Department of Applied Informatics, Hosei University, Tokyo, Japan.
Comput Med Imaging Graph. 2011 Mar;35(2):89-98. doi: 10.1016/j.compmedimag.2010.08.003. Epub 2010 Oct 8.
Accurate color information in dermoscopy images is very important for melanoma diagnosis since inappropriate white balance or brightness in the images adversely affects the diagnostic performance. In this paper, we present an automated color calibration method for dermoscopy images of skin lesions. On a set of 319 dermoscopy images, we develop color calibration filters based on the HSV color system. We determined that the color characteristics of the peripheral part of the tumors have significant influence on the color calibration filters and confirmed that the presented filters achieved satisfactory calibration performance as evaluated by cross-validation. We also confirmed that our method successfully modifies the color distribution of a given image to make it closer to the color distribution of the training image set.
准确的颜色信息在皮肤镜图像中对于黑色素瘤的诊断非常重要，因为图像中不适当的白平衡或亮度会对诊断性能产生不利影响。在本文中，我们提出了一种用于皮肤病变皮肤镜图像的自动颜色校准方法。在一组 319 张皮肤镜图像上，我们基于 HSV 颜色系统开发了颜色校准滤波器。我们确定肿瘤周边部分的颜色特征对颜色校准滤波器有重大影响，并通过交叉验证确认所提出的滤波器实现了令人满意的校准性能。我们还确认我们的方法成功地修改了给定图像的颜色分布，使其更接近训练图像集的颜色分布。
