Parthasarathy Subashini

Avinashilingam Deemed University for Women, Computer Science, Professor

Followers

377

Following

Co-authors

Public Views

Parthasarathy Subashini received a B.Sc (Mathematics) degree from Gobi Arts College, Bharathiar University, TamilNadu, India in 1990 and M.CA degree from the same in 1993. She has also received qualified degree of M.Phil and Ph.D respectively in Computer Science in year 1998 and 2009 from Avinashilingam University for Women, Tamil Nadu, India. From 1994 to 2007, she worked in the Computer Science Department of Avinashilingam University, where she is currently a Professor. She has also held few short-term appointments at several institutions around the state.Professor Subashini’s research has spanned a large number of disciplines like Image analysis, Pattern recognition, Neural networks, and Computational Intelligence. Concurrently, she contributed to several fields of mathematics, especially Nature inspired computing. She has authored or co-authored 1 Book, 4 Book chapters, 1 Monograph, 145 papers, including IEEE, Springer’s in various international, national journals and conferences. In course of her research and teaching, Professor Subashini has mentored over a hundred of post graduate students and guiding several doctoral students. She has held positions as reviewer, chairpersons for different peer reviewed journals. Under her supervision, she has ten research projects of worth more than 2.3 crores from various funding agencies like Defence Research and Development Organization, Department of Science and Technology, SERB and University Grants Commission. She has visited many countries like Singapore, Malaysia, Dubai, France, Switzerland, Italy, Canada, Germany, Spain, Czech Republic, Rome and China for various knowledge sharing events. As a member of IEEE, IEEE Computational Intelligence Society and IEEE Computer Society of India, She extended her contribution as IEEE Chair for Women in Computing under IEEE Computer Society of India Council in the year 2015-2016.To add up her credit, recently she has contributed a Nature Inspired Optimization algorithm called ‘Synergistic Fibroblast Optimization(SFO)’. The codes and published articles are publicly available for the perusal of the Research community in MATLAB central, Researchgate and Adademia.edu.

less

InterestsView All (6)

Uploads

Books by Parthasarathy Subashini

A New Optimization Approach – SFO for Denoising Digital Images

by Parthasarathy Subashini and Krishnaveni Marimuthu

— Computational paradigm which follows the theory of natural phenomenon is proved as an efficient... more — Computational paradigm which follows the theory of natural phenomenon is proved as an efficient approach to build versatile and adaptable systems to solve non-linear complicated problems. The widely used filter for removing noise in the digital images is median filter with different version, but low noise suppression and edge blurring are the most common demerits which are identified from it. In this paper, a newly developed metaheuristic algorithm Synergistic Fibroblast Optimization (SFO) is introduced by applying it to the median filtering technique for denoising the digital images. The work is evaluated in real time Tamil Sign Language dataset to assess the degradation of noise level and the performance is examined using standard metrics which shows that SFO based filtering technique produced promising results in both qualitative and quantitative perspectives. Keywords— Nature Inspired Computing (NIC), Synergistic Fibroblast Optimization (SFO), denoising technique, Tamil Sign Language, noise removal filters.

Download

Synergistic Fibroblast Optimization

Movement is the main characteristic of living species and is the major source of biologically ins... more Movement is the main characteristic of living species and is the major source of biologically inspired computational systems. The migration of cell organism can take the form of either movement of cells or movement within cells, and it is also capable of changing the shape as a result of reversible or irreversible contraction. This paper simulates synergistic fibroblast optimization (SFO), a multi-agent heuristic technique that models the migration and methodical behavior of the fibroblast. The proposed SFO technique exhibits the role of fibroblast in dermal wound healing process, by migrating the individual cell through the connective tissue, and synthesizes the collagen in the extracellular matrix for the new tissue formation during wound healing. Compared to related technique particle swarm optimization (PSO), SFO produces better results in terms of both accuracy and performance. An analysis of the proposed algorithm indicates that, the two most important factors contributing to SFO effectiveness are, fibroblast collaborative nature and goal oriented feature. The results suggest that SFO is a promising new optimization technique, which may be particularly applicable to find optimal maxima or minima, among the candidate solutions in the non-linear complicated optimization problem.

