KeyRes Co-Occurrence Features v.1.32b
 

Step 1. Original CT image                 Step 2. Features Extraction               Step 3. 3D Visualization
 

KeyRes Co-Occurrence Features is an advanced features extraction and image processing software for scientific and industrial imaging applications based on Haralick feature functions.

Haralick feature functions are well-suited for classifying images characterized by varying textures.

This software supports grayscale images stored in RTOG, TIFF, GIF, JPEG, BMP or many other image file formats. Color images are converted into grayscale images in order to extract meaningful features. Algorithms are fast and optimized using sparse matrix notation and compilation in C/C++ language.

You can choose a pixel-based or a block-based scan, select a sliding window size, a gray level value, and start processing. It is possible to select the neighbouring pixels distance and eventually normalize the result within a 0-255 range.

After processing, perform a 3D visualization, define a correlation map and plot the features histogram. Then, export the feature values - or feature images  as well - and import into another image processing tool.

KeyRes Co-Occurrence Features is currently being used by leading research organizations and academic laboratories around the world.

* this software works under Matlab 7 or under (free) Matlab Component RunTime (MCR) - see instructions to download the MCR for Windows NT/2000/XP.

(MATLAB and Matlab Component RunTime (MCR) are trademarks of The Mathworks, Inc. - KeyRes Co-occurrence Software is provided according to the Matlab Application Deployment Program).
 
 

Reference:

KeyresCF Handbook 1: general information about use of the software.

KeyresCF Handbook 2: detailed information about library and C functions.

KeyresCF Handbook 3: basic concepts on co-occurrence features.
 

Contact:

E-mail: info@keyres-technologies.com
 
 
 

Reference:

• A. Zizzari, et al., Detection of Tumor in Digital Images of the Brain. Proceedings of the IASTED International Conference on Signal Processing, Pattern Recognition and Applications SPPRA 2001, Rhodes, Greece, July 3-6, 2001, pp. 132-137.

• R.M. Haralick, K. Shanmugam and I. Dinstein, “Textural Features for Image Classification”, IEEE Transactions on Systems, Man and Cybernetics, vol. SMC-3, no. 6, pp. 610-621, 1973.

A. Zizzari, Methods on Tumor Recognition and Planning Target Prediction for the Radiotherapy of Cancer. Shaker-Verlag, Aachen - Germany, 2004.  (ISBN 3-8322-2562-5)