MIT-World Peace University (MIT-WPU) is a top educational institute located in Pune, India. It is recognized within&nbsp;UGC under Government of Maharashtra Act No. XXXV 2017.&nbsp;

It is part of the MIT group of institutions (established in 1983) which covers 10+ campuses across India and has more than 50,000+ students enrolled across various disciplines at a given point of time. The institute houses 15 schools ranging from Engineering &amp; Technology, Design, Pharmacy, Commerce, Governance among others. It offers undergraduate, postgraduate and PhD programs among different disciplines.&nbsp;

&nbsp;

MIT World Peace University

Due to the scattered lighting and light absorbed conditions, the underwater images frequently suffered from the low contrast as well as color distortion. As underwater images with the different color tones are captured under different light conditions, it is difficult to perform restoration and enhancement of such images. There are number of conventional methods reported to improve the quality of underwater images, however they constantly performs poor. In this paper, we propose a novel underwater image restoration and enhancement algorithm. We proposed the novel modified depth estimation approach for underwater images based on image blurriness as well as light absorption. To improve the processing speed as well as image quality we proposed novel image blurriness estimation approach in first we performed the image normalization and double precision conversion to improve the processing speed, then apply the edge-stopping pyramid technique rather than Gaussian filtering to improve image quality. The proposed approach is simulated and evaluated against the state-of-art methods in terms of processing time, PSNR, SSIM etc. © 2018 IEEE.

World University root node

School of Electronics & Communication Engineering

Engineering and Technology

Proceedings - 2018 4th International Conference on Computing, Communication Control and Automation, ICCUBEA 2018

Underwater Image Restoration Based on Light Absorption

Electrocardiogram (ECG) is a non-stationary signal which constitutes a lineal recording that provides an insight into heart's electrical activity. Because Cardio Vascular diseases (CVD) are numbered one as reason of mortality globally, detection of abnormalities in ECG at an early stage is crucial for diagnosis and accordingly the treatment. A system can help the cardiologists in diagnosing the arrhythmia present in a patient. The proposed architecture uses Adaptive Neuro-Fuzzy Inference System (ANFIS) with the input preprocessed with subtractive clustering method to learn fuzzy logic. Five morphological and five statistical ECG features are utilized to determine if the patient's heartbeats are normal or irregular and classify them accordingly. During statistical feature extraction, Principal Component Analysis (PCA) on detail coefficients is implemented for optimization. For classification, four classes of ECG are considered, Left Bundle Branch Block (LBBB), normal, Atrial Premature Contraction (APC) and Paced Beats (PB). The proposed system gives an overall classification accuracy of 97.75%. The overall sensitivity, average specificity and average false prediction ratio obtained are 0.9775, 0.9925 and 0.0075 respectively. © 2017 IEEE.

2017 3rd International Conference on Advances in Computing, Communication &amp; Automation (ICACCA)(Fall)

Arrhythmia classification using neuro fuzzy approach

Video compression is a key enabling technology for multimedia communication. The need for high-quality video processing in multimedia products is increasing, leading to enhancement in coding techniques. In future, multimedia systems require efficient video coding algorithms that provide high and efficient compression. The H.264 is one of the latest coding standards that provide high compression efficiency and network friendly representation compare to previous standards. In this paper, we present an architecture for Context-Based Adaptive Binary Arithmetic coding (CABAC) decoder which is used in H.264 as entropy decoding. CABAC gives higher compression efficiency by bringing higher implementation cost and complexity. In this work, we are focusing on designing an efficient and fast hardware and software co-design for CABAC which can be useful for the real-time application. A complex part of CABAC is design over FPGA hardware and remaining parts are on processing system (PS). For this work, we are using zynq-7000 based Zedboard which consists two parts one is Programing Logic (FPGA) and second is Processing system (Arm Cortex-9). We create an IP for a part of CABAC which can communicate with PS by AXI bus.

Proceedings of the International Conference on Inventive Computation Technologies, ICICT 2016

Hardware software co-design for CABAC entropy decoder

The recent technology in digital cameras uses single CCD or CMOS sensors as a substitute to three separate RGB sensors. Color camera consists of single CCD or CMOS sensor with an overlaid Color Filter Array (CFA). This paper proposes a novel approach of CFA demosaicing. In proposed approach, bilinear interpolation with sharpening filter is used for CFA demosaicing. The proposed work tested on Virtex 5 FPGA in real time mode as well as on true color test image database. Xilinx System Generator (XSG) has been used for system modeling and design implemented on target device FPGA. The results of proposed FPGA based work improved than software based simple bilinear interpolation, edge directed interpolation and adaptive color plane interpolation methods and comparative to modified adaptive color plane interpolation method. The proposed approach has low computational complexity and high image processing speed; hence the design can be implemented in real time low cost embedded system applications. © 2015 IEEE.