Download

Handwritten sentence recognition using Hybrid hidden Markov model

Concerning to Optical character recognition, Handwriting has sustained to persist as a means of c... more Concerning to Optical character recognition, Handwriting has sustained to persist as a means of communication and recording information in day to day life even with the introduction of new technologies. OCR is a process of automatic recognition of characters by computers in optically scanned and digitized pages of text. Some practical application potentials of OCR system are: (1) reading aid for the blind, (2) automatic text entry into the computer for desktop publication, library cataloging, ledgering, etc. (3) automatic reading for sorting of postal mail, bank cheques and other documents, (4) document data compression: from document image to ASCII format, (5) language processing, (6) multi-media system design, etc. The motivation of this work is to recognize handwritten Tamil sentences. Such a research will be useful to digitize ancient documents available both on paper, palm leaves and copper and stone inspirations.

‘Image denoising based on wavelet analysis for Satellite imagery’

Digital images are prone to a variety of types of noise. Noise is the result of errors in the im... more Digital images are prone to a variety of types of noise. Noise is the result of errors in the
image acquisition process that result in pixel values that do not reflect the true intensities
of the real scene (Gagnon & Smaili, 1996). There are several ways that noise can be
introduced into an image, depending on how the image is created. For example if the
image is scanned from a photograph made on film, the film grain is a source of noise.
Noise can also be the result of damage to the film, or be introduced by the scanner itself. If
the image is acquired directly in a digital format, the mechanism for gathering the data
(such as a CCD detector) can introduce noise. Electronic transmission of image data can
introduce noise. Noise is considered to be any measurement that is not part of the
phenomena of interest. Noise can be categorized as Image data independent noise and
image data dependent noise.

Wavelets are mathematical functions that cut up data into different frequency components,
and then study each component with a resolution matched to its scale (Durand &
Froment,1992). They have advantages over traditional Fourier methods in analyzing
physical situations where the signal contains discontinuities and sharp spikes. Wavelets
were developed independently in the fields of mathematics, quantum physics, electrical
engineering, and seismic geology. Interchanges between these fields during the last ten
years have led to many new wavelet applications such as image compression, turbulence,
human vision, radar, and earthquake prediction.

Download

‘Image denoising based on wavelet analysis for Satellite imagery’

Download

‘Intelligent Classifiers Fusion for enhancing recognition of genes and protein pattern of inheritance diseases’

Most the objective of intelligent systems is to create a model, which given a minimum amount of i... more Most the objective of intelligent systems is to create a model, which given a minimum amount of input data or information, is able to produce reliable recognition rates and correct decisions. In the application, when an individual classifier has reached its limit and, at the same time, it is hard to develop a better one, the solution might only be to combine the existing well performing classifiers. Combination of multiple classifier decisions is a powerful method for increasing classification rates in difficult pattern recognition problems. To achieve better recognition rates, it has been found that in many applications, it is better to fuse multiple relatively simple classifiers than to build a single sophisticated classifier. Such classifiers fusion seems to be worth applying in terms of uncertainty reduction. Different individual classifiers performing on different data would produce different errors. Assuming that all individual methods perform well, intelligent combination of multiple experts would reduce overall classification error and as consequence increase correct outputs. To date, content interpretation still remains as a highly complex task which requires many features to be fused. However, the fusion mechanism can be done at different levels of the classification. The fusion process can be carried out on three levels of abstraction closely connected with the flow of the classification process, i.e. data level fusion, feature level fusion, and classifier fusion. The work presented in this chapter focuses on the fusion of classifier outputs for intelligent models.

