Ganesh S. Raghtate
Ganesh S. Raghtate has a total of 1 co-authors. Here are the top co-authors by number of shared publications:
- Suresh S. Salankar
G H Raisoni College of Engineering, Nagpur, India
4 shared publications
Latest Publications
- 18 August 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1241-1246
Automatic Brain MRI Classification Using Modified Ant Colony System and Neural Network Classifier
In this paper, a hybrid intelligent machine learning technique for automatic classification of brain magnetic resonance images is presented. The proposed multistage technique involves the following computational methods, Otsu's method for skull removal, Fuzzy Inference System for image enhancement, Modified Fuzzy C Means with the Optimized Ant Colony System for image segmentation, Second Order Statistical Analysis and Wavelet Transform Method for feature extraction and the Feed Forward back-propagation neural network to classify inputs into normal or abnormal. The experiments were carried out on 200 images consisting of 100 normal and 100 abnormal (malignant and benign tumors) from a real human brain MRI data set. Experimental results indicate that the proposed algorithm achieves high classification rate and outperforms recently introduced methods while it needs a least number of features for classification.
- 18 August 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1241-1246
Automatic Brain MRI Classification Using Modified Ant Colony System and Neural Network Classifier
In this paper, a hybrid intelligent machine learning technique for automatic classification of brain magnetic resonance images is presented. The proposed multistage technique involves the following computational methods, Otsu's method for skull removal, Fuzzy Inference System for image enhancement, Modified Fuzzy C Means with the Optimized Ant Colony System for image segmentation, Second Order Statistical Analysis and Wavelet Transform Method for feature extraction and the Feed Forward back-propagation neural network to classify inputs into normal or abnormal. The experiments were carried out on 200 images consisting of 100 normal and 100 abnormal (malignant and benign tumors) from a real human brain MRI data set. Experimental results indicate that the proposed algorithm achieves high classification rate and outperforms recently introduced methods while it needs a least number of features for classification.
- 18 August 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1283-1288
Modified Fuzzy C Means with Optimized Ant Colony Algorithm for Image Segmentation
Segmentation technique is used for analysis and diagnosis of tumor in MRI Brain image. The paper presents Modified Fuzzy C Means with Optimized Ant Colony Algorithm for segmentation of brain tumors in 3D magnetic resonance images. In this paper, the image segmentation is obtained by using Modified Fuzzy C Means with Optimized Ant Colony Algorithm using Min - Max Ant System. The proposed methodology is tested on 13 real patients MRI images. It is compared with Fuzzy C Means and Fuzzy C Means with Ant Colony Algorithm. The Fuzzy C Means algorithm is not efficient due to limitation in initialization. FCM with ACA has the disadvantage of requirement of increased processing time. The proposed methodology shows a PSNR improvement of 9.33 dB and 0.62 dB over FCM and FCM with ACA respectively. It has segmentation accuracy improvement of 24.55% and 0.22% over FCM and FCM with ACA respectively. It shows 55.72 sec reduction in processing time over FCM with ACA.
- 18 August 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1283-1288
Modified Fuzzy C Means with Optimized Ant Colony Algorithm for Image Segmentation
Segmentation technique is used for analysis and diagnosis of tumor in MRI Brain image. The paper presents Modified Fuzzy C Means with Optimized Ant Colony Algorithm for segmentation of brain tumors in 3D magnetic resonance images. In this paper, the image segmentation is obtained by using Modified Fuzzy C Means with Optimized Ant Colony Algorithm using Min - Max Ant System. The proposed methodology is tested on 13 real patients MRI images. It is compared with Fuzzy C Means and Fuzzy C Means with Ant Colony Algorithm. The Fuzzy C Means algorithm is not efficient due to limitation in initialization. FCM with ACA has the disadvantage of requirement of increased processing time. The proposed methodology shows a PSNR improvement of 9.33 dB and 0.62 dB over FCM and FCM with ACA respectively. It has segmentation accuracy improvement of 24.55% and 0.22% over FCM and FCM with ACA respectively. It shows 55.72 sec reduction in processing time over FCM with ACA.
- 18 August 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 312-317
Comparison of Classification Methods with Second Order Statistical Analysis and Wavelet Transform for Texture Image Classification
In computer vision system, texture refers to the characteristics of an object that appear on its surface. Texture classification is to classify textures in correct texture groups. The accuracy of texture image classification depends on quality of texture features and classification algorithm used. In this paper, Brodatz texture images are used as an experimental data. Features are extracted from texture images using Gray Level Co -- occurrence method (GLCM) and two-level, two-dimensional discrete wavelet transform (2D DWT). The extracted features are applied to the k-nearest neighbor (k - NN), support vector machine (SVM) and feed forward back propagation neural network (FFBPNN) classifiers. Haralick features are found more suitable for Brodatz texture image classification than wavelet features. It is found that Neural network classifier performs better than k -- Nearest Neighbour classifier and Support Vector Machine classifier for the selected Brodatz texture images.
- 18 August 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 312-317
Comparison of Classification Methods with Second Order Statistical Analysis and Wavelet Transform for Texture Image Classification
In computer vision system, texture refers to the characteristics of an object that appear on its surface. Texture classification is to classify textures in correct texture groups. The accuracy of texture image classification depends on quality of texture features and classification algorithm used. In this paper, Brodatz texture images are used as an experimental data. Features are extracted from texture images using Gray Level Co -- occurrence method (GLCM) and two-level, two-dimensional discrete wavelet transform (2D DWT). The extracted features are applied to the k-nearest neighbor (k - NN), support vector machine (SVM) and feed forward back propagation neural network (FFBPNN) classifiers. Haralick features are found more suitable for Brodatz texture image classification than wavelet features. It is found that Neural network classifier performs better than k -- Nearest Neighbour classifier and Support Vector Machine classifier for the selected Brodatz texture images.
- 18 August 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 318-323
Comparison of Second Order Statistical Analysis and Wavelet Transform Method for Texture Image Classification
The quality of texture image classification depends on quality of texture features and classification algorithms. Most important is to select texture features with highly discriminative to inter-class textures. In this paper, features are extracted from texture images using Gray Level Co-occurrence method and Wavelet method. Haralick features with a feed forward neural network show classification accuracy of 98.21%, while Wavelet features show classification accuracy of 96.05% for the same data. These results show that Haralick features are suitable for texture classification.
- 18 August 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 318-323
Comparison of Second Order Statistical Analysis and Wavelet Transform Method for Texture Image Classification
The quality of texture image classification depends on quality of texture features and classification algorithms. Most important is to select texture features with highly discriminative to inter-class textures. In this paper, features are extracted from texture images using Gray Level Co-occurrence method and Wavelet method. Haralick features with a feed forward neural network show classification accuracy of 98.21%, while Wavelet features show classification accuracy of 96.05% for the same data. These results show that Haralick features are suitable for texture classification.