Qualification: 
Ph.D, M.Tech
Email: 
ok_sikha@cb.amrita.edu

Dr. Sikha O. K. joined Amrita School of Engineering, Coimbatore in June 2013. She received her B. Tech. degree in Information Technology from Calicut University Institute of Engineering and Technology, Calicut and M. Tech. degree in Computational Engineering and Networking from Amrita School of Engineering, Coimbatore. She currently serves as Assistant Professor in the Department of Computer Science and Engineering, School of Engineering, Amrita Vishwa Vidyapeetham, Coimbatore campus. Her areas of interest include image Processing, Medical Image Processing, Computer Vision and AI.

Awards, Achievements & Honors

  • Received “Amrita Innovation and Research Award (AIRA-2021).
  • Received “Young Women Educator & Researcher” award , from National Foundation for Entrepreneurship Development (NFED).
  • Received the “Excellence in Teaching” award for the academic year 2016-2017, from Amrita School of Engineering, Coimbatore.
  • Awarded with shield for securing University First Rank in M.TECH (Computational Engineering and Networking) (2011-2013) by Amrita Vishwa Vidyapeetham, Coimbatore.

Professional Experience

  • Assistant Professor, Computer Science and Engineering, Amrita Vishwa Vidyapeetham, Coimbatore, (June 2013 -till date).
  • Successfully defended her Ph. D. Thesis titled, " Dynamic Mode Decomposition for Salient Region Detection In Images" on July 2020 under the supervision of Dr. K. P. Soman, Professor & Head, CEN, Amrita School of Engineering, Coimbatore.
  • Promoted as Assistant Professor (Senior Grade) on January 2018.

Research Area

  • Image Processing
  • Machine Learning
  • Deep Learning
  • Artificial Intelligence for HealthCare Analytics

Reviewer of Journal/ Conference

  • Active Reviewer of the SCIE indexed journal: “Journal of Intelligent and Fuzzy Systems”.
  • Served as Reviewer of 4th International Conference on Smart Computing and Informatics (SCI-2020)
  • Active Reviewer for the journal “KSII Transactions on Internet and Information Systems

Online Certified Courses

  • Neural Networks and Deep Learning- Coursera (Sponsored by deeplearning.ai)
  • Convolutional Neural Networks – Coursera (Sponsored by deeplearning.ai)
  • Image Classi'cation with CNNs using Keras- Coursera
  • Classi'cation with Transfer Learning in Keras - Coursera
  • Machine Learning for All – Coursera (Sponsored by University of London)
  • Structuring Machine Learning Projects - Coursera (Sponsored by deeplearning.ai)
  • Deep Learning Fundamentals with Keras- EDX ( offered by IBM)
  • Image and Video Processing: From Mars to Hollywood with a Stop at the Hospital – Coursera (Sponsored by Duke University)

Invited Talks

  • Rendered a session on “Data Driven Models for Visual Computingduring one week online AICTE ATAL faculty Development Programme(FDP) on Deep Learning for Visual Computing organized by Srikrishna College of Engineering and Technology, Kuniamputhur, Coimbatore on 15th July 2021.[Certificate of Appreciation
  • Rendered a series of sessions on “Data science and Data Citizenship” as a part of NPA Data science Certification program, organized by University of Stirling , Ras Al Khaima, UAE during June 12- 20. [Letter of Appreciation]

Publications

Publication Type: Journal Article

Year of Publication Title

2021

Sikha O. K. and P., S. K., “Dynamic Mode Decomposition based salient edge/region features for content based image retrieval”, 2021.[Abstract]


Considering the gap between low-level image features and high-level retrieval concept, this paper investigates the effect of incorporating visual saliency based features for content-based image retrieval(CBIR).Visual saliency plays an important role in human perception due to its capability to focus the attention on the point of interest, i.e. an intended target. This selection based processing can be well explored in localized CBIR systems, since in context of CBIR the users will be interested only in certain parts of the image. The proposed methodology uses Dynamic Mode Decomposition framework to extract the saliency map which highlights the part of the image that grabs human attention. Then, based on the saliency map, an efficient salient edge detection model is introduced. Visual saliency based features (salient region, edge) are then combined with texture and color features to formulate the high dimensional feature vector for image retrieval. State-of-the-art learning based CBIR models demands for user feed back to model the retrieval concept. In contrast with these models, proposed CBIR system does not require any user interaction, since it uses perceptual level features for the retrieval task. Performance of the proposed CBIR system is evaluated and confirmed on images from Wang’s dataset using benchmark evaluation metrics like precision and recall. Experimental results reveals that incorporation of saliency features can represent human perception well and produces good retrieval performance.

