论文标题
频率和空间域的显着性皮肤病变细分
Frequency and Spatial domain based Saliency for Pigmented Skin Lesion Segmentation
论文作者
论文摘要
由于人工制品的存在，病变和边界之间的低对比度，颜色变种，模糊的皮肤病变边界和皮肤镜图像中的异质背景，皮肤病变分割可能是一项具有挑战性的任务。在本文中，我们提出了一种在频率和空间结构域中得出的简单但有效的基于显着性的方法，以检测有色皮肤病变。两种颜色模型用于构建这些地图。我们建议每个颜色模型通过颜色特征在空间域中设计图。频域中的地图是由聚合图像生成的。我们采用单独的融合方案将其各自域中的显着特征结合在一起。最后，设计了两阶段显着性集成方案，以使用PixelWise乘法结合这些图。在PH2和ISIC 2016数据集上评估了该方法的性能。实验的结果表明，与最新方法相比，提出的方案会产生更好的分割结果。
Skin lesion segmentation can be rather a challenging task owing to the presence of artifacts, low contrast between lesion and boundary, color variegation, fuzzy skin lesion borders and heterogeneous background in dermoscopy images. In this paper, we propose a simple yet effective saliency-based approach derived in the frequency and spatial domain to detect pigmented skin lesion. Two color models are utilized for the construction of these maps. We suggest a different metric for each color model to design map in the spatial domain via color features. The map in the frequency domain is generated from aggregated images. We adopt a separate fusion scheme to combine salient features in their respective domains. Finally, two-phase saliency integration scheme is devised to combine these maps using pixelwise multiplication. Performance of the proposed method is assessed on PH2 and ISIC 2016 datasets. The outcome of the experiments suggests that the proposed scheme generate better segmentation result as compared to state-of-the-art methods.
