Title :
Neural networks applications for multimedia processing
Author :
Bojkovic, Zoran ; Milovanovic, Dragorad ; Mastorakis, Nikos
Author_Institution :
Fac. of Electr. Eng., Belgrade Univ., Serbia
Abstract :
Adaptive neural networks (NN) technologies present a unified solution to a broad spectrum of multimedia applications. In this paper we pointed out that current research frontier of multimedia signal processing is shifting from coding (MPEG-1,2,4) to automatic recognition (MPEG-7). Its research domain will cover techniques for object-based representation/coding, segmentation/tracking, pattern detection/recognition, multimodal signals fusion/conversion/synchronization, as well as content-based indexing and subject-based retrieval/browsing. Also, we reported successfully applications of NN for compression, denoising, contrast enhancement, snakes model segmentation/visualization, audio-to-video conversion and content-based processing/indexing/retrieval
Keywords :
adaptive systems; information science; multimedia computing; neural nets; pattern recognition; signal processing; MPEG-7; NN; adaptive neural networks applications; audio-to-video conversion; content-based indexing; content-based retrieval; contrast enhancement; denoising; multimedia processing; multimedia signal processing; multimodal signal conversion; multimodal signal fusion; multimodal signal synchronization; object-based coding; object-based representation; pattern detection; pattern recognition; segmentation; signal compression; snakes model segmentation; snakes model segmentation/visualization; subject-based retrieval; tracking; Adaptive signal processing; Adaptive systems; Content based retrieval; Indexing; MPEG 7 Standard; Neural networks; Noise reduction; Pattern recognition; Transform coding; Visualization;
Conference_Titel :
Neural Network Applications in Electrical Engineering, 2000. NEUREL 2000. Proceedings of the 5th Seminar on
Conference_Location :
Belgrade
Print_ISBN :
0-7803-5512-1
DOI :
10.1109/NEUREL.2000.902390
