Rajkumar Kannan

Bishop Heber College(Autonomous), Data Science, Department Chair

King Faisal University, Computer Science, Associate Professor

Followers

Following

Co-authors

Public Views

Rajkumar is the Dean - International Relations, Professor and Head of Department of Data Science, Professor and Head of Department of Computer Science(Shift-I), Bishop Heber College (Auto), India. Previously Rajkumar worked for King Faisal University, Al Hasa, Saudi Arabia, in the Faculty of Computer Sciences and Information Technology where he taught ABET(USA) accredited BS and MS programmes.Awarded a PhD by National Institute of Technology Tiruchirappalli in 2007, he has published several papers related to Social Multimedia Retrieval. Rajkumar visited many countries including UK, USA, Germany, Japan, Slovakia, Thailand, Austria, Malaysia, Indonesia and all Gulf countries in pursuance of teaching and research activities. He is the author of a widely followed book, Java Programming, published by Pearson and edited books for Springer LNCS and IGI. Rajkumar also serves as an editorial member to many international journals and conferences and is a senior member of ACM and a life-time member of CSI and ISTE. His research primarily lies at the confluence of Information Retrieval, Multimedia Semantics, Data Science and Collaborative
Phone: 96635898138
Address: Department of Information Systems
College of Computer Science and IT
King Faisal University, Ah Hassa
Saudi Arabia

less

InterestsView All (8)

Uploads

Papers by Rajkumar Kannan

A State-of-the art Review: A survey on Multimedia Tagging Techniques

by Dr.(Mrs.)Kirubai D Computer Science-Aided and Rajkumar Kannan

International Journal of Scientific Research in Science and Technology, 2018

Social media prevails in every walk of our life. Multimedia shared through social networks has tr... more Social media prevails in every walk of our life. Multimedia shared through social networks has tremendously increased the need for efficient retrieval methods and expects more accuracy in terms of annotating an existing image or video. Retrieval methods and annotation techniques are two sides in the development of an efficient multimedia retrieval system. Annotating the image and video is a challenging task. Collaborative user annotations can be incorporated into multimedia to increase the efficiency and accuracy in the retrieval methods. Collaborative user annotations are useful for two reasons: (i) Multi-label annotation for a multimedia is possible with less time-consuming even for large-scale image corpus (ii) Correlation between images and videos build a multi-class label propagation without much human effort and in reduced cost. There are many areas of research the collaborative annotations are incorporated with small modification in the existing machine learning algorithms. This survey paper presents the state-of-the-art annotation techniques for multimedia in the new era.

Download

Proceedings of the Second international conference on Data Engineering and Management

Taman Tasik Titiwangsa lakes are popular for water sport activity. Thus, it is important to keep ... more Taman Tasik Titiwangsa lakes are popular for water sport activity. Thus, it is important to keep the health of the lakes at an acceptable level for the optimum usage of water sport activity. The water quality index is used to assess the water quality condition of the lakes. Water quality index (WQI) and interim national water quality standards (INWQS) for Malaysia are used to monitor the health of the lakes. A total of two sample stations were collected at Lake 1 and Lake 2 of Taman Tasik Titiwangsa. Six selected parameters (biological oxygen demand, chemical oxygen demand, dissolved oxygen, pH, suspended solid and ammoniacal nitrogen) were used to calculate the water quality index. From the analysis, it showed that both Lake 1 and Lake 2 are Class II condition and visitors can use it for water sport activity. Several recommendations are noted to improve the WQI value for the use of Taman Tasik Titiwangsa visitors especially for water sport activity.

Download

International Workshop on Semantic and Social Media Adaptation and Personalization

The proceedings contain 12 papers. The topics discussed include: impact of covid-19 on education ... more The proceedings contain 12 papers. The topics discussed include: impact of covid-19 on education using twitter data;automating road junction identification using crowdsourcing and machine learning on gps transformed data;augmented and personalized digital narratives for cultural heritage under a tangible interface;issues and challenges associated with blockchain in smart cities;identifying dominant nodes in semantic taxonomies;correlation of biological and computer viruses through evolutionary game theory;and a system for collecting, managing, analyzing and sharing diverse, multi-faceted cultural heritage and tourism data.

