摘要
针对传统色彩传递算法在实际应用中灵活度不高的问题,提出一种基于感兴趣区域ROI(Regions of Interest)的色彩传递算法。通过提取目标图像的感兴趣区域,将其与用户所选图像进行拼贴,得到新目标图像,并以此进行色彩传递,解决了色彩传递用户对图像色彩处理多样化、个性化需求的问题。同时,针对传统感兴趣区域提取方法容易受纹理噪声干扰、提取尺寸不易控制等问题,提出一种基于变异度的感兴趣区域提取新算法。实验结果表明,该算法效果良好。基于变异度的感兴趣区域提取算法可更准确获取图像的感兴趣区域。基于感兴趣区域的色彩传递算法可在不影响图像主体内容表达的情况下,使得色彩传递的效果更加生动多变,更具个性化,提高了色彩传递应用的灵活度。
Aiming at the problem of low flexibility of traditional color transfer algorithm in practical application,we proposed a color transfer algorithm based on region of interest.By extracting the region of interest of the target image and collaging it with the user's selected image,a new target image was obtained,and color transfer was carried out,which solved the problem of the user's diversification and individualization of image color processing.To solve the problem that traditional ROI extraction methods were easily disturbed by texture noise and the size of extraction was not easy to control,we proposed a new ROI extraction algorithm based on coefficient of variance.The experimental results show that the proposed algorithm works well.The ROI extraction algorithm based on the coefficient of variance can obtain the ROI of the image more accurately.The color transfer algorithm based on ROI can make the effect of color transfer more vivid and changeable without affecting the expression of the main content of the image,and improve the flexibility of the application of color transfer.
引文
[1]朱黎博,孙韶媛,谷小婧,等.基于色彩传递与扩展的图像着色算法[J].中国图象图形学报,2010,15(2):200-205.
[2]靳坤.黑白视频的色彩迁移技术的研究与实现[D].呼和浩特:内蒙古大学,2016.
[3]滕秀花,胡文瑜,陈敏.一种基于SLIC的超像素快速色彩传递算法[J].哈尔滨师范大学自然科学学报,2014,30(3):77-80.
[4]许文韬,陈昭炯.主体对象可控的渐进式色彩传递[J].计算机工程,2016,42(9):246-251.
[5]仲红玉,尹丽菊,高明亮.多参数亮度值重映射的颜色传递方法[J].红外与激光工程,2018,47(5):21-28.
[6]Harris C,Stephens M.A combined corner and edge detector[C]//4th Alvey Vision Conference,1988:147-151.
[7]You J,Cohen H A,Pissaloux E.A new approach to object recognition in textured images[C]//Proceedings of the 1995 International Conference on Image Processing.IEEE,1995:2639.
[8]Itti L,Koch C.Computational modeling of visual attention[J].Nature Reviews Neuroscience,2001,2(3):100-112.
[9]陈昭炯,叶东毅.变异系数的新性质及其在图像处理中的应用[J].小型微型计算机系统,2006,27(1):162-165.