Kanakaraj, S, GovindanV.K., P.N. P.
2012.
A Fast Brain Image Registration Using Axial Transformation. Wireless Networks and Computational Intelligence. (
Venugopal, K. R., Patnaik, L. M., Eds.).:206–212., Berlin, Heidelberg: Springer Berlin Heidelberg
AbstractThe registration process in the medical field has evolved rapidly making the physicians to rely on computer algorithms for processing and diagnosing the diseases. Registration has been used for studying disease growth and treatment responses of the diseases. Brain image registration enables physicians to diagnose diseases like Alzheimer's based on the changes in the internal structure of the brain. One of the main challenges in this topic is the huge computational requirements of the registration processes. In this paper we propose a method for the fast and accurate registration of MR brain images using the shape property of the axial slice of the brain. The algorithm exhibits reduced computational time when compared to a standard existing approach, which makes it useful for real time applications.
Pournami, PN, Govindan VK.
2019.
Highly Repeatable Feature Point Detection in Images Using Laplacian Graph Centrality. Proceedings of the International Conference on ISMAC in Computational Vision and Bio-Engineering 2018 (ISMAC-CVB). (
Pandian, Durai, Fernando, Xavier, Baig, Zubair, Shi, Fuqian, Eds.).:687–697., Cham: Springer International Publishing
AbstractImage registration is an indispensible task required in many image processing applications, which geometrically aligns multiple images of a scene, with differences caused due to time, viewpoint or by heterogeneous sensors. Feature-based registration algorithms are more robust to handle complex geometrical and intensity distortions when compared to area-based techniques. A set of appropriate geometrically invariant features forms the cornerstone for a feature-based registration framework. Feature point or interest point detectors extract salient structures such as points, lines, curves, regions, edges, or objects from the images. A novel interest point detector is presented in this paper. This algorithm computes interest points in a grayscale image by utilizing a graph centrality measure derived from a local image network. This approach exhibits superior repeatability in images where large photometric and geometric variations are present. The practical utility of this highly repeatable feature detector is evident from the simulation results.
Maddaiah, PN, Pournami PN.
2019.
Image Registration Using Single Swarm PSO with Refined Search Space Exploration. Pattern Recognition and Machine Intelligence. (
Deka, Bhabesh, Maji, Pradipta, Mitra, Sushmita, Bhattacharyya, Dhruba Kumar, Bora, Prabin Kumar, Pal, Sankar Kumar, Eds.).:337–346., Cham: Springer International Publishing
AbstractImage registration is an elementary task in Computer Vision, which geometrically aligns multiple images of a scene, captured at different times, from various viewpoints, or by heterogeneous sensors. The optimisation strategy we employ for achieving the optimal set of transformation vectors is a major factor that determines the success and effectiveness of an automatic registration procedure. This paper discusses a scheme to modify the conventional Particle Swarm Optimisation (PSO) algorithm for better search space exploration and for faster convergence. While PSO is running, after half of the total number of iterations, find the particle which is in worst position in space, then reposition that particle by mean value of its current position and the global solution. It is observed that re-positioning the worst particle in space helps that particle from premature convergence to a local optimum solution and motivates the particle to generate unique search directions, which increased the possibility of finding the globally best solution. An image registration algorithm using this modified PSO method is also presented. From the experimental results presented here, it is visible that the proposed algorithm guarantees superior results in terms of registration accuracy and reduced execution time, even in the case of large deformations between the reference and float images.
Antony, J, Penikalapati A, Reddy VKJ, Pournami PN, Jayaraj PB.
2021.
Towards Protein Tertiary Structure Prediction Using LSTM/BLSTM. Advances in Computing and Network Communications. (
Thampi, Sabu M., Gelenbe, Erol, Atiquzzaman, Mohammed, Chaudhary, Vipin, Li, Kuan-Ching, Eds.).:65–77., Singapore: Springer Singapore
AbstractAntony, JisnaPenikalapati, AkhilReddy, J. Vinod KumarPournami, P. N.Jayaraj, P. B.Determining the native structure of a protein, given its primary sequence is one of the most demanding tasks in computational biology. Traditional protein structure prediction methods are laborious and involve vast conformation search space. Contrarily, deep learning is a rapidly evolving field with outstanding performance at problems where there are complicated relationships between input features and desired outputs. Various deep neural network architectures such as recurrent neural networks, convolution neural networks, deep feed-forward neural networks are becoming popular for solving problems in protein science. This work mainly concentrates on prediction of three-dimensional structure of proteins from the given primary sequences using deep learning techniques. Long short-term memory (LSTM) and bidirectional LSTM (BLSTM) neural network architectures are used for predicting protein tertiary structures from primary sequences. The result shows that single-layer BLSTM networks fed with primary sequence and position-specific scoring matrix data gives better accuracy compared to LSTM and two-layer BLSTM models. This study may get benefited to the computational biologists working in the area of protein structure prediction.