Extracting Sentiments and Summarizing Health Reviews from Social Media Using Machine Learning Techniques

Transactions on Machine Learning and Artificial Intelligence, 2018

Most of the health organizations provide an array of medical services and request their beneficia... more Most of the health organizations provide an array of medical services and request their beneficiaries to provide their experience’s in the form of opinion/reviews for which they are associated. Doctors of national and international repute have hundreds and even thousands of reviews authored by the health consumers around the globe. For an individual it is difficult and time consuming process to look all the reviews before taking an appropriate decision. Thus it is necessary to summarize the reviews to make an individual to take prompt decision. For a doctor it is also difficult to keep track of patient’s reviews given by the patients in different time intervals, but he may have the summary of his entire patient’s reviews to understand what is the best can be done to the patient’s community. This research paper aims to mine and summarize the medical reviews authored by the health consumers. This article is performed by summarization of text in three steps, the first step is to identi...

CLRF: Compressed Local Retinal Features for image description

2015 Eighth International Conference on Advances in Pattern Recognition (ICAPR), 2015

ABSTRACT This paper presents a new methodology to extract discriminative features from images, th... more ABSTRACT This paper presents a new methodology to extract discriminative features from images, that are robust and invariant to image blur and JPEG compression. The local patches are quantized in the polar geometric structure using Log Polar Transformation (LPT). Then two-dimensional Discrete Wavelet Transformation (DWT) is used to decompose the polar structured patch into sub-bands. Each approximation sub-band of the wavelet decomposition is converted to vectors which are considered as features namely Compressed Local Retinal Features (CLRF). The proposed approach is comparatively evaluated with the state-of-the-art image descriptors on the standard Oxford dataset. The experimental results demonstrate the robustness of the proposed descriptor against image blur and JPEG compressions.

Features for Art Painting Classification Based on Vector Quantization of MPEG-7 Descriptors

Lecture Notes in Computer Science, 2012

An approach for extracting higher-level visual features for art painting classification based on ... more An approach for extracting higher-level visual features for art painting classification based on MPEG-7 descriptors is presented in this paper. The MPEG-7 descriptors give a good presentation of different types of visual features, but are complex structures. This prevents their direct use into standard classification algorithms and thus requires specific processing. Our approach consists of the following steps: (1) the images are tiled into non-overlapping rectangles to capture more detailed information; (2) the tiles of the images are clustered for each MPEG-7 descriptor; (3) vector quantization is used to assign a unique value to each tile, which corresponds to the number of the cluster where the tile belongs to, in order to reduce the dimensionality of the data. Finally, the significance of the attributes and the importance of the underlying MPEG-7 descriptors for class prediction in this domain are analyzed.

Download

Improving video summarization based on user preferences

2013 Fourth National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics (NCVPRIPG), 2013

ABSTRACT Although in the past, several automatic video summarization systems had been proposed to... more ABSTRACT Although in the past, several automatic video summarization systems had been proposed to generate video summary, a generic summary based only on low-level features will not satisfy every user. As users’ needs or preferences for the summary vastly differ for the same video, a unique personalized and customized video summarization system becomes an urgent need nowadays. To address this urgent need, this paper proposes a novel system for generating unique semantically meaningful video summaries for the same video, that are tailored to the preferences or interests of the users. The proposed system stitches video summary based on summary time span and top-ranked shots that are semantically relevant to the user’s preferences. The proposed summarization system is evaluated both quantitatively and subjectively. The experimental results on the performance of the proposed video summarization system are encouraging.

Deity face recognition using schur decomposition and hausdorff distance measure

2013 IEEE 56th International Midwest Symposium on Circuits and Systems (MWSCAS), 2013

ABSTRACT Face recognition in deity images is a challenging problem. Most of the existing face rec... more ABSTRACT Face recognition in deity images is a challenging problem. Most of the existing face recognition methods are very sensitive to pose and illumination changes. This paper proposes a new technique for deity face recognition which is suitable for pose and illumination changes. The proposed approach uses Schur decomposition to speedup PCA computations and doubly modified hausdorff distance for measuring similarity between different face edge maps. In addition, this paper introduces a new dataset (IDES) for face recognition which contains a collection of images of Indian Deities. Performances of the proposed method for deity face recognition are experimented with IDES dataset.The results show that the proposed method provides promising face recognition accuracy with pose and illumination changes.

