Recognizing Materials using Perceptually Inspired Features.
Recognizing Materials using Perceptually Inspired Features.
复制标题
DOI：
10.1007/s11263-013-0609-0
复制
发表时间：
2013-07-01
影响因子：
19.5
通讯作者：
Adelson, Edward H.
中科院分区：
文献类型：
--
作者：
Sharan, Lavanya;Liu, Ce;Rosenholtz, Ruth;Adelson, Edward H.
我们的世界不仅是由物体和景物组成的，而且是由各种各样的材料组成的。能够识别我们周围的材料（例如，塑料、玻璃、混凝土）对于人类以及对于计算机视觉系统都是重要的。不幸的是，材料在视觉识别文献中很少受到关注，并且很少有计算机视觉系统专门设计用于识别材料。在本文中，我们提出了一个系统识别材料类别从单一的图像。我们提出了一套低，中级图像特征，是基于人体材料识别的研究，我们联合收割机使用SVM分类器结合这些功能。我们的系统在现实世界材料类别的具有挑战性的数据库上优于最先进的系统。当我们的系统的性能直接与人类观察者的性能进行比较时，人类很容易超过我们的系统。然而，当我们考虑到我们的图像特征的局部性质和它们测量的表面属性（例如，颜色、纹理、局部形状），我们的系统可以与人类的表现相媲美。我们认为，材料识别的未来进展将来自：（1）对非局部表面性质（例如，扩展的高光、对象标识）;以及（2）对图像中的这种非局部表面特性进行建模的努力。
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 on a challenging database of real-world material categories. 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.
登录
查看更多内容
影响因子：
64.8
作者：
Bloj, MG;Kersten, D;Hurlbert, AC
通讯作者：
Hurlbert, AC
影响因子：
1.8
作者：
Fleming, RW;Torralba, A;Adelson, EH
通讯作者：
Adelson, EH
影响因子：
6.2
作者：
Dana, KJ;Van Ginneken, B;Koenderink, JJ
通讯作者：
Koenderink, JJ
影响因子：
4.8
作者：
Burges, CJC
通讯作者：
Burges, CJC
影响因子：
6
作者：
Blei, DM;Ng, AY;Jordan, MI
通讯作者：
Jordan, MI