Sharan Lavanya, Liu Ce, Rosenholtz Ruth, Adelson Edward H
Disney Research, Pittsburgh, 4720 Forbes Avenue, Lower Level, Suite 110, Pittsburgh, PA 15213,
Int J Comput Vis. 2013 Jul 1;103(3):348-371. doi: 10.1007/s11263-013-0609-0.
Our world consists not only of objects and scenes but also of materials of various kinds. Being able to recognize the materials that surround us (e.g., plastic, glass, concrete) is important for humans as well as for computer vision systems. Unfortunately, materials have received little attention in the visual recognition literature, and very few computer vision systems have been designed specifically to recognize materials. In this paper, we present a system for recognizing material categories from single images. We propose a set of low and mid-level image features that are based on studies of human material recognition, and we combine these features using an SVM classifier. Our system outperforms a state-of-the-art system [Varma and Zisserman, 2009] on a challenging database of real-world material categories [Sharan et al., 2009]. When the performance of our system is compared directly to that of human observers, humans outperform our system quite easily. However, when we account for the local nature of our image features and the surface properties they measure (e.g., color, texture, local shape), our system rivals human performance. We suggest that future progress in material recognition will come from: (1) a deeper understanding of the role of non-local surface properties (e.g., extended highlights, object identity); and (2) efforts to model such non-local surface properties in images.
我们的世界不仅由物体和场景构成，还包含各种各样的材料。能够识别我们周围的材料（例如塑料、玻璃、混凝土）对人类以及计算机视觉系统都很重要。不幸的是，材料在视觉识别文献中很少受到关注，而且专门设计用于识别材料的计算机视觉系统也非常少。在本文中，我们提出了一种从单张图像中识别材料类别的系统。我们基于对人类材料识别的研究提出了一组低层次和中层的图像特征，并使用支持向量机分类器对这些特征进行组合。在一个具有挑战性的真实世界材料类别数据库[Sharan等人，2009]上，我们的系统优于一个先进的系统[Varma和Zisserman，2009]。当将我们系统的性能与人类观察者的性能直接比较时，人类很容易超越我们的系统。然而，当我们考虑到我们图像特征的局部性质以及它们所测量的表面属性（例如颜色、纹理、局部形状）时，我们的系统与人类表现相当。我们认为，材料识别未来的进展将来自于：（1）对非局部表面属性（例如扩展高光、物体身份）作用的更深入理解；以及（2）在图像中对这种非局部表面属性进行建模的努力。
