Caption Localisation in Video Sequences by Fusion of Multiple Detectors
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Text segmentation in color images using tensor voting
Image and Vision Computing
Automatic segmentation of natural scene images based on chromatic and achromatic components
MIRAGE'07 Proceedings of the 3rd international conference on Computer vision/computer graphics collaboration techniques
A tensor voting for corrupted region inference and text image segmentation
MMM'07 Proceedings of the 13th international conference on Multimedia Modeling - Volume Part I
Detection of text region and segmentation from natural scene images
ISVC'05 Proceedings of the First international conference on Advances in Visual Computing
Hi-index | 0.00 |
Abstract: A new connected component based segmentation algorithm which automatically extracts text regions from natural scene images is proposed in this paper. This approach utilizes a multi-channel decomposition method to locate text blocks in complex backgrounds. Block alignment analysis and recognition confidence values are used in the combination and identification of the connected components. The algorithm is applied to a test image database and shows promising results.