Exploring features in a Bayesian framework for material recognition
Ce Liu,Lavanya Sharan,Edward H. Adelson,Ruth Rosenholtz +3 more
- pp 239-246
TLDR
In this article, an augmented Latent Dirichlet Allocation (aLDA) model was proposed to combine low and mid-level features under a Bayesian generative framework and learn an optimal combination of features.Abstract:Â
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.read more
Citations
More filters
Journal ArticleDOI
Selective Search for Object Recognition
TL;DR: This paper introduces selective search which combines the strength of both an exhaustive search and segmentation, and shows that its selective search enables the use of the powerful Bag-of-Words model for recognition.
Book ChapterDOI
Unified Perceptual Parsing for Scene Understanding
TL;DR: A multi-task framework called UPerNet and a training strategy are developed to learn from heterogeneous image annotations and it is shown that it is able to effectively segment a wide range of concepts from images.
Proceedings ArticleDOI
Material recognition in the wild with the Materials in Context Database
TL;DR: The Materials in Context Database (MINC) as mentioned in this paper is a large-scale, open dataset of materials in the wild, and combine this dataset with deep learning to achieve material recognition and segmentation of images from the wild.
Posted Content
Material recognition in the wild with the Materials in Context Database
TL;DR: A new, large-scale, open dataset of materials in the wild, the Materials in Context Database (MINC), is introduced, and convolutional neural networks are trained for two tasks: classifying materials from patches, and simultaneous material recognition and segmentation in full images.
Journal ArticleDOI
Pairwise Rotation Invariant Co-Occurrence Local Binary Pattern
TL;DR: This work formally introduces a Pairwise Transform Invariance (PTI) principle, and proposes a novel Pairwise Rotation Invariant Co-occurrence Local Binary Pattern (PRICoLBP) feature, and extends it to incorporate multi-scale, multi-orientation, and multi-channel information.
References
More filters
Journal ArticleDOI
Distinctive Image Features from Scale-Invariant Keypoints
TL;DR: This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.
Proceedings ArticleDOI
Histograms of oriented gradients for human detection
Navneet Dalal,Bill Triggs +1 more
TL;DR: It is shown experimentally that grids of histograms of oriented gradient (HOG) descriptors significantly outperform existing feature sets for human detection, and the influence of each stage of the computation on performance is studied.
Journal ArticleDOI
Latent dirichlet allocation
TL;DR: This work proposes a generative model for text and other collections of discrete data that generalizes or improves on several previous models including naive Bayes/unigram, mixture of unigrams, and Hofmann's aspect model.
Journal ArticleDOI
A Computational Approach to Edge Detection
TL;DR: There is a natural uncertainty principle between detection and localization performance, which are the two main goals, and with this principle a single operator shape is derived which is optimal at any scale.
Journal ArticleDOI
Shape matching and object recognition using shape contexts
TL;DR: This paper presents work on computing shape models that are computationally fast and invariant basic transformations like translation, scaling and rotation, and proposes shape detection using a feature called shape context, which is descriptive of the shape of the object.