Zhou Shuwang, Shu Minglei, Di Chong
College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, China.
Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan 250014, China.
Entropy (Basel). 2024 Dec 22;26(12):1123. doi: 10.3390/e26121123.
Image segmentation is a crucial task in artificial intelligence fields such as computer vision and medical imaging. While convolutional neural networks (CNNs) have achieved notable success by learning representative features from large datasets, they often lack geometric priors and global object information, limiting their accuracy in complex scenarios. Variational methods like active contours provide geometric priors and theoretical interpretability but require manual initialization and are sensitive to hyper-parameters. To overcome these challenges, we propose a novel segmentation approach, named PolarVoting, which combines the minimal path encoding rich geometric features and CNNs which can provide efficient initialization. The introduced model involves two main steps: firstly, we leverage the PolarMask model to extract multiple source points for initialization, and secondly, we construct a voting score map which implicitly contains the segmentation mask via a modified circular geometric voting (CGV) scheme. This map embeds global geometric information for finding accurate segmentation. By integrating neural network representation with geometric priors, the PolarVoting model enhances segmentation accuracy and robustness. Extensive experiments on various datasets demonstrate that the proposed PolarVoting method outperforms both PolarMask and traditional single-source CGV models. It excels in challenging imaging scenarios characterized by intensity inhomogeneity, noise, and complex backgrounds, accurately delineating object boundaries and advancing the state of image segmentation.
图像分割是计算机视觉和医学成像等人工智能领域中的一项关键任务。虽然卷积神经网络（CNN）通过从大型数据集中学习代表性特征取得了显著成功，但它们往往缺乏几何先验和全局对象信息，限制了其在复杂场景中的准确性。像活动轮廓这样的变分方法提供了几何先验和理论可解释性，但需要手动初始化且对超参数敏感。为了克服这些挑战，我们提出了一种名为PolarVoting的新型分割方法，它将编码丰富几何特征的最小路径与能够提供有效初始化的CNN相结合。引入的模型包括两个主要步骤：首先，我们利用PolarMask模型提取多个源点进行初始化；其次，我们通过改进的圆形几何投票（CGV）方案构建一个隐式包含分割掩码的投票得分图。该图嵌入全局几何信息以找到准确的分割。通过将神经网络表示与几何先验相结合，PolarVoting模型提高了分割的准确性和鲁棒性。在各种数据集上进行的大量实验表明，所提出的PolarVoting方法优于PolarMask和传统的单源CGV模型。它在以强度不均匀、噪声和复杂背景为特征的具有挑战性的成像场景中表现出色，能够准确描绘对象边界并推动图像分割技术的发展。
