This paper proposes a hybrid approach of texture-based method and connected component-based one for extracting texts in real scene images. For detecting texts having a lot of variations in size, shape, etc, we use a multiple-continuously adaptive mean shift algorithm on the text probability image produced by a multi-layer perceptron. It is assumed that scene text lies on planar rectangular surfaces with homogeneous background colors. We correct perspective distortion using warping parameters calculated after segmentation of an input image. We can detect and reconstruct text images accurately and efficiently.
|Title of host publication||Proceedings - International Conference on Pattern Recognition|
|Number of pages||4|
|Publication status||Published - 2002|
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition
- Hardware and Architecture
- Electrical and Electronic Engineering