Texture Classification Using 2D LSTM Networks

2014 ◽  
Author(s):  
Wonmin Byeon ◽  
Marcus Liwicki ◽  
Thomas M. Breuel
Keyword(s):  
Texture Classification

CNN performance dependence on linear image processing

2020 ◽  
Vol 2020 (10) ◽  
pp. 310-1-310-7
Author(s):  
Khalid Omer ◽  
Luca Caucci ◽  
Meredith Kupinski
Keyword(s):  
Image Processing ◽  
Texture Classification ◽  
Full Rank ◽  
Detection Performance ◽  
Ideal Observer ◽  
Training Data ◽  
Image Texture ◽  
Training Images ◽  
Analytic Expressions ◽  
Linear Compression

This work reports on convolutional neural network (CNN) performance on an image texture classification task as a function of linear image processing and number of training images. Detection performance of single and multi-layer CNNs (sCNN/mCNN) are compared to optimal observers. Performance is quantified by the area under the receiver operating characteristic (ROC) curve, also known as the AUC. For perfect detection AUC = 1.0 and AUC = 0.5 for guessing. The Ideal Observer (IO) maximizes AUC but is prohibitive in practice because it depends on high-dimensional image likelihoods. The IO performance is invariant to any fullrank, invertible linear image processing. This work demonstrates the existence of full-rank, invertible linear transforms that can degrade both sCNN and mCNN even in the limit of large quantities of training data. A subsequent invertible linear transform changes the images’ correlation structure again and can improve this AUC. Stationary textures sampled from zero mean and unequal covariance Gaussian distributions allow closed-form analytic expressions for the IO and optimal linear compression. Linear compression is a mitigation technique for high-dimension low sample size (HDLSS) applications. By definition, compression strictly decreases or maintains IO detection performance. For small quantities of training data, linear image compression prior to the sCNN architecture can increase AUC from 0.56 to 0.93. Results indicate an optimal compression ratio for CNN based on task difficulty, compression method, and number of training images.

Gradient Texture Classification Based On Age Prediction of Face Images

2014 ◽  
Vol 1 (3) ◽  
pp. 23-31
Author(s):  
Basava Raju ◽  
◽  
K. Y. Rama Devi ◽  
P. V. Kumar ◽  
◽  
...  
Keyword(s):  
Texture Classification ◽  
Face Images ◽  
Age Prediction

Trabecular bone texture classification using wavelet leaders

2016 ◽  
Author(s):  
Zilong Zou ◽  
Jie Yang ◽  
Vasileios Megalooikonomou ◽  
Rachid Jennane ◽  
Erkang Cheng ◽  
...  
Keyword(s):  
Trabecular Bone ◽  
Texture Classification ◽  
Wavelet Leaders

scholarly journals T1K+: A Database for Benchmarking Color Texture Classification and Retrieval Methods

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 1010
Author(s):  
Claudio Cusano ◽  
Paolo Napoletano ◽  
Raimondo Schettini
Keyword(s):  
Design Of Experiments ◽  
Texture Classification ◽  
Construction Materials ◽  
Heterogeneous Database ◽  
High Quality ◽  
Visual Descriptors ◽  
Classification Tasks ◽  
Color Texture

In this paper we present T1K+, a very large, heterogeneous database of high-quality texture images acquired under variable conditions. T1K+ contains 1129 classes of textures ranging from natural subjects to food, textile samples, construction materials, etc. T1K+ allows the design of experiments especially aimed at understanding the specific issues related to texture classification and retrieval. To help the exploration of the database, all the 1129 classes are hierarchically organized in 5 thematic categories and 266 sub-categories. To complete our study, we present an evaluation of hand-crafted and learned visual descriptors in supervised texture classification tasks.

Sign in / Sign up

Export Citation Format

Share Document