Hi Hardik,
I recommend you to use Libsvm or Liblinear libraries, which have been commonly used in SVM-based classification over the last years. You can download them in the following links:
http://www.csie.ntu.edu.tw/~cjlin/libsvm/
http://www.csie.ntu.edu.tw/~cjlin/liblinear/
We have applied these libraries for a vehicle logo recognition problem using HOG features with remarkable results (see the attached publication), so I recommend you to use them.
Good luck with your research!
Conference Paper Vehicle logo recognition in traffic images using HOG features and SVM
LIBSVM is highly recommended...The documentation describes the parameter tuning very well, leading to improved results. We have used it for real time gesture recognition
The Statistics Toolbox has an SVM implementation. The Computer Vision System Toolbox has HOG.
Here's an example of classifying digits using HOG-SVM:
http://www.mathworks.com/help/vision/examples/digit-classification-using-hog-features.html
Hi Hardik, as others, I would recommend you libsvm library.
After this, you ask how to implement it. Well, it depends on which kind of use you want to get from your classifier. Which kind of application you aim to develop with your images? Object recognition,classification,segmentation?....
In Matlab you can use the functions : svmtrain and svmclassify
for more information you can see the book on the link
Cristianini, N., and Shawe-Taylor, J. (2000). An Introduction to Support Vector Machines and Other Kernel-based Learning Methods, First Edition (Cambridge: Cambridge University Press). http://www.support-vector.net/
- Badges
- Science topic