The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON INFORMATION SCIENCE AND APPLICATIONS
Transactions ID Number: 53-773
Full Name: Parthasarathy Subashini
Position: Associate Professor
Age: ON
Sex: Female
Address: Dept. of Computer Science, Avinashilingam University for Women, Coimbatore
Country: INDIA
Tel: 0422-2440241
Tel prefix: 0422
Fax: 0422-2438381
E-mail address: mail.p.subashini@gmail.com
Other E-mails:
Title of the Paper: Optimization of image processing techniques using Neural Networks â€" A Review
Authors as they appear in the Paper: Dr.P.Subashini, Mrs. P.T.Bharathi
Email addresses of all the authors: mail.p.subashini@gmail.com, bharathi2028@gmail.com
Number of paper pages: 23
Abstract: We have studied around 50 papers on the applications of neural networks in image processing. Neural networks, especially uses feed-forward neural networks, Kohonen feature maps, back-propagation neural networks, multi-layer perception neural networks and Hopfield neural networks. The various applications are categorized into a novel two-dimensional taxonomy. One dimension specifies the type of task performed by the algorithm, preprocessing, data reduction or feature extraction, segmentation, object recognition, image understanding and optimization. The other dimension captures the abstraction level of the input data processed by the algorithm that is pixel-level, local feature-level, structure-level, objectlevel, object-set-level and scene characterization. Each of the six types of tasks poses specific constraints to a neural-based approach. A synthesis is made of unresolved problems related to the application of pattern recognition techniques in image processing a!
nd specifically to the application of neural networks.
Keywords: Image preprocessing, Data reduction, Image Segmentation, Object recognition, Image understanding, Optimization, Neural Networks
EXTENSION of the file: .pdf
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress: Image processing, Neural networks, Pattern recognition
IP ADDRESS: 117.211.120.65
