V. Santhi

Bio: V. Santhi is an academic researcher from VIT University. The author has contributed to research in topics: Speckle pattern & The Internet. The author has an hindex of 2, co-authored 2 publications receiving 4 citations.

Region based speckle noise reduction approach using fuzzy techniques

Abstract: Image denoising is an important step in the field of image processing. Presence of noise can lead to various obstacles in the way of proper analysis of images to extract information from it like misinterpretation of data, loss in the usability of the image etc. Denoised images are used in various applications such as in medical diagnosis, ultrasound imaging, satellite imaging, pattern recognition etc. Different image denoising techniques are already in existence that uses different filters to remove noise. Fuzzy logic is a soft computing technique that allows for approximations and partial truths. The benefit of using fuzzy logic for denoising purpose is to increase the tractability, robustness and effectiveness of the existing traditional denoising methods. This paper presents a novel fuzzy based method for removal of speckle noise, which mostly affects ultrasound and SAR images.

Web based portal using a biometrie interface and Android application to assist non-government organizations

Abstract: A web based application can only function with an active internet connection and uses HTTP as its primary protocol for communication. They often run inside a web-browser. Most applications are client-based, where a minor part of the program is downloaded to a user's desktop, but processing of requests are done over the internet on an external server. It has now become the leading approach to utilize technology in order to enhance an organizations efficiency and productivity. It helps to access any business information from all over the world at any time as well as allows us to save time and money and increase interactions between customers and partners. However, such applications have not been made much use of in the management of a Non-Government Organization (NGO). This proposed work suggests an approach to create a database structured to that of an NGO which will be interfaced with an application server. A web based application along with and android app will act as clients. To increase the security and transparency of the NGO, it will also be using a biometric interface that will link all related information of the organization. The proposed approach can also be modified to suit other non-profit organizations with similar requirements. Most NGO websites simply provide basic information about their organization, whereas this proposed approach aspires to not only provide information but automate all the functions of the organization, reduce tedious paperwork, decrease queueing, increase interaction between members of the organization in a safe and secure manner.

A Review of Wavelet Transform based Techniques for Denoising Latent Fingerprint Images

Abstract: Authentication systems robustness can be affected by the fingerprint image quality. Fingerprint image denoising is essential for better performance of any authentication system. In this paper, most recent wavelet transform based techniques for fingerprint image denoising are reviewed. It is observed that there are four important components of wavelet transform based denoising techniques. These important components include wavelet filter, thresholding rule, threshold value computation method and the level of decomposition. The stationary wavelet transform and the weighted median are recommended over conventional discrete wavelet transform and median estimator.

Performance Analysis of Medical Image Denoising Techniques

Abstract: Noise reduction in digital image is a daunting assignment for the analysts in Digital Image Processing. As per survey, images are affected by some kind of noises such as gaussian noise, speckle noise and salt and pepper noise. Noise destroys the quality of the active radar, synthetic aperture radar (SAR), medical images. As per the literature, medical images are affected by low resolution, low contrast and geometric deformations, thereby reducing the diagnostic value of medical image. Predominantly, ultrasound images are influenced by speckle noise. Denoising is used to improve visual appearance of an organ and helps in better understanding of disease and accordingly decide the line of treatment for medical field. The proposed work focuses the importance of Spatial filtering techniques that improves resolution, contrast, edge preservation. This paper emphasis on preprocessing techniques that improves the statistical parameter peak signal to noise ratio (PSNR) which are the integral attributes of image quality. The generated result shows that the Wiener and Noise Adaptive Fuzzy switching median filter performs better PNSR values for reduction of low (10%), medium (50%) and high (80%) densities of speckle noise while Adaptive median and Noise Adaptive fuzzy switching median filters achieves good PSNR value for low (10%), medium (50%) and high (80%) noise densities of Gaussian noise among various types of filters. Hence Noise Adaptive Fuzzy switching median filter performs well for low, medium and high noise densities of both types speckle and gaussian noise.

SAR Object Detection Using a Novel Convolutional Neural Network Architecture

Abstract: . In recent years, the importance of SAR (synthetic aperture radar) image analysis is growing day by day due to the vast applications in the field of oceanography, military war, land observation, agriculture, disaster management and geography. These applications required accurate classification of high-resolution SAR images. In the present study, two different machine learning techniques are applied on the SAR dataset to analyze the classification accuracy. The first classification technique is SVM (support vector machine) along with principal component analysis (PCA) for feature reduction. While, in the second technique, a novel CNN (convolutional neural network) has been proposed to perform the classification on SAR images. Essential experimental analysis has been carried out based on the MSTAR dataset. Experimental results of the current study showed that the proposed CNN model outperformed the SVM classifier with an accuracy of 98.69% .

Designing real-time research data portal of JTI POLINEMA

Abstract: Research culture in Department of Information Technology Polinema is always developed continuously every time. In addition, many research titles that are critical of environmental problems are beginning to be seen. The Information Technology Department has an outstanding focus on issues, namely smart systems which include smart education, smart living, smart healthy, smart city and smart tourism. Research resources in the Information Technology Department Polinema are competing to realize that research focus. For this reason, efforts are needed to increase the availability of facilities that are not only material. The fast response can be solved by providing Real-Time Research Data Portal. The contribution of this paper is to design of middle ware on web portals that have high scalability capabilities for providing large data facilities and fast access. Real-time big data processing is the path that will be described in the architecture that will be created and adapted to the needs of the Department of Information Technology Polinema. The results of the latency evaluation test indicated that RabbitMQ allowed us to enforce concurrency, thereby reducing overall RTC by up to 50% compared to traditional HTTP.

De-Speckling of SAR Images with Fuzzy Filters along with Altered Preserved Edge Values

Abstract: In this research, the de-noising of speckled SAR image has been done with fuzzy filters (ATMED, TMED, ATMAV & TMAV). SAR image or Synthetic Aperture Radar image consists of the informatics of ISW (Internal solitary waves). A new technique has been proposed which preserved the edge pixels by fuzzy edge detection method and then altered with the filtered image-pixels by fuzzy filtration for getting the de-noised image. The comparative result shows that the proposed filter performs better than the other filtered results in terms of PSNR (41.61 dB), MAE (1.47), MSE (4.54) for TMAVxAPE & SSIM (81%) for ATMEDwAPE. The proposed method in this research shows better SSI (Spackle Suppression Index) value. Therefore the experimental result illustrates that the suggested fuzzy filter is much more capable of simultaneously protecting edges and suppressing speckle noise. This research will be beneficial to remove spackle noise from SAR images and can be used for remote sensing and mapping of surface area of earth.