 |
 |
*Call For Chapters* *Feature Dimension Reduction for Content-Based Image Identification* Please Visit: *http://www.igi-global.com/publish/call-for-papers/call-details/2770 <http://www.igi-global.com/publish/call-for-papers/call-details/2770>* Image data has portrayed immense potential as a resourceful foundation of information in current context for numerous applications including biomedicine, military, commerce, education, and Web image classification and searching. It has been considered as an important part of Big Data. Mass affinity to converse using images and graphics has been observed. Recently, broad applications of image identification have been recognized for autonomous vehicles. Hence, the domain is considered to be contemporary as well as of interest to the funding agencies for developing advanced applications in robotics and artificial intelligence in future. Researchers from assorted domain have shown consistent urge to explore the rich contents in image data and to design new techniques to exploit the usefullness of the images. Numerous methods for feature extraction from image data have been proposed by the scholars to facilitate timely identification of image data which can combat a terminal disease or a natural calamity. It is an essential component for achieving the sustainable development goals for our future generation and to make the earth a better place to live. The book is going to be based on contemporary trends and techniques in content based image recognition. The domain of research has been contemporary to recent trends in multimedia computing that have witnessed a surge in rapid growth in digital image collections. The publication will be about managing, archiving, maintaining and extracting information from these huge repositories. Two specific drawbacks have been observed in contemporary literatures regarding the dimension of feature vectors extracted from the images which in turn increase the time for convergence of classification and/or retrieval results. The aforesaid scenario can be threatening in real time. Late identification may result in delayed decision making for treatment of a terminal disease or to take remedial action against catastrophe. Therefore, the extracted features must be reduced in dimension to minimize time consumption for recognition of image data. Reduced feature size facilitates fusion of multiple features which allow rich exploration of image data. This also increases the classification rate which in turn enhances accuracy. On the other hand, smaller feature dimension decrease time consumption. Thus, the publication will propose innovative solutions to all the above mentioned problems and will offer new research directions. The publication will cover segmentation techniques for feature reduction, clustering techniques for feature reduction, early fusion of extracted features, late fusion of classification decision, supervised learning and unsupervised learning techniques. Researchers and practitioners are invited to submit on or before June 15, 2017, a 2-3 page chapter proposal clearly explaining the mission and concerns of his or her proposed chapter. Authors of accepted proposals will be notified by June 30, 2017 about the status of their proposals and sent chapter guidelines. Full chapters are expected to be submitted by September 30, 2017. All submitted chapters will be reviewed on a double-blind review basis. Contributors may also be requested to serve as reviewers for this project. *Proposal Submission* *June 15, 2017* *Full Chapter Due* September 30, 2017 *Submission Date* September 30, 2017 Contributors are welcome to submit chapters on the following topics: i) Image Segmentation for feature extraction ii) Image Segmentation for feature dimension reduction iii) Feature Dimension Reduction for multi technique fusion based image classification iv) Feature Dimension Reduction for multi technique fusion based image retrieval v) Early fusion techniques in content based image classification vi) Late fusion techniques in content based image retrieval vii) Clustering Techniques for content based feature extraction from images viii) Clustering techniques for feature dimension reduction ix) Supervised learning using unsupervised feature extraction For additional information regarding the publisher, please visit www.igi-global.com. *Inquiries and submissions can be forwarded electronically (Word document) or by mail to:* Prof. Rik Das Department of Information Technology, Xavier Institute of Social Service 7, Purulia Road, Ranchi, Jharkhand, Pin -834001, India Tel.: (0651)220 - 0873 E-mail: [log in to unmask] Best Regards *Rik Das* Assistant Professor, Dept. of Information Technology, XAVIER INSTITUTE OF SOCIAL SERVICE Ranchi, Jharkhand *Research Interests**:* Image Processing, Feature Extraction, Fusion Techniques, Image Classification, Image Retrieval *Research Profiles :* https://scholar.google.co.in/citations?user=cCO7ih8AAAAJ&hl=en http://www.researchgate.net/profile/Rik_Das