G. ELAIYARAJA
@vemu.org
Professor and ECE/Faculty
Vemu Institute of Technology
RESEARCH, TEACHING, or OTHER INTERESTS
Engineering, Electrical and Electronic Engineering, Multidisciplinary, Signal Processing
Scopus Publications
Scopus Publications
Elaiyaraja Gandhi and Kumaratharan Narayanaswamy
Universiti Putra Malaysia
Flames recognition methodology is most important for completely diminishing the flame losses in different fired environmental conditions. However, there is delayed detection and lower accuracy in the various common detection methods. Thus, optimum image/video fire detection technology is proposed in this paper based on a support vector machine (SVM) with the fuzzy c-mean, discrete wavelet transform (DWT), and gray level co-occurrence matrices (GLCM) feature extraction for the detection of fires. This algorithm has been tested on various fire and non-fire images for classification accuracy. A performance evaluation of the proposed classifier algorithm and existing algorithms is compared, showing that the accuracy and other metrics of the proposed classifier algorithm are higher than other algorithms. Furthermore, simulation results show that the proposed classifier model is improved the forecast detection accuracy of fires.
G. Elaiyaraja, N. Kumaratharan, and T. Chandra Sekhar Rao
Informa UK Limited
We proposed an optimum de-noising filter using wavelet threshold for the removal of adaptive white Gaussian noise from degraded medical images/colour video sequence based on system noise calculation. The performance of the proposed Gaussian de-noising technique is compared with various de-noising techniques such as Bayesian least squares-Gaussian scale mixtures, bilateral filter, adaptive bilateral filter, multi-resolution bilateral filter, nonlocal-Means, wavelet threshold based filters, and kernel-based method. The proposed methods have comparable/superior performance and less computational time compared to other techniques.
G. Elaiyaraja and N. Kumaratharan
The Korean Institute of Electrical Engineers
In recent years, medical image diagnosis has growing significant momentous in the medicinal field. Brain and lung image of patient are distorted with salt and pepper noise is caused by moving the head and chest during scanning process of patients. Reconstruction of these images is a most significant field of diagnostic evaluation and is produced clearly through techniques such as linear or non-linear filtering. However, restored images are produced with smaller amount of noise reduction in the presence of huge magnitude of salt and pepper noises. To eliminate the high density of salt and pepper noises from the reproduction of images, a new efficient fuzzy based median filtering algorithm with a moderate elapsed time is proposed in this paper. Reproduction image results show enhanced performance for the proposed algorithm over other available noise reduction filtering techniques in terms of peak signal -to -noise ratio (PSNR), mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), image enhancement factor (IMF) and structural similarity (SSIM) value when tested on different medical images like magnetic resonance imaging (MRI) and computer tomography (CT) scan brain image and CT scan lung image. The introduced algorithm is switching filter that recognize the noise pixels and then corrects them by using median filter with fuzzy two-sided π- membership function for extracting the local information.
G. ELAIYARAJA, N. KUMARATHARAN, and C RAMA PRAPAU
Oriental Scientific Publishing Company
The recent advances in sparse representations of images have achieved outstanding results in terms of denoising and restoration; but removal of real and structured noise in digital video sequences remains a challenging problem. Based on this idea, the problem addressed in this paper proposes to improve the decision median filtering algorithm for denoising of video sequences corrupted with impulse noise. The proposed algorithm processes the extracted frame (from corrupted video sequences) by incorporating robust decisions to selectively operate upon the corrupted pixels. The local statistical parameters (of the spatial kernel) are then used to decide whether to restore the centre pixel with median value or adaptively increment the kernel size. This helps in restoration of structural content with minimal blurring at high noise densities. Experimental results show that the proposed algorithm achieves better performance with minimal computational complexity; yielding higher values of PSNR and SSIM for restored frames.