Inference of Surfaces, 3D Curves, and Junctions from Sparse, Noisy, 3D Data
IEEE Transactions on Pattern Analysis and Machine Intelligence
Mean Shift: A Robust Approach Toward Feature Space Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Computational Framework for Segmentation and Grouping
Computational Framework for Segmentation and Grouping
Unsupervised Segmentation of Color Images Based on k -means Clustering in the Chromaticity Plane
CBAIVL '99 Proceedings of the IEEE Workshop on Content-Based Access of Image and Video Libraries
ICMI '02 Proceedings of the 4th IEEE International Conference on Multimodal Interfaces
A New Method of Color Image Segmentation Based on Intensity and Hue Clustering
ICPR '00 Proceedings of the International Conference on Pattern Recognition - Volume 3
Automatic Text Location in Natural Scene Images
ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
ICDAR 2003 Robust Reading Competitions
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
First Order Augmentation to Tensor Voting for Boundary Inference and Multiscale Analysis in 3D
IEEE Transactions on Pattern Analysis and Machine Intelligence
Image Repairing: robust image synthesis by adaptive ND tensor voting
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Hi-index | 0.00 |
Most computer vision applications often require reliable segmentation of objects when they are mixed with corrupted text images. In the presence of noise, graffiti, streaks, shadows and cracks, this problem is particularly challenging. We propose a tensor voting framework in 3D for the analysis of candidate features. The problem has been formulated as an inference of hue and intensity layers from a noisy and possibly sparse point set in 3D. Accurate region layers are extracted based on the smoothness of color features by generating candidate features with outlier rejection and text segmentation. The proposed method is non-iterative and consistently handles both text data and background without using any prior information on the color space.