Browsing by Author "Raja, Sharif Ahmmad"

Now showing 1 - 3 of 3

2D Log gabor and SVD based parallel texture feature extraction usingNVIDIA GPU
(BRAC University, 4/20/2016) Raja, Sharif Ahmmad; Ratul, Aminur Rab; Niloy, Sakib Anjum; Uddin, Jia
Texture feature is one of the most popular technique in image segmentation, classification, retrieval and many others. Now a days, among other ways of texture feature extraction, Gabor filtering has been widely used. Here, we are presenting a well ordered two dimensional texture feature extraction method. First, we convert the image to gray level. Then a 2D Log Gabor filter with different frequencies decomposed with the SVD algorithm applies on each converted part of gray level image to extract appropriate distinctive texture information. To evaluate the performance of proposed model, we utilize singular values of SVD as a feature vector. For classifier, we use Naïve Bayes classifier for training and testing our experimental dataset. In our experimental set up we utilize an NVDIA GeForce GTX780 graphics card. Experimental result showed this parallel implementation of our model is56X faster than conventional CPU implementation.
A novel parallel texture feature extraction method using log-gabor filter and singular value decomposition (SVD)
(© 2017 ACM, 2017-01) Ratul, Md Aminur Rab; Raja, Sharif Ahmmad; Uddin, Jia
Texture feature extraction consolidated with texture feature detection and feature matching solves many typical problems of image processing and computer vision; such as, texture classification, pattern recognition, object detection, and image segmentation. Through this paper, a new method for texture feature extraction is presented which uses Log-Gabor Filter and Singular Value Decomposition (SVD) algorithm. In the proposed model, sample images are converted to gray level images. And then, to elicit suitable distinctive texture orientation, a 2D Log- Gabor filter with various frequencies and different edges disintegrated with the SVD employ on each converted gray level images. Finally, singular values of SVD used as feature vector for this texture feature extraction model. For training and testing of experimental datasets, Naive Bayes classifier has been used. The Log-Gabor and SVD based feature extraction shows improved performance by exhibiting higher classification accuracy for our tested dataset compare to conventional Gabor and SVD feature extraction method. Furthermore, in order to decrease the computational and time complexity, an NVIDIA GeForce GTX780 GPU is used to implement our proposed model in parallel. The GPU implementation of proposed model showed average 3X speedup for per image than conventional CPU implementation.
A novel parallel texture feature extraction method using log-gabor filter and singular value decomposition (SVD)
(© 2017 ACM, 2017-01) Ratul, Md Aminur Rab; Raja, Sharif Ahmmad; Uddin, Jia
Texture feature extraction consolidated with texture feature detection and feature matching solves many typical problems of image processing and computer vision; such as, texture classification, pattern recognition, object detection, and image segmentation. Through this paper, a new method for texture feature extraction is presented which uses Log-Gabor Filter and Singular Value Decomposition (SVD) algorithm. In the proposed model, sample images are converted to gray level images. And then, to elicit suitable distinctive texture orientation, a 2D Log- Gabor filter with various frequencies and different edges disintegrated with the SVD employ on each converted gray level images. Finally, singular values of SVD used as feature vector for this texture feature extraction model. For training and testing of experimental datasets, Naive Bayes classifier has been used. The Log-Gabor and SVD based feature extraction shows improved performance by exhibiting higher classification accuracy for our tested dataset compare to conventional Gabor and SVD feature extraction method. Furthermore, in order to decrease the computational and time complexity, an NVIDIA GeForce GTX780 GPU is used to implement our proposed model in parallel. The GPU implementation of proposed model showed average 3X speedup for per image than conventional CPU implementation.