Qualification: 
MCA, M.Tech
Email: 
md_dhanya@cb.amrita.edu

Dhanya M. Dhanalakshmy currently serves as Assistant Professor at the department of Computer Science and Engineering, Amrita School of Engineering, Coimbatore. Her areas of research include Image Processing.

Publications

Publication Type: Journal Article

Year of Publication Title

2020

Dhanya M. Dhanalakshmy, Akhila, M. S., Vidhya, C. R., and Dr. Jeyakumar G., “Improving the search efficiency of differential evolution algorithm by population diversity analysis and adaptation of mutation step sizes”, International Journal of Advanced Intelligence Paradigms, vol. 15, no. 2, p. 119, 2020.[Abstract]


The aim of this research work is to improve the efficiency of differential evolution (DE) algorithm, at the cases of its unsuccessful searches. Initially, this work discusses and compares different methods to measure the population diversity of DE algorithm implemented for DE/rand/1/bin variant for a set of benchmarking functions. A method which well demonstrates difference in population diversity evolution at successful and unsuccessful cases of DE search is identified based on comparison. This work is then extended to detect unsuccessful searches in advance using the evolution of population diversity measured by the identified method. On detecting a search as unsuccessful, a parameter adaptation strategy to adapt the mutation step size (F) is added to DE algorithm to recover from it. The improved DE algorithm, which comprises of the logic of adapting F value based on the population diversity, is compared with its classical version and found outperforming. The comparison results are reported in this paper.

More »»

2019

Dhanya M. Dhanalakshmy, Dr. Jeyakumar G., and Velayutham, C., “Crossover-Free Differential Evolution Algorithm to study the impact of Mutation Scale Factor Parameter”, International Journal on Recent Technology and Engineering, vol. 7, pp. 1728-1737, 2019.[Abstract]


The Differential Evolution (DE) algorithm, which is one of the popular optimization algorithms in the category of Evolutionary Algorithms (EAs), is known for its simplicity and wide applicability. Analysing and understanding the working nature of DE algorithm, for its further improvement, is an active research area in Evolutionary Computing (EC) field. In particular studying the role of its control parameters and their effects in its performance needs more attention. As an attempt in this direction, this paper presents evidences to showcase the role of the Scale Factor (F) parameter of DE algorithm through the plots generated based on the studies made from experimental results obtained through a well formulated experimental setup. The experimental set up includes five different benchmarking functions and a crossover-free DE algorithm, in which the crossover component is removed, for capturing better insights about the impact of F. The empirical evidences for the observed inferences are plotted as graphs.

More »»

2018

K. Vikram, Menon, H. P., and Dhanya M. Dhanalakshmy, “Segmentation of brain parts from MRI image slices using genetic algorithm”, Lecture Notes in Computational Vision and Biomechanics, vol. 28, pp. 457-465, 2018.[Abstract]


In this work a genetic algorithm based approach for segmenting the parts of brain MRI (Magnetic Resonance Imaging) image slices has been presented. Segmentation of the brain MRI image has been a challenging task and an open area for research off late due to reason that, the intensity differences between the different regions present in the image is very less. Hence a complete automation of segmentation process is difficult. In this work the various parameters of the genetic algorithm has been analyzed and an oprimized threshold value has been determined based on the slice type. The complexities in the segmentation algorithm and the challenges have also been reported. © 2018, Springer International Publishing AG.

More »»

2016

R. Suganya and Dhanya M. Dhanalakshmy, “Graphical representation of handwritten mathematical expression recognized from offline video lectures”, Asian Journal of Information Technology, vol. 15, pp. 2943-2947, 2016.[Abstract]


Mathematics is a universal language in terms of science and technology. It gives the exact information than any other languages. Hence recognition of mathematical expression is one of the hot areas of research in pattern recognition and machine language. In this study, recognition of handwritten mathematical expression with the corresponding graphical representation is done for a camera-based offline video that contains handwritten mathematical expressions. © Medwell Journals, 2016.

