结合视觉显著图的Seam Carving图像缩放方法
|
摘要
Seam Carving算法在缩放主体区域与背景颜色对比不明显或者视觉主体区域较大的图像时,可能会造成图像视觉主体变形和重要内容缺失的现象.为了改善Seam Carving算法的不足,采用图像梯度图和显著图结合的方法来改进图像的梯度能量图.实验表明,这种方法在缩放图像时比Seam Carving算法更能很好地保持图像重要内容,整体视觉效果较好,图像像素的平均能量值更大,图像缩放质量更好.
Seam Carving algorithm may result in the distortion of the visual subject area and the missing of the important content of the image when scaling an image with no obvious contrast between the subject area and the background color or with larger subject area.In order to improve the lack of Seam Carving algorithm,we use a combination of image gradient graph and saliency map to improve the gradient energy graph of the image.The results of experiments show that,compare with the Seam Carving algorithm,the proposed method can better maintain the important content of the image,preserves a better overall visual effect,and obtains a larger average energy value of the image pixel and a better image scaling quality in scaling the image.
Seam Carving algorithm may result in the distortion of the visual subject area and the missing of the important content of the image when scaling an image with no obvious contrast between the subject area and the background color or with larger subject area.In order to improve the lack of Seam Carving algorithm,we use a combination of image gradient graph and saliency map to improve the gradient energy graph of the image.The results of experiments show that,compare with the Seam Carving algorithm,the proposed method can better maintain the important content of the image,preserves a better overall visual effect,and obtains a larger average energy value of the image pixel and a better image scaling quality in scaling the image.
引文
[1]张洋.基于双线性插值法的图像缩放算法的设计与实现[J].电子设计工程,2016,24(3):169-175.ZHANG Y.Design and implementation of image scaling algorithm based on bilinear interpolation[J].Electronic Design Engineering,2016,24(3):169-175.
[2]HARB S M E,ISA N A M,SALAMAH S.New adaptive interpolation scheme for image upscaling[J].Multimedia Tools and Applications,2016,75(12):7 293-7 325.
[3]SETLUR V,TAKAGI S,RASKAR R.Automatic image retargetting[C].Proc of Mobile and Ubiquitous Multimedia(MUM),2005:59-68.
[4]赵旦峰,王博,杨大为.基于随机置乱的内容感知图像缩放算法[J].吉林大学学报:工学版,2015,45(4):1 324-1 328.ZHAO D F,WANG B,YANG D W.Content-Aware image resizing based on random permutation[J].Journal of Jilin University:Engineering and Technology Edition,2015,45(4):1 324-1 328.
[5]AVIDAN S,SHAMIR A.Seam carving for content-aware image resizing[J].Acm Transactions on Graphics,2007,26(3):10.
[6]CHOI J,KIM C.Sparse seam-carving for structure preserving image retargeting[J].Journal of Signal Processing Systems,2016,85(2):1-9.
[7]赵伟伟,张俊华,王逍.改进能量函数的Seam Carving图像缩放方法[J].云南大学学报:自然科学版,2014,36(2):181-186.ZHAO W W,ZHANG J H,WANG X.Seam carving with improved energy function for image resizing[J].Journal of Yunnan University:Natural Sciences Edition,2014,36(2):181-186.
[8]彭国琴,施美玲,杨磊.一种基于视觉显著图的线裁剪算法[J].中国传媒大学学报:自然科学版,2011,18(2):74-78.PENG G Q,SHI M L,YANG L.Seam carving for image resizing based on saliency[J].Journal of Communication University of China:Science and Technology,2011,18(2):74-78.
[9]LIU,SUN K,YAN B.Matching-area-based seam carving for video retargeting[J].IEEE Transactions on Circuits&Systems for Video Technology,2013,23(2):302-310.
[10]CHEN Y,PAN Y,SONG M.Improved seam carving combining with 3D saliency for image retargeting[J].Neurocomputing,2015,151:645-653.
[11]林晓,张晓煜,马利庄.基于缝裁剪和变形的图像缩放方法[J].计算机科学,2015,42(9):289-292.LIN X,ZHANG X Y,MA L Z.Image resizing based on seam carving and warping[J].Computer Science,2015,42(9):289-292.
