Title :
Characterization of perceptual importance for object-based image segmentation
Author :
Wong, Hau-San ; Guan, Ling
Author_Institution :
Sch. of Electr. & Inf. Eng., Sydney Univ., NSW, Australia
Abstract :
We propose a machine learning approach for characterizing the perceptual importance of particular regions in an image. A modular neural network architecture is adopted for encoding our usual notion of a perceptually important region in such a way that generalization of this knowledge to previously unseen images is possible. Specifically, users are allowed to specify examples of perceptually significant regions in images, which are then incorporated as training data for the network. An important characteristic of this approach is its provision for grouping distinct regions into a single perceptually significant area through the previous user guidance, unlike conventional segmentation approaches which partition the image into homogeneous regions without further specifying the relationship between these regions
Keywords :
feedforward neural nets; image segmentation; learning (artificial intelligence); machine learning approach; modular neural network architecture; multilayer feedforward neural network; object-based image segmentation; perceptual importance characterization; perceptually significant regions; Australia; Cost function; Image coding; Image segmentation; MPEG 4 Standard; MPEG 7 Standard; Machine learning; Neural networks; Training data; Video sequences;
Conference_Titel :
Image Processing, 2000. Proceedings. 2000 International Conference on
Conference_Location :
Vancouver, BC
Print_ISBN :
0-7803-6297-7
DOI :
10.1109/ICIP.2000.899287