Exploring features in a Bayesian framework for material recognition

Ce Liu; Lavanya Sharan; Edward H. Adelson; Ruth Rosenholtz

doi:10.1109/cvpr.2010.5540207

Abstract

We are interested in identifying the material category, e.g. glass, metal, fabric, plastic or wood, from a single image of a surface. Unlike other visual recognition tasks in computer vision, it is difficult to find good, reliable features that can tell material categories apart. Our strategy is to use a rich set of low and mid-level features that capture various aspects of material appearance. We propose an augmented Latent Dirichlet Allocation (aLDA) model to combine these features under a Bayesian generative framework and learn an optimal combination of features. Experimental results show that our system performs material recognition reasonably well on a challenging material database, outperforming state-of-the-art material/texture recognition systems.

Keywords

Computer scienceLatent Dirichlet allocationArtificial intelligenceBayesian probabilitySet (abstract data type)Generative grammarPattern recognition (psychology)Feature (linguistics)Dirichlet distributionMachine learningComputer visionTopic modelMathematics

Affiliated Institutions

Related Publications

Invariant Scattering Convolution Networks

Joan Bruna , Stéphane Mallat

A wavelet scattering network computes a translation invariant image representation which is stable to deformations and preserves high-frequency information for classification. I...

2013 IEEE Transactions on Pattern Analysis... 1576 citations

Region-based image querying

Chad Carson , Serge Belongie , Hayit Greenspan +1 more

Retrieving images from large and varied collections using image content as a key is a challenging and important problem. In this paper, we present a new image representation whi...

1997 1997 Proceedings IEEE Workshop on Con... 263 citations

Local Features and Kernels for Classification of Texture and Object Categories: An In-Depth Study

Jianguo Zhang , Marcin Marszałek , Svetlana Lazebnik +1 more

Recently, methods based on local image features have shown promise for texture and object recognition tasks. This paper presents a large-scale evaluation of an approach that rep...

2005 HAL (Le Centre pour la Communication ... 106 citations

Combining Markov Random Fields and Convolutional Neural Networks for Image Synthesis

Chuan Li , Michael Wand

This paper studies a combination of generative Markov random field (MRF) models and discriminatively trained deep convolutional neural networks (dCNNs) for synthesizing 2D image...

2016 695 citations

Feature selection: evaluation, application, and small sample performance

Anil K. Jain , Douglas E. Zongker

A large number of algorithms have been proposed for feature subset selection. Our experimental results show that the sequential forward floating selection algorithm, proposed by...

1997 IEEE Transactions on Pattern Analysis... 2147 citations

Publication Info

Year: 2010
Type: article
Pages: 239-246
Citations: 251
Access: Closed

External Links

View on DOI.org

Social Impact

Altmetric

Exploring features in a Bayesian framework for material recognition

PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

251

OpenAlex

Cite This

APA Style

                            
                                    Ce Liu, 
                                
                                    Lavanya Sharan, 
                                
                                    Edward H. Adelson
                                
                                et al.
                            
                            (2010). 
                            Exploring features in a Bayesian framework for material recognition. 
                            
                            , 239-246.
                            https://doi.org/10.1109/cvpr.2010.5540207

Identifiers

DOI: 10.1109/cvpr.2010.5540207