This shows you the differences between two versions of the page.

publications:materials-ijcv2012 [2013/02/14 10:23]
elmer created
publications:materials-ijcv2012 [2014/09/11 11:50] (current)
Line 4: Line 4:
===== Abstract ===== ===== Abstract =====
-Vision is an active process: We repeatedly move our eyes to seek out objects of interest and explore our environment. Visual search experiments capture aspects of this process, by having subjects look for a target within a background of distractors. Search speed often correlates with target–distractor discriminability; search is faster when the target and distractors look quite different. However, there are notable exceptions. A given discriminability can yield efficient searches (where the target seems to “pop-out”) as well as inefficient ones (where additional distractors make search significantly slower and more difficult). Search is often more difficult when finding the target requires distinguishing a particular configuration or conjunction of features. Search asymmetries abound. These puzzling results have fueled three decades of theoretical and experimental studies. We argue that the key issue in search is the processing of image patches in the periphery, where visual representation is characterized by summary statistics computed over a sizable pooling region. By quantifying these statistics, we predict a set of classic search results, as well as peripheral discriminability of crowded patches such as those found in search displays.+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, TPAMI 31(11):2032–2047, 2009) on a challenging database of real-world material categories (Sharan et al., J Vis 9(8):784–784a, 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. 
 +===== Project page ===== 
 +[[http://people.csail.mit.edu/lavanya/matlrecog.html | Recognizing Materials using Perceptually Inspired Features ]] 
===== Information ===== ===== Information =====
Line 11: Line 16:
title        : Recognizing Materials Using Perceptually Inspired Features title        : Recognizing Materials Using Perceptually Inspired Features
authors      : Sharan, L., Liu. C., Rosenholtz, R., Adelson. E. H. authors      : Sharan, L., Liu. C., Rosenholtz, R., Adelson. E. H.
-citation     : International Journal of Computer Vision, 2012+citation     : International Journal of Computer Vision
shortcite    : IJCV shortcite    : IJCV
-year         : 2012+year         : 2013
created_dt   : 2012-09-14 created_dt   : 2012-09-14
summary_page : publications:materials-ijcv2012 summary_page : publications:materials-ijcv2012
-keyword_tags : adelson +keyword_tags : adelson, rosenholtz, sharan, liu, materialperception 
-www_url      : +www_url      :  
-pdf_url      : http://persci.mit.edu/pub_pdfs/materials-ijcv2012+pdf_url      : http://link.springer.com/content/pdf/10.1007%2Fs11263-013-0609-0
type         : publication type         : publication
---- ----
publications/materials-ijcv2012.1360855432.txt.gz · Last modified: 2013/02/14 10:23 by elmer