one
is to extract the texture features of each block based on Gabor filter, and second is to classify
the texture features for segmentation based kernel self-optimization Fisher classifier. Some
experiments are implemented to testify the performance of the proposed method.
Abstract
Recognizing optical character from document image of text mixed by figure has its wide applications such as document auto-reading. Segmenting the document region from text-mixed is a crucial step of this system. The segmentation procedure includes two stages, one is to extract the texture features of each block based on Gabor filter, and second is to classify the texture features for segmentation based kernel self-optimization Fisher classifier. Some experiments are implemented to testify the performance of the proposed method.
Elsevier
以上显示的是最相近的搜索结果。 查看全部搜索结果