Modification of indistinguishable colors based on personal characteristic model for people with color defective vision

与色觉正常的人相比，有色觉缺陷（CVD）的人在区分某些颜色组合方面有困难。为了解决这个问题，我们修改了原始图像的饱和度成分，以保留心血管疾病患者感知时的视觉细节。该方法可以自动构造一个变换，既保留CVD患者的细节，又保持正常观察者的自然性。此外，采用中值切割算法，在颜色量化的基础上进行聚类，实现了快速的重着色处理。另一方面，为了对视觉障碍类型进行分类，我们在android操作系统的移动设备上实施了farnsworth-munsell D-15测试。最后，为了证明所提出系统的有效性，我们进行了评估实验。此外，针对颜色难以区分的图像，提出了一种基于最大距离算法的图像自动分割方法。

Compared to people with normal color vision, people with color vision deficiency(CVD) have difficulty in distinguishing between certain combinations of colors. To address this problem, we modify saturation components of the original image to preserve visual detail when perceived by people with CVD. The proposed method can automatically construct a transformation to maintain details for people with CVD while preserving naturalness for normal viewers. In addition, high-speed processing of re-coloring is achieved by clustering based on color quantization using the median cut algorithm. On the other hand, to classify type of vision disability, we implemented the farnsworth-munsell D-15 test to a mobile device with android OS. Finally, in order to show the effectiveness of the proposed system, we performed evaluational experiments. In addition, we proposed automatic image segmentation by using the maximum distance algorithm for an image which has indistinguishable colors.