Gradient-Orientation-Based PCA Subspace for Novel Face Recognition

IEEE Access, 2014

Face recognition is an interesting and a challenging problem that has been widely studied in the ... more Face recognition is an interesting and a challenging problem that has been widely studied in the field of pattern recognition and computer vision. It has many applications such as biometric authentication, video surveillance, and others. In the past decade, several methods for face recognition were proposed. However, these methods suffer from pose and illumination variations. In order to address these problems, this paper proposes a novel methodology to recognize the face images. Since image gradients are invariant to illumination and pose variations, the proposed approach uses gradient orientation to handle these effects. The Schur decomposition is used for matrix decomposition and then Schurvalues and Schurvectors are extracted for subspace projection. We call this subspace projection of face features as Schurfaces, which is numerically stable and have the ability of handling defective matrices. The Hausdorff distance is used with the nearest neighbor classifier to measure the similarity between different faces. Experiments are conducted with Yale face database and ORL face database. The results show that the proposed approach is highly discriminant and achieves a promising accuracy for face recognition than the state-of-the-art approaches.

Download

A novel user-centered design for personalized video summarization

2014 IEEE International Conference on Multimedia and Expo Workshops (ICMEW), 2014

In the past, several automatic video summarization systems had been proposed to generate video su... more In the past, several automatic video summarization systems had been proposed to generate video summary. However, a generic video summary that is generated based only on audio, visual and textual saliencies will not satisfy every user. This paper proposes a novel system for generating semantically meaningful personalized video summaries, which are tailored to the individual user's preferences over video semantics. Each video shot is represented using a semantic multinomial which is a vector of posterior semantic concept probabilities. The proposed system stitches video summary based on summary time span and top-ranked shots that are semantically relevant to the user's preferences. The proposed summarization system is evaluated using both quantitative and subjective evaluation metrics. The experimental results on the performance of the proposed video summarization system are encouraging.

Download

ESAS 2008 Workshop Committee

Atilla Elçi Internet Technology Research Center Dept. of Computer Engineering Eastern Mediterrane... more Atilla Elçi Internet Technology Research Center Dept. of Computer Engineering Eastern Mediterranean University Famagusta, North Cyprus, via Mersin 10, Turkey Atilla.Elci@emu.edu.tr ... Mamadou Tadiou Kone Dept. of Computer Science Faculty of Science and Engineering Laval University, Québec, Canada Kone.Mamadou@ift.ulaval.ca ... Mehmet A. Orgun Department of Computing Macquarie University Sydney, NSW 2109, Australia mehmet@comp.mq.edu.au ... Alia Abdelmoty, Cardiff University, UK Alex Abramovich, Gordon College, Israel Khalil ...

Salient Region Detection Using Patch Level and Region Level Image Abstractions

IEEE Signal Processing Letters, 2015

In this letter, a novel salient region detection approach is proposed. Firstly, color contrast cu... more In this letter, a novel salient region detection approach is proposed. Firstly, color contrast cue and color distribution cue are computed by exploiting patch level and region level image abstractions in a unified way, where these two cues are fused to compute an initial saliency map. A simple and computationally efficient adaptive saliency refinement approach is applied to suppress saliency of background noises, and to emphasize saliency of objects uniformly. Finally, the saliency map is computed by integrating the refined saliency map with center prior map. In order to compensate different needs in speed/accuracy tradeoff, three variants of the proposed approach are also presented in this letter. The experimental results on a large image dataset show that the proposed approach achieve the best performance over several state-of-the-art approaches.

Download

Digital library for mulsemedia content management

Proceedings of the International Conference on Management of Emergent Digital EcoSystems, MEDES'10, 2010

Abstract Digital Libraries are key infrastructure for document management. Until now, these docum... more Abstract Digital Libraries are key infrastructure for document management. Until now, these documents have included multimedia objects such video, images, text, sounds. In this paper, we focus on enhanced sensorial media content management in Digital Library. Enhanced sensorial media content combines the sense of touch with other media. All mulsemedia content management requires new methods, starting from the source through storage to delivery. Digital libraries have to use all modern technologies in order to supply services ...

