Pre-processing is an important step in digital image matting, which aims to classify more accurate foreground and background pixels from the unknown region of the input three-region mask （Trimap）. This step has no r...Pre-processing is an important step in digital image matting, which aims to classify more accurate foreground and background pixels from the unknown region of the input three-region mask （Trimap）. This step has no relation with the well-known matting equation and only compares color differences between the current unknown pixel and those known pixels. These newly classified pure pixels are then fed to the matting process as samples to improve the quality of the final matte. However, in the research field of image matting, the importance of pre-processing step is still blurry. Moreover, there are no corresponding review articles for this step, and the quantitative comparison of Trimap and alpha mattes after this step still remains unsolved. In this paper, the necessity and the importance of pre-processing step in image matting are firstly discussed in details. Next, current pre-processing methods are introduced by using the following two categories： static thresholding methods and dynamic thresholding methods. Analyses and experimental results show that static thresholding methods, especially the most popular iterative method, can make accurate pixel classifications in those general Trimaps with relatively fewer unknown pixels. However, in a much larger Trimap, there methods are limited by the conservative color and spatial thresholds. In contrast, dynamic thresholding methods can make much aggressive classifications on much difficult cases, but still strongly suffer from noises and false classifications. In addition, the sharp boundary detector is further discussed as a prior of pure pixels. Finally, summaries and a more effective approach are presented for pre-processing compared with the existing methods.展开更多
This paper proposed a method to automatically generate the trimap for digital matting. Camera parameters of aperture and shutter speed are used to control its exposure, and accordingly to take pictures of stationary f...This paper proposed a method to automatically generate the trimap for digital matting. Camera parameters of aperture and shutter speed are used to control its exposure, and accordingly to take pictures of stationary foreground with blurred background. Our method was inspired by color difference matting, both of which require a pre-record background image. In our method, only one image was required. Upon this input image, the process of blurring-deblurring, subtraction, thresholding and dilation were applied to finally generate the trimap. No user＇ s direct interface with the image was needed, and the user only needed to adjust the threshold or width of dilation for some input images. It reduces users＇ conservative interaction, and results are reliable for most of the pictures.展开更多
In this paper,we aim to propose a novel and effective iris segmentation method that is robust to uneven light intensity and different kinds of noises such as occlusion by light spots,eyelashes,eyelids,specta-cle-frame...In this paper,we aim to propose a novel and effective iris segmentation method that is robust to uneven light intensity and different kinds of noises such as occlusion by light spots,eyelashes,eyelids,specta-cle-frame,etc.Unlike previous methods,the proposed method makes full use of gray intensities of the iris image.Inspired by the matting algorithm,a premier assumption is made that the foreground and background images of the iris image are both locally smooth.According to the RST algorithm,trimaps are built to provide priori in-formation.Under the assumption and priori,the optimal alpha matte can be obtained by least square loss function.A series of effective post processing methods are applied to the alpha image to obtain a more precise iris seg-mentation.The experiment on CASIA-iris-thousand database shows that the proposed method achieves a much better performance than conventional methods.Our experimental results achieve 20.5%and 26.4%,more than the well-known integro-differential operator and edge detection combined with Hough transform on iris seg-mentation rate respectively.The stability and validity of the proposed method is further demonstrated through the complementary experiments on the challenging iris images.展开更多