More »»

2020

Sikha O. K., Dr. Soman K. P., and S. Kumar, S., “VMD-DMD coupled data-driven approach for visual saliency in noisy images”, vol. 79, no. 3, pp. 1951 - 1970, 2020.[Abstract]


Human visual system is endowed with an innate capability of distinguishing the salient regions of an image. It do so even in the presence of noise and other natural disturbances. Conventional8 computational saliency models in the literature assume that the input images are clean, though an explicit treatment of noise is missing. In this paper, we propose a coupled data-driven approach for estimating saliency map for a noisy input using Variational Mode Decomposition (VMD) and Dynamic Mode Decomposition(DMD. Variational Mode Decomposition (VMD) is a well received technique explored for denoising in the literature. VMD modes with high entropy (randomness) are removed and the residual modes are employed to generate a scalar valued saliency map. The proposed method is compared against seven state-of-the-art methods over a wide range of noise strengths. The submitted approach furnished comparable results with respect to state-of-the art methods for clean and noisy images in terms of various benchmark performance measures.

More »»

2018

Sikha O. K., S. Sachin Kumar, and Dr. Soman K. P., “Salient region detection and object segmentation in color images using dynamic mode decomposition”, Journal of Computational Science, vol. 25, pp. 351-366, 2018.[Abstract]


Estimation of visual saliency in images has become an important tool since it allows the processing of images without knowing the actual contents. In this paper we introduce a novel method to detect salient regions of an image using dynamic mode decomposition (DMD). The key idea is to utilize the analytical power of DMD, which is a powerful tool evolving in data science. The applicability of DMD in static image processing applications is made possible by developing a new way of image representation. The proposed algorithm utilizes color and luminance information to generate a full resolution saliency map. In order to model the non-linear behavior of human visual system we exploited the power of different color spaces including CIELab, YCbCr, YUV and RGB. The proposed method is computationally less expensive, simple and generates full resolution saliency maps. The effectiveness of the generated saliency map is evaluated and confirmed on three benchmark data sets across fourteen existing algorithms based on the standard performance measures such as F-measure, precision and recall curve, mean absolute error (MAE), area under ROC curve (AUC-Borji), normalized scanpath saliency (NSS) and Pearson's correlation coefficient (CC). We also propose a saliency driven transition region [SDTR] based segmentation to segment the salient object from images.

More »»

2015

Suchithra M. and Sikha O. K., “Accelerating the performance of secret sharing algorithm using GPU”, International Journal of Applied Engineering Research, vol. 10, pp. 2921-2925, 2015.[Abstract]


The speed of the computer system is getting down as the complexity of the technology grows. Nowadays the popularity of GPU is getting increased and played an important role to accelerate the performance of the computer system. It maintains the computational efficiency and flexibility effectively compared to the CPU systems. In this work, we exploit the fundamental visual cryptographic algorithm by utilizing the computational power of GPU. Here we focus the parallel implementation of basic (2,2) visual cryptographic and compare the efficiency of execution with traditional CPU system.. This paper mainly emphasizes the strength of GPU. © Research India Publications.

More »»

2014

P. Prabha, Sikha O. K., Suchithra M., and Dr. Soman K. P., “Accelerating the performance of DES on GPU and a visualization tool in Microsoft Excel Spreadsheet”, Advances in Intelligent Systems and Computing, vol. 246, pp. 405-411, 2014.[Abstract]


Graphic processing units (GPU) have attained a greater dimension based on their computational efficiency and flexibility compared to that of classical CPU systems. By utilizing the parallel execution capability of GPU, traditional CPU systems can handle complex computations effectively. In this work, we exploit the parallel structure of GPU and provide an improved parallel implementation for data encryption standard (DES), one of the famous symmetric key cryptosystems. We also developed a visualization tool for DES in Microsoft Excel Spreadsheet which helps the students to understand the primitive operations that constitute the DES cryptosystem clearly. The main objective of this work is to investigate the strength of parallel implementation, on the basis of execution time on GPU as well as on CPU systems. © Springer India 2014. More »»

Publication Type: Conference Proceedings

Year of Publication Title

2020

N. Ratakonda, Kondaveeti, N., Alla, A., and Sikha O. K., “Salient Edge(s) and Region(s) Extraction for RGB-D Image”, Intelligent Computing and Communication, vol. 1034. Springer Singapore, Singapore, pp. 269-279, 2020.[Abstract]


In human visual systems, detection of the salient region plays an important role, as it ensures effective allocation of resources and fast processing. Though depth is an essential cue for visual saliency, it has not been well explored. This introduces a salient edge-based, region extraction model for RGB-D images. Most of the computational saliency models, reported in, produce smooth saliency maps; however, the edge information is not preserved. This paper presents a simple framework for the detection of salient edges by the preservation of the edges with high saliency scores. The final saliency map is obtained by fusion of the generated salient edge map and the RGB saliency map. Experiments are conducted over the publicly available RGB-D-2 dataset. The stability of the proposed RGB-D saliency model was assessed against standard evaluation metrics such as precision, recall, F-measure, MAE, NSS and AUC scores.