[12]ZHOU B,WANG X,CAO S.Optimal bi-directional seam carving for compressibility-aware image retargeting[J].Journal of Visual Communication&Image Representation,2016(41):21-30.
[13]SCHOLKOPF B,PLATT J,HOFMANN T.Graphbased visual saliency[J].Advances in Neural Information Processing Systems,2007,19:545-552.
[14]潘跃龙,顾寄南,郑立斌.基于梯度算子的边缘检测方法的研究与改进[J].制造业自动化,2014(17):82-84.PAN Y L,GU J N,ZHENG L B.Research and improvement on the algorithms of image edge detection based on gradient operators[J].Manufacturing Automation,2014(17):82-84.
[15]ITTI L,KOCH C,NIEBUR E.A Model of saliencybased visual attention for rapid scene analysis[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,1998,20(11):1 254-1 259.
[2]HARB S M E,ISA N A M,SALAMAH S.New adaptive interpolation scheme for image upscaling[J].Multimedia Tools and Applications,2016,75(12):7 293-7 325.
[3]SETLUR V,TAKAGI S,RASKAR R.Automatic image retargetting[C].Proc of Mobile and Ubiquitous Multimedia(MUM),2005:59-68.
[4]赵旦峰,王博,杨大为.基于随机置乱的内容感知图像缩放算法[J].吉林大学学报:工学版,2015,45(4):1 324-1 328.ZHAO D F,WANG B,YANG D W.Content-Aware image resizing based on random permutation[J].Journal of Jilin University:Engineering and Technology Edition,2015,45(4):1 324-1 328.
[5]AVIDAN S,SHAMIR A.Seam carving for content-aware image resizing[J].Acm Transactions on Graphics,2007,26(3):10.
[6]CHOI J,KIM C.Sparse seam-carving for structure preserving image retargeting[J].Journal of Signal Processing Systems,2016,85(2):1-9.
[7]赵伟伟,张俊华,王逍.改进能量函数的Seam Carving图像缩放方法[J].云南大学学报:自然科学版,2014,36(2):181-186.ZHAO W W,ZHANG J H,WANG X.Seam carving with improved energy function for image resizing[J].Journal of Yunnan University:Natural Sciences Edition,2014,36(2):181-186.
[8]彭国琴,施美玲,杨磊.一种基于视觉显著图的线裁剪算法[J].中国传媒大学学报:自然科学版,2011,18(2):74-78.PENG G Q,SHI M L,YANG L.Seam carving for image resizing based on saliency[J].Journal of Communication University of China:Science and Technology,2011,18(2):74-78.
[9]LIU,SUN K,YAN B.Matching-area-based seam carving for video retargeting[J].IEEE Transactions on Circuits&Systems for Video Technology,2013,23(2):302-310.
[10]CHEN Y,PAN Y,SONG M.Improved seam carving combining with 3D saliency for image retargeting[J].Neurocomputing,2015,151:645-653.
[11]林晓,张晓煜,马利庄.基于缝裁剪和变形的图像缩放方法[J].计算机科学,2015,42(9):289-292.LIN X,ZHANG X Y,MA L Z.Image resizing based on seam carving and warping[J].Computer Science,2015,42(9):289-292.
[12]ZHOU B,WANG X,CAO S.Optimal bi-directional seam carving for compressibility-aware image retargeting[J].Journal of Visual Communication&Image Representation,2016(41):21-30.
[13]SCHOLKOPF B,PLATT J,HOFMANN T.Graphbased visual saliency[J].Advances in Neural Information Processing Systems,2007,19:545-552.
[14]潘跃龙,顾寄南,郑立斌.基于梯度算子的边缘检测方法的研究与改进[J].制造业自动化,2014(17):82-84.PAN Y L,GU J N,ZHENG L B.Research and improvement on the algorithms of image edge detection based on gradient operators[J].Manufacturing Automation,2014(17):82-84.
[15]ITTI L,KOCH C,NIEBUR E.A Model of saliencybased visual attention for rapid scene analysis[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,1998,20(11):1 254-1 259.