More »»

2016

Dhanya M. Dhanalakshmy, Pranav, P., and Dr. Jeyakumar G., “A Survey on Adaptation Strategies for Mutation and Crossover Rates of Differential Evolution Algorithm”, International Journal on Advanced Science, Engineering and Information Technology (IJASEIT) (Scopus) , vol. 6, no. 5, pp. 613–623, 2016.[Abstract]


Differential Evolution (DE), the well-known optimization algorithm, is a tool under the roof of Evolutionary Algorithms (EAs) for solving non-linear and non-differential optimization problems. DE has many qualities in its hand, which are attributing to its popularity. DE also is known for its simplicity in solving the given problem with few control parameters: the population size (NP), the mutation rate (F) and the crossover rate (Cr). To avoid the difficulty involved in setting of suitable values for NP, F and Cr many parameter adaptation strategies are proposed in the literature. This paper is to present the working principle of the parameter adaptation strategies of F and Cr. The adaptation strategies are categorized based on the logic used by the authors, and clear insights about all the categories are presented. More »»

2015

M. K. Vineeth, Arafath, A. B. Yazir, Dhanya M. Dhanalakshmy, and Bagyammal T., “Blind watermarking for the images captured by android mobiles”, International Journal of Applied Engineering Research, vol. 10, no. 55, pp. 2733-2736, 2015.[Abstract]


In this paper we present a securable image watermarking process for the user authentication as an android application. This system is built to protect personal and official images of a person that are captured using his/her own phone. The user can choose the types of watermark that he/she wants. The proposed system requires less battery consumption and processing time. © 2015, Research India Publications.

More »»

2015

G. Sivan and Dhanya M. Dhanalakshmy, “Automated traffic sign recognition system for Indian roads”, International Journal of Applied Engineering Research, vol. 10, pp. 35618-35626, 2015.[Abstract]


<p>Traffic Sign recognition systems are used for increasing the road traffic safety by helping drivers gain better awareness of the road and its potential hazards, which automatically alerts and informs the driver about the nearby traffic signs on the roads. In this paper, a real time sign detection and recognition system is proposed for Indian traffic signs. A camera mounted on the vehicle will capture roadside video. The BRISK descriptor is used in order to extract a set of invariant features of the detected road sign. After the detection and recognition phase, the sign will be getting identified and proper feed back will be given to the driver. © Research India Publications.</p>

More »»

2014

Dhanya M. Dhanalakshmy, “Musical Sheet Segmentation”, International Journal of Engineering Research and Applications, vol. 4, no. 5, pp. 11-16, 2014.[Abstract]


Music has had an important role in human life from time immemorial. Music has been shared in two ways aurally and as written documents known as musical notes or musical scores. Many ancient cultures have used musical symbols to represent melodies and lyrics but none of them is as comprehensive as a written language or document. Thus the knowledge of ancient music is limited to a few fragments which are mostly unpublished. Hence to preserve such music we need to introduce a computerized system to digitalize and to decode the musical symbol images and reconstruct it as new score which will be in machine readable format. Here the machine readable format is MIDI. Prior to converting the musical symbols into MIDI format, musical sheets need to be segmented for isolating the musical symbols. Since synthetically generated musical sheets are used here, the segmentation process can be carried out using recursive graph cut method. Here we discuss the initial few steps such as staff line removal, text removal and segmentation of musical sheet.​​​​​​​

More »»

2014

and Dhanya M. Dhanalakshmy, “Text Line Segmentation of Curved Document Images”, International Journal of Engineering Research and Applications, vol. 4, pp. 32-36, 2014.[Abstract]


Document image analysis has been widely used in historical and heritage studies, education and digital library. Document image analytical techniques are mainly used for improving the human readability and the OCR quality of the document. During the digitization, camera captured images contain warped document due perspective and geometric distortions. The main difficulty is text line detection in the document. Many algorithms had been proposed to address the problem of printed document text line detection, but they failed to extract text lines in curved document. This paper describes a segmentation technique that detects the curled text line in camera captured document images.

