Image texture classification using exponential curve fitting of wavelet domain singular values

2006 ◽  
Author(s):  
S. Ramakrishnan ◽  
S. Selvan
Keyword(s):  
Curve Fitting ◽  
Texture Classification ◽  
Singular Values ◽  
Image Texture ◽  
Wavelet Domain ◽  
Exponential Curve

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.

Multigrid computation for curve fitting in the wavelet domain

1998 ◽  
Vol 34 (5) ◽  
pp. 433 ◽  
Author(s):  
Wen-Jen Ho ◽  
Wen-Thong Chang
Keyword(s):  
Curve Fitting ◽  
Wavelet Domain ◽  
Fitting In

Texture Segmentation of Jacquard Fabric Using Wavelet-Domain Markov Model

2012 ◽  
Vol 468-471 ◽  
pp. 2720-2723
Author(s):  
Yang Zhang ◽  
You Cheng Tong ◽  
Jun Zhou Yao
Keyword(s):  
Markov Model ◽  
Low Frequency ◽  
Gaussian Mixture ◽  
Texture Segmentation ◽  
Image Texture ◽  
Distribution Model ◽  
Wavelet Domain ◽  
Markov Random ◽  
Multi Level ◽  
Fabric Design

To improve the accuracy and efficiency of fabric design CAD, a wavelet-domain Markov model to image texture segmentation from a natural framework for intergrating both local and global information of jacquard fabric image behavior, together with contextual information.Firstly the Daubechies wavelet and tree-structure is selected, then the approach decomposes the low frequency part of the jacquard fabric image. Secondly within the theoretical framework of Markov random field, we construct the grey field distribution model and label field prior model with finite Gaussian mixture algorithm and multi-level logistic algorithm respectively. The experiments for almost 30 warp knitting jacquard fabric images show that this approach is a feasible way for jacquard fabric, and it supplies a theoretical platform for subsequent research.

A new algorithm for remotely sensed image texture classification and segmentation

2004 ◽  
Vol 25 (19) ◽  
pp. 4043-4050 ◽  
Author(s):  
Yao-Wei Wang ◽  
Yan-Fei Wang ◽  
Yong Xue ◽  
Wen Gao
Keyword(s):  
Texture Classification ◽  
Remotely Sensed ◽  
Image Texture ◽  
Remotely Sensed Image
Sign in / Sign up

Export Citation Format

Share Document