A Computational Approach to Edge Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Scale-Space and Edge Detection Using Anisotropic Diffusion
IEEE Transactions on Pattern Analysis and Machine Intelligence
Image selective smoothing and edge detection by nonlinear diffusion. II
SIAM Journal on Numerical Analysis
Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Emerging Topics in Computer Vision
Emerging Topics in Computer Vision
Photo Defect Detection for Image Inpainting
ISM '05 Proceedings of the Seventh IEEE International Symposium on Multimedia
Correlation Based Image Defect Detection
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 01
Object Removal By Cross Isophotes Exemplar-based Inpainting
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 03
ICIAR '08 Proceedings of the 5th international conference on Image Analysis and Recognition
Removal of Partial Occlusion from Single Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
Image inpainting based on probabilistic structure estimation
ACCV'10 Proceedings of the 10th Asian conference on Computer vision - Volume Part III
CrackTree: Automatic crack detection from pavement images
Pattern Recognition Letters
Hi-index | 0.00 |
Heritage structures are very important to mankind as they help in studying and understanding the growth of civilization and are sources of inspiration to modern craftsmen. However, many structures get degraded / vandalized due to various reasons like aging, material degradation, human interventions, etc. With the use of image inpainting techniques, one can digitally restore these structures. In almost all the available inpainting techniques, one has to manually select the target region. In this paper, we propose a novel approach to automatically identify cracks in the heritage structures. The method exploits the use of order-statistics filtering and the tensor voting to detect crack regions which are given as input to inpainting algorithms. The order-statistics filters enhance the contrast of the crack regions, which then act as input to a Canny edge detector. A 2D tensor voting is applied on the edge output for enhancing the curveness of the probable crack regions. Finally, image dilation is used for crack filling, generating the final target regions for image inpainting. We show the effectiveness of the method by conducting experiments on the images captured from the world Heritage site Hampi, Karnataka.