A Two-stage Online Handwritten Chinese Character Segmentation Algorithm Based on Dynamic Programming
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Text segmentation based on stroke filter
MULTIMEDIA '06 Proceedings of the 14th annual ACM international conference on Multimedia
A Multi-Lingual Translation System For Real-World Images
Journal of Integrated Design & Process Science
Accurate text localization in images based on SVM output scores
Image and Vision Computing
Vision-Based Text Segmentation System for Generic Display Units
IWINAC '09 Proceedings of the 3rd International Work-Conference on The Interplay Between Natural and Artificial Computation: Part II: Bioinspired Applications in Artificial and Natural Computation
Hi-index | 0.00 |
Abstract: Because of no prior knowledge about the color of characters, and the disturbance of lighting and noise, character segmentation of scene images is a very difficult issue. In this paper, a novel character segmentation method of color images from digital camera is presented combining edge detection, watershed transform and clustering. Since the extracted characters from color images are output by the binary format, they can be input directly to OCR system for recognition. The experimental results have proven its effectiveness.