More »»

2018

B. Sriram, Reddy, K. S. H., Kumar, S. S., and Sikha O. K., “An improved levelset method using saliency map as initial seed”, Proceedings of IEEE International Conference on Signal Processing and Communication, ICSPC 2017, vol. 2018-January. Institute of Electrical and Electronics Engineers Inc., pp. 375-379, 2018.[Abstract]


Image segmentation is a challenging task in computer vision and image understanding, which partitions an input image in to several segments. Segmentation techniques try to detect objects from the background by exploiting image features such as texture, intensity, color etc. This paper introduces an enhanced Level set based method for segmentation using the saliency map as the initialization. A high quality saliency map is generated by combining the maps from HDCT and MB algorithms, the resultant saliency map is then given to the Level set module for segmentation. The effectiveness of the saliency based level set method against normal level set segmentation is evaluated and confirmed on MSRA dataset based on standard performance measures such as Miss Classification Error, FPR, FNR, TPR, accuracy and precision. © 2017 IEEE.

More »»

2016

G. Mohan and Sikha O. K., “Completely Separable Reversible Data Hiding with Increased Embedding Capacity Using Residue Number System”, Proceedings of the Second International Conference on Computer and Communication Technologies. Advances in Intelligent Systems and Computing, vol. 380. Springer India, 2016.[Abstract]


Separable reversible data hiding techniques facilitate hiding and extraction of data in the encrypted domain. This paper proposes a novel method to embed binary data in an encrypted cover image that provides complete independence of data extraction and covers image recovery. This allows the content owner to retrieve the host signal without any distortion regardless of the embedded data and the data hider to perform lossless extraction of embedded message. The method also provides a high data-embedding capacity using Residue number system (RNS) technique and ensures that only an authorized person can access the contents of the plain image.

More »»

2016

S. T. Reddy, Lakshmi, D., Deepthi, C., and Sikha O. K., “USB_SEC: A secure application to manage removable media”, 10th International Conference on Intelligent Systems and Control (ISCO). pp. 1-4, 2016.[Abstract]


Nowadays securing data has become a prime concern for educational institutes, workplaces etc. USB drives are now largely used for storing and transferring data due to its large capacity at nominal cost, high-transferring rate and portability. These drives are not only used to store data but they also have the ability to run software programs and boot the operating systems. Besides several advantages, USB drives are being misused for stealing data and injecting viruses, Trojans and malicious software into the system. With the invent of U3 technology, which runs based on the auto-run facility of the operating system it has become possible to copy data without the owner's knowledge. This paper provides a solution to safeguard from data-thefts without using physical methods like using superglue to block the USB ports, without altering the registry values and without using Bios method.

More »»

2015

Suchithra M. and Sikha O. K., “A Novel Image Encryption Scheme Using an Irrevocable Multimodal Biometric Key”, Security in Computing and Communications. Springer International Publishing, Cham, 2015.[Abstract]


In today's digital world the use of secret key is inevitable to any secure communication through the network. But human beings feel hard to recollect the lengthy cryptographic key. One solution to this would be the use of biometric characteristics of human beings which are unique in nature, that makes the attacker difficult to guess the key generated from these features. Here we propose a new scheme for multimodal biometric key generation to secure cryptographic communication. Initially, the feature points of fingerprint and iris image are extracted using SLGS feature extraction algorithm followed by which chaotic mechanism is applied to shuffle the feature vectors and finally fused them to produce a single biometric key. In this paper we also present a new image encryption technique using the multimodal biometric key, where we are able to reconstruct the secret image without any pixel quality loss. More »»

2013

Suchithra M., Sukanya, P., Prabha, P., Sikha O. K., Sowmya, and Dr. Soman K. P., “An experimental study on application of orthogonal matching pursuit algorithm for image denoising”, 2013 IEEE International Multi Conference on Automation, Computing, Control, Communication and Compressed Sensing, iMac4s 2013. IEEE, Kochi, Kerala, pp. 729-736, 2013.[Abstract]


