Liu Feihong, Zhang Xiao, Wang Hongyu, Feng Jun
School of Information Science and Technology, Northwest University, Xi'an 710027, China.
School of Computer Science and Technology, Xi'an University of Posts and Telecommunications, Xi'an 710121, China.
Entropy (Basel). 2019 Dec 23;22(1):20. doi: 10.3390/e22010020.
Superpixel clustering is one of the most popular computer vision techniques that aggregates coherent pixels into perceptually meaningful groups, taking inspiration from Gestalt grouping rules. However, due to brain complexity, the underlying mechanisms of such perceptual rules are unclear. Thus, conventional superpixel methods do not completely follow them and merely generate a flat image partition rather than hierarchical ones like a human does. In addition, those methods need to initialize the total number of superpixels, which may not suit diverse images. In this paper, we first propose context-aware superpixel (CASP) that follows both Gestalt grouping rules and the top-down hierarchical principle. Thus, CASP enables to adapt the total number of superpixels to specific images automatically. Next, we propose bilateral entropy, with two aspects conditional intensity entropy and spatial occupation entropy, to evaluate the encoding efficiency of image coherence. Extensive experiments demonstrate CASP achieves better superpixel segmentation performance and less entropy than baseline methods. More than that, using Pearson's correlation coefficient, a collection of data with a total of 120 samples demonstrates a strong correlation between local image coherence and superpixel segmentation performance. Our results inversely support the reliability of above-mentioned perceptual rules, and eventually, we suggest designing novel entropy criteria to test the encoding efficiency of more complex patterns.
超像素聚类是最流行的计算机视觉技术之一，它从格式塔分组规则中汲取灵感，将连贯的像素聚合为具有感知意义的组。然而，由于大脑的复杂性，这种感知规则的潜在机制尚不清楚。因此，传统的超像素方法并未完全遵循这些规则，只是生成了一个平面的图像划分，而不是像人类那样生成层次化的划分。此外，这些方法需要初始化超像素的总数，这可能不适用于各种图像。在本文中，我们首先提出了上下文感知超像素（CASP），它既遵循格式塔分组规则，又遵循自上而下的层次原则。因此，CASP能够自动使超像素的总数适应特定图像。接下来，我们提出了双边熵，包括条件强度熵和空间占用熵两个方面，以评估图像连贯性的编码效率。大量实验表明，与基线方法相比，CASP实现了更好的超像素分割性能和更低的熵。不仅如此，使用皮尔逊相关系数，一组总共120个样本的数据表明局部图像连贯性与超像素分割性能之间存在很强的相关性。我们的结果反过来支持了上述感知规则的可靠性，最终，我们建议设计新的熵准则来测试更复杂模式的编码效率。
