Convolutional Networks Based Edge Detector Learned via Contrast Sensitivity Function
Edge detection extracts rich geometric structures of the image and largely reduces the amount of data to be processed, providing essential input to many visual tasks. Traditional algorithms consist of three steps: smoothing, filtering and locating, in which the filters are usually designed manually and thresholds are selected without strictly theoretical support. In this paper, convolutional networks (ConvNets) are trained to detect edges by learning a group of filters and classifiers simultaneously. In addition, the contrast sensitivity function (CSF) in visual psychology is adopted to determine whether an edge is visible to human visual system (HVS). Edge samples of various appearance are synthesised, and then labelled via CSF for model training. Multi-channel ConvNets are trained to perceive edges of different frequencies and composed at last. Compared with classical algorithms, ConvNets-CSF model is more robust to contrast variation and more biologically plausible. Evaluated on USF edge detection dataset, it achieves comparable performance as Canny edge detector and outperforms other classical algorithms.
KeywordsEdge detection Convolutional networks Contrast sensitivity function
The work was supported in part by the National Basic Research Program of China (2013CB329304), the “Twelfth Five-Year” National Science & Technology Support Program of China (No. 2012BAI12B01), the Major Project of National Social Science Foundation of China (No.12&ZD119), the research special fund for public welfare industry of health (201202001) and National Natural Science Foundation of China (No. 81170906).
- 1.Sobel, I.: An isotropic 3x3 image gradient operator. Talk at the Stanford, Artificial Intelligence Project (SAIP) (1968)Google Scholar
- 2.Prewitt, J.M.S.: Object enhancement and extraction. In: Lipkin, B.S., Rosenfeld, A. (eds.) Picture Processing and Psychopictorics, pp. 75–149. Academic Press, New York (1970)Google Scholar
- 3.Roberts, L.G.: Machine perception of three-dimensional solids. In: Tippett, T., et al. (eds.) Optical and Electro-Optical Information Processing, pp. 159–197. MIT Press, Cambridge (1965)Google Scholar
- 8.Pablo, A., Michael, M., Charless, F., Jitendra, M.: Contour detection and hierarchical image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 57–74 (2011)Google Scholar
- 12.Watson, A.B., Ahumada Jr, A.J.: A standard model for foveal detection of spatial contrast. J. Vison 5, 717–740 (2005)Google Scholar
- 14.Bastien, F., Lamblin, P., et al.: Theano: new features and speed improvements. In: Deep Learning Workshop, NIPS (2012)Google Scholar