A novel edge detection approach using a fusion model
Edge detection is a long standing but still challenging problem. Although there are many effective edge detectors, none of them can obtain ideal edges in every situation. To make the results robust for any image, we propose a new edge detection algorithm based on a two-level fusion model that combines several typical edge detectors together with new proposed edge estimation strategies. At the first level, we select three typical but diverse edge detectors. The edge score is calculated for every pixel in the image based on a consensus measurement by counting positive voting number of approaches. Then results are combined at the second level using the Hadamard product with two additional edge estimations proposed in the paper, based on edge spatial characteristics, where one is binary matrix of the most probable edge distribution and the other is a score matrix based on calculating differences between maxima and minima neighboring intensity change at each point. Comprehensive experiments are conducted on two image databases, and three evaluation methods are employed to measure the performance, viz. F1-measure, ROC and PFOM. Experiments results show that our proposed method outperforms the three standard baseline edge detectors and shows better results than a state-of-the-art method.
KeywordsEdge detection Fusion Most probable distribution Voting count score matrix Difference score matrix
We appreciate the support of the Chinese Natural Science Foundation under Grant No. 61070117, No. 61171169 and the Beijing Natural Science Foundation under Grant No. 4122004, No.4132013 and the Importation and Development of High-Caliber Talents Project of Beijing Municipal Institutions.
- 6.Farhadi A et al (2010) Every picture tells a story: generating sentences from images, Computer Vision–ECCV 2010. Springer Berlin Heidelberg 15–29Google Scholar
- 8.Gao W, Yang L, Zhang X, Liu H An improved Sobel edge detection, 3rd IEEE International Conference on Computer Science and Information Technology (ICCSIT), p 67–71Google Scholar
- 12.Lewis TW, Powers DMW (2004) Sensor fusion weighting measures in audio-visual speech recognition. Proc. 27th Australasian Conference on Computer Science 26:305–314Google Scholar
- 15.Mathworks (2002) Image processing toolbox for use with MATLAB. User’s guide version 3Google Scholar
- 17.Novak CL, Shafer SA (1987) Color edge detection. In: Proc. DARPA Image Understanding Workshop I:35–37Google Scholar
- 19.Powers DMW (2012) ROC-ConCert: ROC-based measurement of consistency and certainty. Spring Congress on Engineering and Technology (S-CET)Google Scholar
- 20.Powers DMW (2013) AdaBook & MultiBook: adaptive boosting with chance correction, 10th International Conference on Informatics in Control, Automation and Robotics (ICINCO), Reykjavic, JulyGoogle Scholar
- 21.Prewitt JMS (1970) Object enhancement and extraction, picture processing and psychopictorics. Academic PressGoogle Scholar
- 23.Roberts LG (1963) Machine perception of three-dimensional solids, No. TR315. Massachusetts Inst. of Tech Lexington Lincoln LabGoogle Scholar
- 25.Sobel I (1970) Camera models and machine perception, No. AIM-121. Stanford Univ. Calif. Dept. of Computer ScienceGoogle Scholar
- 26.Swets JA (1996) Signal detection theory and ROC analysis in psychology and diagnostics: collected papers. Lawrence Erlbaum Associates, IncGoogle Scholar