![Open Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltextgreen.png)
![Restricted Access](https://i-scholar.in/lib/pkp/templates/images/icons/fulltextred.png)
Scene Classification Using GLCM, Gabor Filter and Invariant Moments Method Based on PNN and SVM Classification
Classification of images into semantic categories is a challenging and important problem nowadays. In this paper, images of real natural scenes and manmade structures of same depth are taken. Roughness increases in case of man-made structures whereas natural scene images become smooth, thus reducing the local roughness of the picture. In this paper, we tested various techniques for features extraction: (GLCM) & Gabor filter. The extracted features are trained and tested with (i) the multilayer perceptron neural network model with Probabilistic Invariant Moments, Gray Level Co-occurrence Matrix Neural Network (PNN) and (ii) Support Vector Machines (SVM) using radial basis kernel function with p=5. This complete work is carried out using real world data set.
Keywords
Gray Level Co-Occurrence Matrix, Gabor Filter, Invariant Moments, Scene Classification, Probabilistic Neural Network, Support Vector Machine.
User
Font Size
Information
![](https://i-scholar.in/public/site/images/abstractview.png)
Abstract Views: 181
![](https://i-scholar.in/public/site/images/pdfview.png)
PDF Views: 0