RC算法引入区域级别的对比度,对颜色模型进行重新量化,能大幅提高处理速度、突出显著目标,然而其基于图的分割算法易出现分割区域不能较好地贴合物体边缘的问题。引入优化的SLIC算法代替基于图的分割算法,对RC算法进行改进,并实现一个...RC算法引入区域级别的对比度,对颜色模型进行重新量化,能大幅提高处理速度、突出显著目标,然而其基于图的分割算法易出现分割区域不能较好地贴合物体边缘的问题。引入优化的SLIC算法代替基于图的分割算法,对RC算法进行改进,并实现一个基于图像显著性识别的自动抠图系统,克服传统抠图系统必须人工标记的缺点。实验结果表明,相比IT、MZ、GB、RC等经典算法,改进的RC算法抠取的显著目标更精确,其查准率、查全率、 F 值分别为0.82、0.85和0.83,系统能自动抠取显著目标并提供图片合成应用。展开更多
文摘Pre-processing is an important step in digital image matting, which aims to classify more accurate foreground and background pixels from the unknown region of the input three-region mask （Trimap）. This step has no relation with the well-known matting equation and only compares color differences between the current unknown pixel and those known pixels. These newly classified pure pixels are then fed to the matting process as samples to improve the quality of the final matte. However, in the research field of image matting, the importance of pre-processing step is still blurry. Moreover, there are no corresponding review articles for this step, and the quantitative comparison of Trimap and alpha mattes after this step still remains unsolved. In this paper, the necessity and the importance of pre-processing step in image matting are firstly discussed in details. Next, current pre-processing methods are introduced by using the following two categories： static thresholding methods and dynamic thresholding methods. Analyses and experimental results show that static thresholding methods, especially the most popular iterative method, can make accurate pixel classifications in those general Trimaps with relatively fewer unknown pixels. However, in a much larger Trimap, there methods are limited by the conservative color and spatial thresholds. In contrast, dynamic thresholding methods can make much aggressive classifications on much difficult cases, but still strongly suffer from noises and false classifications. In addition, the sharp boundary detector is further discussed as a prior of pure pixels. Finally, summaries and a more effective approach are presented for pre-processing compared with the existing methods.
基金Supported by the National Key Techenology Innovation Program of China under Grant(02BK-029)National Natural Science Foundation of China Under Grant(60105002)
文摘This paper proposed a method to automatically generate the trimap for digital matting. Camera parameters of aperture and shutter speed are used to control its exposure, and accordingly to take pictures of stationary foreground with blurred background. Our method was inspired by color difference matting, both of which require a pre-record background image. In our method, only one image was required. Upon this input image, the process of blurring-deblurring, subtraction, thresholding and dilation were applied to finally generate the trimap. No user＇ s direct interface with the image was needed, and the user only needed to adjust the threshold or width of dilation for some input images. It reduces users＇ conservative interaction, and results are reliable for most of the pictures.
文摘In this paper,we aim to propose a novel and effective iris segmentation method that is robust to uneven light intensity and different kinds of noises such as occlusion by light spots,eyelashes,eyelids,specta-cle-frame,etc.Unlike previous methods,the proposed method makes full use of gray intensities of the iris image.Inspired by the matting algorithm,a premier assumption is made that the foreground and background images of the iris image are both locally smooth.According to the RST algorithm,trimaps are built to provide priori in-formation.Under the assumption and priori,the optimal alpha matte can be obtained by least square loss function.A series of effective post processing methods are applied to the alpha image to obtain a more precise iris seg-mentation.The experiment on CASIA-iris-thousand database shows that the proposed method achieves a much better performance than conventional methods.Our experimental results achieve 20.5%and 26.4%,more than the well-known integro-differential operator and edge detection combined with Hough transform on iris seg-mentation rate respectively.The stability and validity of the proposed method is further demonstrated through the complementary experiments on the challenging iris images.
文摘RC算法引入区域级别的对比度,对颜色模型进行重新量化,能大幅提高处理速度、突出显著目标,然而其基于图的分割算法易出现分割区域不能较好地贴合物体边缘的问题。引入优化的SLIC算法代替基于图的分割算法,对RC算法进行改进,并实现一个基于图像显著性识别的自动抠图系统,克服传统抠图系统必须人工标记的缺点。实验结果表明,相比IT、MZ、GB、RC等经典算法,改进的RC算法抠取的显著目标更精确,其查准率、查全率、 F 值分别为0.82、0.85和0.83,系统能自动抠取显著目标并提供图片合成应用。