Signal or image reconstruction has now become a common task in many applications. According to linear algebra perspective, the number of measurements made or the number of samples taken for reconstruction must be greater than or equal to the dimension of signal or image. Also reconstruction follows the Shanon's sampling theorem which is based on the Nyquist sampling rate. The reconstruction of a signal or image using the principle of compressed sensing is an exception which makes use of only few number of samples which is below the sampling limit. Compressive sensing also known as sparse recovery aims to provide a better data acquisition and reduces computational complexities that occur while solving problems. The main goal of this paper is to provide clear and easy way to understand one of the compressed sensing greedy algorithm called Orthogonal Matching Pursuit (OMP). The OMP algorithm involves the concept of overcomplete dictionary that is formulated based on different thresholding methods. The proposed method gives the simplified approach for image denoising by using OMP only. The experiment is performed on few standard image data set simulated with different types of noises such as Gaussian noise, salt and pepper noise, exponential noise and Poisson noise. The performance of the proposed method is evaluated based on the image quality metric, Peak Signal-to-Noise Ratio (PSNR). © 2013 IEEE.

More »»

2013

P. Sukanya, Suchithra M., Sikha O. K., Prabha, P., and Dr. Soman K. P., “Understanding CDMA in linear algebra point of view and its simulation in Excel”, Proceedings - 2013 IEEE International Multi Conference on Automation, Computing, Control, Communication and Compressed Sensing, iMac4s 2013. Kerala, pp. 78-83, 2013.[Abstract]


Code Division Multiple Access (CDMA) is one of the famous channel access method, mainly used in radio communication technologies. Unfortunately this concept is less understood by the student community due to the lack of understanding the mathematical rules behind it. This paper is intended to provide a linear algebra point of explanation of the concepts behind CDMA. The CDMA concept which was otherwise analyzed in spectral point of view is explained using the orthogonality of the bases. The Microsoft Excel Spread Sheet is used as an aid for the simulation since every one can go deep in to the basic concepts. © 2013 IEEE.

More »»

2012

R. Anand, Prabha, P., Sikha O. K., Suchithra M., Dr. Soman K. P., and Sowmya, “Visualization of OFDM using Microsoft Excel spreadsheet in Linear Algebra Perspective”, International Conference on Advances in Computing and Communications, ICACC 2012. IEEE, Kochi, Kerala, pp. 58-64, 2012.[Abstract]


Orthogonal Frequency Division Multiplexing (OFDM) is one of the leading technology that is ruling the communication field. But unfortunately, it is shrouded in mystery. A good knowledge in Linear Algebra is required to appreciate the technology in a better way. So the work focuses on explaining OFDM system from linear algebra point of view. Also, OFDM model communication system is simulated using Excel which makes ease for anyone experiment with OFDM and understand the underlying principle. The paper aims to provide strong foundation on the concept behind OFDM without the need of having much knowledge in electronics field. © 2012 IEEE.

More »»

2012

P. Prabha, Sikha O. K., Suchithra M., Sukanya, P., Sowmya, and Dr. Soman K. P., “Computation of continuous wavelet transform using microsoft excel spreadsheet”, Proceedings - 2012 International Conference on Advances in Computing and Communications, ICACC 2012. IEEE, Kochi, Kerala, pp. 73-77, 2012.[Abstract]


Wavelet theory has become an essential and significant tool for signal and image processing applied in the analysis of various real time signals. It is thus necessary to include wavelet transform and its application in multifractal analysis as a part of the engineering curriculum. In this paper, we present simple and effective way of computing Continuous Wavelet Transform (CWT) using Microsoft Excel Spreadsheet which serves as an user friendly mathematical tool for beginners. The motivation of this paper is to prove the computational power of excel, using which students can have better understanding of the basic concept behind the computation of Continuous Wavelet Transform. The plot of Continuous Wavelet Transform of Brownian signal computation in Excel is compared with that of the result in the Matlab Toolbox. The singularities present in the signal can be inferred from the wavelet modulus maxima plot. The visual interpretation proves that Excel tool provides computational power comparable to that of the Matlab software. The codes for the implementation of CWT in Excel are available on nlp.amrita.edu:8080/sisp/wavelet/cwt/cwt.xlsm, nlp.amrita.edu:8080/sisp/wavelet/cwt/modmax.xlsm, nlp.amrita.edu:8080/sisp/ wavelet/cwt/thermo.xlsm © 2012 IEEE.

More »»