Human skin segmentation is a crucial task in computer vision and biometric systems, yet it poses several challenges such as variability in skin color, pose, and illumination. This paper presents a robust data-driven skin segmentation method for a single image that addresses these challenges through the integration of contextual information and efficient network design. In addition to robustness and accuracy, the integration into real-time systems requires a careful balance between computational power, speed, and performance. The proposed method incorporates two attention modules, Body Attention and Skin Attention, that utilize contextual information to improve segmentation results. These modules draw attention to the desired areas, focusing on the body boundaries and skin pixels, respectively. Additionally, an efficient network architecture is employed in the encoder part to minimize computational power while retaining high performance. To handle the issue of noisy labels in skin datasets, the proposed method uses a weakly supervised training strategy, relying on the Skin Attention module. The results of this study demonstrate that the proposed method is comparable to, or outperforms, state-of-the-art methods on benchmark datasets.

翻译：人体皮肤分割是计算机视觉与生物特征识别系统中的关键任务，然而该任务面临肤色变化、姿态差异及光照条件等挑战。本文提出一种基于数据驱动的鲁棒性单幅图像皮肤分割方法，通过整合上下文信息与高效网络架构应对上述挑战。在保证鲁棒性与准确性的同时，为集成至实时系统，需在算力、速度与性能间实现精密平衡。该方法包含身体注意力与皮肤注意力两个注意力模块，利用上下文信息优化分割结果：前者聚焦人体轮廓区域，后者则关注皮肤像素。编码器部分采用高效网络架构，在维持高性能的同时最大限度降低计算开销。针对皮肤数据集中存在的标签噪声问题，本文基于皮肤注意力模块引入弱监督训练策略。实验结果表明，该方法在基准数据集上的表现可与当前最优方法比肩，甚至超越现有技术水平。