Understanding honest feedbacks and opinions in academic environments

Compute 2011 - 4th Annual ACM Bangalore Conference, 2011

Abstract Student evaluation is an important component of any higher education. Online student fee... more Abstract Student evaluation is an important component of any higher education. Online student feedbacks and opinions have become increasingly popular means of gathering reviews and judging the quality of various services offered by an institution. This paper focuses on studying student behaviour while reporting their feedbacks. Particularly, we investigate the reliability of quantitative features through numerical ratings that students offer, by estimating the linguistic evidence from the free text that accompany the feature ...

Towards multimodal capture, annotation and semantic retrieval from performing arts

Communications in Computer and Information Science, 2011

A well-annotated dance media is an essential part of a nation's identity, transcending cultural a... more A well-annotated dance media is an essential part of a nation's identity, transcending cultural and language barriers. Many dance video archives suffer from tremendous problems concerning authoring and access, because of the multimodal nature of human communication and complex spatio-temporal relationships that exist between dancers. A multimodal dance document consists of video of dancers in space and time, their dance steps through gestures and emotions and accompanying song and music.This work presents the architecture of an annotation system capturing information directly through the use of sensors, comparing and interpreting them using a context and a user's model in order to annotate, index and access multimodal documents.

Download

Tutoring System for Dance Learning

arXiv preprint arXiv:1001.0440, Jan 4, 2010

Abstract: Recent advances in hardware sophistication related to graphics display, audio and video... more Abstract: Recent advances in hardware sophistication related to graphics display, audio and video devices made available a large number of multimedia and hypermedia applications. These multimedia applications need to store and retrieve the different forms of media like text, hypertext, graphics, still images, animations, audio and video. Dance is one of the important cultural forms of a nation and dance video is one such multimedia types. Archiving and retrieving the required semantics from these dance media collections is a crucial and ...

Download

The role of mulsemedia in digital content ecosystem design

Proceedings of the International Conference on Management of Emergent Digital EcoSystems, MEDES'10, 2010

Abstract Digital ecosystem is a self-organizing infrastructure for creating digital environment. ... more Abstract Digital ecosystem is a self-organizing infrastructure for creating digital environment. Similar to natural ecosystems, several digital ecosystems exist. This is due to differentiation and the development of native products and services tailored to specific local needs. Digital content is the core component of any digital ecosystem. As of now, most of the digital content focuses on only two senses. This paper highlights the significance of other senses which are to be incorporated in the creation of digital content to be used in the digital ecosystems.

ESAS 2008 Workshop Organization

by Atilla ELCI and Rajkumar Kannan

2008 32nd Annual IEEE International Computer Software and Applications Conference, 2008

Atilla Elçi Internet Technology Research Center Dept. of Computer Engineering Eastern Mediterrane... more

Modeling and Annotating the Expressive Semantics of Dance Videos

Dance videos are interesting and semantics-intensive. At the same time, they are the complex type... more Dance videos are interesting and semantics-intensive. At the same time, they are the complex type of videos compared to all other types such as sports, news and movie videos. In fact, dance video is the one which is less explored by the researchers across the globe. Dance videos exhibit rich semantics such as macro features and micro features and can be classified into several types. Hence, the conceptual modeling of the expressive semantics of the dance videos is very crucial and complex. This paper presents a generic Dance Video Semantics Model (DVSM) in order to represent the semantics of the dance videos at different granularity levels, identified by the components of the accompanying song. This model incorporates both syntactic and semantic features of the videos and introduces a new entity type called, Agent, to specify the micro features of the dance videos. The instantiations of the model are expressed as graphs. The model is implemented as a tool using J2SE and JMF to annot...

Download

Semantic Modeling and Retrieval of Dance Video Annotations

Dance video is one of the important types of narrative videos with semantic rich content. This pa... more Dance video is one of the important types of narrative videos with semantic rich content. This paper proposes a new meta model, Dance Video Content Model (DVCM) to represent the expressive semantics of the dance videos at multiple granularity levels. The DVCM is designed based on the concepts such as video, shot, segment, event and object, which are the components of MPEG-7 MDS. This paper introduces a new relationship type called Temporal Semantic Relationship to infer the semantic relationships between the dance video objects. Inverted file based index is created to reduce the search time of the dance queries. The effectiveness of containment queries using precision and recall is depicted. Keywords: Dance Video Annotations, Effectiveness Metrics, Metamodeling, Temporal Semantic Relationships.

Download

Rajkumar Kannan

Uploads

Papers by Rajkumar Kannan

Log In