Papers by Parthasarathy Subashini

Computational Intelligence Based Machine Learning Methods For Rule-Based Reasoning In Computer Vision Applications

— In robot control, rule discovery for understanding of data is of critical importance. Basically... more — In robot control, rule discovery for understanding of data is of critical importance. Basically, understanding of data depends upon logical rules, similarity evaluation and graphical methods. The expert system collects training examples separately by exploring an anonymous environment by using machine learning techniques. In dynamic environments, future actions are determined by sequences of perceptions thus encoded as rule base. This paper is focused on demonstrating the extraction and application of logical rules for image understanding, using newly developed Synergistic Fibroblast Optimization (SFO) algorithm with well-known existing artificial learning methods. The SFO algorithm is tested in two modes: Michigan and Pittsburgh approach. Optimal rule discovery is evaluated by describing continuous data and verifying accuracy and error level at optimization phase. In this work, Monk's problem is solved by discovering optimal rules that enhance the generalization and comprehensibility of a robot classification system in classifying the objects from extracted attributes to effectively categorize its domain.

Download

‘A hybrid model for feature selection in mining Text Documents’ –

‘An efficient Thinning algorithm for Tamil handwritten Characters’

‘A Business Process model for e-Publishing industry’

Performance evaluation of the various edge detectors and filters for the noisy IR images

Edge detection is an important process of image processing and it is the foundation of pattern re... more Edge detection is an important process of image processing and it is the foundation of pattern recognition, which will affect the later processes. Especially in a noisy image, the edge detection is more important because noise is a common phenomenon in an image. This paper deeply studies the edge detection methods for noisy IR images and also studies the performance of the filters involved in removing the noise. Four basic edge detection operators such as Sobel, Prewitt, Log and Canny were selected and a comparison is done to check the quality of the edge detectors with noisy IR images. The study shows that the Sobel edge detector is best in detecting the edges when compared to other edge detectors. Then, the filters such as Median, Lee and Kuan were used to remove the noise in IR image. After applying all the filters the result shows that Median filter works good among the three filters. The quality of the edge detectors and the filter is calculated using the parameters PSNR and RMSE.

Download

3. ‘On-line Handwritten Kannada Character Recognition using Feed Forward Network with Back-propagation’

‘A Character recognition system for Tamil handwritten characters using Back propagation Neural network’

‘Securing images using Watermarking Techniques’

‘Holistic Tamil Handwritten Character Recognition’

‘Mining of Documents in Digital Library using Self-Organizing Map’

Women and IT

Automatic Identification of Algal Community from Microscopic Images

Bioinformatics and Biology Insights, 2013

A good understanding of the population dynamics of algal communities is crucial in several ecolog... more A good understanding of the population dynamics of algal communities is crucial in several ecological and pollution studies of freshwater and oceanic systems. This paper reviews the subsequent introduction to the automatic identification of the algal communities using image processing techniques from microscope images. The diverse techniques of image preprocessing, segmentation, feature extraction and recognition are considered one by one and their parameters are summarized. Automatic identification and classification of algal community are very difficult due to various factors such as change in size and shape with climatic changes, various growth periods, and the presence of other microbes. Therefore, the significance, uniqueness, and various approaches are discussed and the analyses in image processing methods are evaluated. Algal identification and associated problems in water organisms have been projected as challenges in image processing application. Various image processing approaches based on textures, shapes, and an object boundary, as well as some segmentation methods like, edge detection and color segmentations, are highlighted. Finally, artificial neural networks and some machine learning algorithms were used to classify and identifying the algae. Further, some of the benefits and drawbacks of schemes are examined.

‘Content Based Image Retrieval

Page 1. Content based image retrieval | 1 / 10 http://www.fit.vutbr.cz/~imlich/ Contentbased imag... more

‘Secured Tamil handwritten Digital Contents using Watermarking Technique’

Parthasarathy Subashini

Uploads

Books by Parthasarathy Subashini

Papers by Parthasarathy Subashini

Log In