A New Color-to-Gray Conversion Method Based on Edge Detection

In recent years, the line projection approach is popular and simple for the color-to-gray conversion. This paper presents a new line projection global mapping method based on edge detection. Firstly, we calculate the ratio of the number of each candidate gray image boundary points to the number of the color image’s. All the gray images are determined by exhaustive search method. Secondly, we choose the maximum ratio as the optimal line projection direction. The method proposed in this paper focuses on the edge information of the image. Experimental results show that the proposed method is superior to the typical other methods in terms of the images with obvious regional features.

[1]  Martin Cadík,et al.  Perceptual Evaluation of Color‐to‐Grayscale Image Conversions , 2008, Comput. Graph. Forum.

[2]  Cewu Lu,et al.  Contrast preserving decolorization , 2012, 2012 IEEE International Conference on Computational Photography (ICCP).

[3]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Mohamed Cheriet,et al.  CorrC2G: Color to Gray Conversion by Correlation , 2017, IEEE Signal Processing Letters.

[5]  Garrison W. Cottrell,et al.  Color-to-Grayscale: Does the Method Matter in Image Recognition? , 2012, PloS one.

[6]  Yi Wan,et al.  A Novel Framework for Optimal RGB to Grayscale Image Conversion , 2016, 2016 8th International Conference on Intelligent Human-Machine Systems and Cybernetics (IHMSC).

[7]  Noriaki Suetake,et al.  Color removal method considering perceived lightness , 2017, Optical Review.

[8]  Eero P. Simoncelli,et al.  Image quality assessment: from error visibility to structural similarity , 2004, IEEE Transactions on Image Processing.

[9]  Peter Xiaoping Liu,et al.  GcsDecolor: Gradient Correlation Similarity for Efficient Contrast Preserving Decolorization , 2015, IEEE Transactions on Image Processing.