An Efficient Color Edge Detection Using the Mahalanobis Distance
0
조회
0
다운로드
1
인용
0
참고문헌
키워드
초록
The performance of edge detection often relies on its ability to correctlydetermine the dissimilarities of connected pixels. For grayscale images, the dissimilarityof two pixels is estimated by a scalar difference of their intensities and for color images,this is done by using the vector difference (color distance) of the three-color components. The Euclidean distance in the RGB color space typically measures a color distance. However, the RGB space is not suitable for edge detection since its color componentsdo not coincide with the information human perception uses to separate objects frombackgrounds. In this paper, we propose a novel method for color edge detection bytaking advantage of the HSV color space and the Mahalanobis distance. The HSVspace models colors in a manner similar to human perception. The Mahalanobisdistance independently considers the hue, saturation, and lightness and gives themdifferent degrees of contribution for the measurement of color distances. Therefore, ourmethod is robust against the change of lightness as compared to previous approaches. Furthermore, we will introduce a noise-resistant technique for determining imagegradients. Various experiments on simulated and real-world images show that ourapproach outperforms several existing methods, especially when the images vary inlightness or are corrupted by noise.
Abstract
The performance of edge detection often relies on its ability to correctlydetermine the dissimilarities of connected pixels. For grayscale images, the dissimilarityof two pixels is estimated by a scalar difference of their intensities and for color images,this is done by using the vector difference (color distance) of the three-color components. The Euclidean distance in the RGB color space typically measures a color distance. However, the RGB space is not suitable for edge detection since its color componentsdo not coincide with the information human perception uses to separate objects frombackgrounds. In this paper, we propose a novel method for color edge detection bytaking advantage of the HSV color space and the Mahalanobis distance. The HSVspace models colors in a manner similar to human perception. The Mahalanobisdistance independently considers the hue, saturation, and lightness and gives themdifferent degrees of contribution for the measurement of color distances. Therefore, ourmethod is robust against the change of lightness as compared to previous approaches. Furthermore, we will introduce a noise-resistant technique for determining imagegradients. Various experiments on simulated and real-world images show that ourapproach outperforms several existing methods, especially when the images vary inlightness or are corrupted by noise.
참고문헌 (16)
- C.L. Novak, "Color edge detection", Proceedings of DARPA Image Understanding Workshop, pp.35~37 (1987)
- A. Koschan, "Detection and classification of edges in color images", IEEE Signal Processing Magazine, 22(1), pp.64~73 (2005)
- M. Hedley, "Segmentation of color images using spatial and color space information", Journal of Electronic Imaging, 1(4), pp.374~380 (1992)
- S. Di Zenzo, "A note on the gradient of a multi-image", Computer Vision, Graphics, and Image Processing, 33(1), pp.116~125 (1986)
- J. Fan, "Automatic image segmentation by integrating color-edge extraction and seeded region growing", IEEE Transactions on Image Processing, 10(10), pp.1454~1466 (2001)
- E. Nezhadarya, "A new scheme for robust gradient vector estimation in color images", IEEE Transactions on Image Processing, 20(8), pp.2211~2220 (2011)
- P. E. Trahanias, "Color edge detection using vector order statistics", IEEE Transactions on Image Processing, 2(2), pp.259~264 (1993)
- J. Lee, "Morphologic edge detection", IEEE Journal of Robotics and Automation, 3(2), pp.142~156 (1987)
- S. Wesolkowski, "Color edge detection in RGB using jointly Euclidean distance and vector angle", Proceedings of the IAPR Vision Interface Conference, pp.9~16 (1999)
- L. Shafarenko, "Automatic watershed segmentation of randomly textured color images", IEEE Transactions on Image Processing, 6(11), pp.1530~1544 (1997)
- A. N. Evans, "A morphological gradient approach to color edge detection", IEEE Transactions on Image Processing, 15(6), pp.1454~1463 (2006)
- M. A. Ruzon, "Color edge detection with the compass operator", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.160~166 (1999)
- P. C. Mahalanobis, "On the generalized distance in statistics", Proceedings of the National Institute of Sciences (Calcutta), Ⅱ(1), pp.49~55 (1936)
- P. Chauhan, "Edge detection comparison on various color spaces using histogram equalization", International Journal of Advance Computational Engineering and Networking, 1(4), pp.7~10 (2013)
- J. Canny, "A computational approach to edge detection", IEEE Transactions on Pattern Analysis and Machine Intelligence, 8(6), pp.679~698 (1986)
- I. E. Abdou, "Quantitative design and evaluation of enhancement", thresholding edge detectors, 1979, pp.67(5), 753~763