gcv9htd / xvis

Toolbox for computer vision in X-ray testing

Xvis

Toolbox for Computer vision for X-ray testing

Xvis is the Matlab Toolbox of the book Computer Vision for X-ray Testing by Domingo Mery. In this book we use many commands of Xvis, i.e. a Matlab Toolbox that we developed for X-ray testing with computer vision. Xvis Tolbox contains approximately 150 functions for image processing, feature extraction, feature transformation, feature analysis, feature selection, data selection and generation, classification, clustering, performance evaluation, multiple-view analysis, image sequence processing and tracking with geometrical constraints.

Commands of Xvis starts with letter 'X'. For example Ximmedian corresponds to the implemented function of Xvis for median filtering. Each function of Xvis has a 'help' with one or more examples.

In addition, Xvis Toolbox includes a general framework that designs a computer vision system automatically in few lines code, or using two powerful graphic user interfaces one for feature extraction and for feature and classifier selection. It finds the features and the classifiers for a given visual task avoiding the classical trial and error framework commonly used by human designers.

Xvis can work perfectly with GDXray, a collection of more than 19.400 X-ray images for the development, testing and evaluation of image analysis and computer vision algorithms. GDXray includes five groups of images: Castings, Welds, Baggage, Nature and Settings.

References:

• Mery, D. (2015): Computer Vision for X-ray Testing, Springer.

• Mery, D.; Riffo, V.; Zscherpel, U.; Mondragón, G.; Lillo, I.; Zuccar, I.; Lobel, H.; Carrasco, M. (2015): GDXray: The database of X-ray images for nondestructive testing. Journal of Nondestructive Evaluation, 34.4:1-12.

• GDXray database.

Copyright 2015-2019 by Group of Machine Intelligence (GRIMA), Department of Computer Science, Universidad Catolica - Chile

All rights reserved. This work is licensed under a Creative Commons Attribution-Noncommercial-Share Alike 2.5 Generic License.

Permission to use, copy, or modify these programs and their documentation for educational and research purposes only and without fee is hereby granted, provided that this copyright notice appears on all copies and supporting documentation. For any other uses of this software, in original or modified form, including but not limited to distribution in whole or in part, specific prior permission must be obtained from Pontificia Universidad Catolica de Chile. These programs shall not be used, rewritten, or adapted as the basis of a commercial software or hardware product without first obtaining appropriate licenses from the Pontificia Universidad Catolica de Chile. Pontificia Universidad Catolica de Chile makes no representations about the suitability of this software for any purpose. It is provided "as is" without express or implied warranty.

NOTES:

Certain Xvis functions use commands of the followings toolboxes: VLFeat, Image Processing, Bioinformatics, and Neural Netowrks. It is necessary to install this toolboxes if you want to use these Balu functions.

Certain neural network functions were implemented based on NetLab Toolbox: (c) 1996-2001, Ian T. Nabney, All rights reserved. Nabney, I.T. (2003): Netlab: Algorithms for Pattern Recognition, Advances in Pattern Recognition, Springer.

Certain Local Binary Patterns functions were implemented based on code written by Heikkila & Ahonen (see http://www.cse.oulu.fi/MVG/Research/LBP) all rights reserved.

Partial Least Squares Regression was implemented based on code developed by Gelady (see http://www.cdpcenter.org/files/plsr ).