More »»

Publication Type: Conference Proceedings

Year of Publication Title

2019

Dhanya M. Dhanalakshmy, Dr. Jeyakumar G., and C. Velayutham, S., “Analytical Study and Empirical Validations on the Impact of Scale Factor Parameter of Differential Evolution Algorithm”, Pattern Recognition and Machine Intelligence, vol. 11941. Springer International Publishing, Cham, pp. 328-336, 2019.[Abstract]


Differential Evolution (DE) is a popular optimization algorithm in the repository of Evolutionary Algorithm (EAs). The DE algorithm is known for its simple algorithmic structure, which has minimal number (only three) of control parameters. A propitious avenue for enhancement of DE’s performance is making it a self-adaptive algorithm. There exist many algorithms for self-adapting one or more of DE parameters. The self-adaptiveness of any parameter needs critical analysis on the impact of that parameter. This paper analyzes and presents the impact of the parameter - mutation scale factor (F) of DE. Including empirical evidences for understanding the effect of F on the nature of convergence of DE at solving a problem is the novelty of this paper. The experiment includes implementing a set of benchmark functions, with diversified features, using different variants of DE, in order to critically analyze the role of F.

More »»

2017

Dhanya M. Dhanalakshmy and Menon, H. P., “Curved document image rectification”, 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI). IEEE, Udupi, India, pp. 783-786, 2017.[Abstract]


Digitization of documents has gained prominence in the recent past for data preserving. Paper documents can be converted to digital form by using various modes of acquisition techniques. In this paper processing of data captured using normal digital camera has been considered. The camera captured document images may contain warped document due to perspective and geometric distortions. Curvature of text lines is a prominent characteristic of such distortions, which can affect the recognition accuracy of Optical Characters for OCR (Optical Character Recognition). To improve the accuracy, rectification of perspective distortions plays an important role. Here, a rectification technique that detects and straightens text lines with curvature in document images captured using normal digital camera is proposed.

More »»

2017

Dhanya M. Dhanalakshmy, Menon, H. P., and Vinaya, V., “Musical notes to MIDI conversion”, 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI). IEEE, Udupi, India, pp. 799-804, 2017.[Abstract]


Most of the popular music compositions exists in either hand-written or facsimile format even in this modern era. In order to preserve these precious music sheets, they needs to be digitization followed by conversion into machine readable format, such that a system can decode the symbolic images automatically and play the music. If an image of the musical work becomes available, the entire process of digitization can be considered as a document image processing application. Musical notes to it machine readable format conversion mainly aims at reading automatically generated musical scores in order to convert them to an electronic format such as MIDI file. In this paper, we propose a system that takes an image of a music sheet as input, identifies music symbols, calculates their pitch and duration and outputs a string corresponding to each line in the music sheet which can be played using Musicgui in DSP Toolbox. Major challenge faced is the removal of staff lines in the music sheet image without losing music symbols. Major steps involved in this are staff line removal, symbol extraction, symbol recognition, and conversion of musical scores into MIDI format.

More »»

Publication Type: Conference Paper

Year of Publication Title

2015

M. K. Vineeth, Arafath, A. B. Yazir, Dhanya M. Dhanalakshmy, and Bagyammal, T., “Blind watermarking for the images captured by android mobiles”, in International Conference on Advances in Applied Engineering and Technology (ICAAET) – 2015, Syed Ammal Engineering College, Dr. E M Abdullah Campus, Ramanathapuram-623502, 2015.

2014

A. .M and Dhanya M. Dhanalakshmy, “Text Line Segmentation of curved document images - A survey”, in National Conference on Recent Advances in Computer Science & Information Engineering (RACIE'14), St. Joseph College of Engg. & Tech., Palai, Kottayam, 2014.

Faculty Research Interest: