Title :
Knowledge-based natural scene description
Author :
Loh, Horng-Hai ; Luo, Ren C.
Author_Institution :
Dept. of Electr. & Comput. Eng., North Carolina State Univ., Raleigh, NC, USA
fDate :
28 Oct-1 Nov 1991
Abstract :
The authors present a knowledge-based image description system that uses fractal features. A knowledge-based recognition process is incorporated in this natural scene description system to enhance the capability of natural scene understanding. The scene description system is based on a fractal model. The fractal model provides useful information. A set of fractal features was developed from the fractal model which can effectively be used in image segmentation. After an image is divided into many regions based on fractal features, the scene information is derived with a knowledge-based scene recognition process. The structure of this system and its interaction strategy for the extraction of scene description are presented. The experimental results are also discussed
Keywords :
computer vision; computerised pattern recognition; fractals; knowledge based systems; computer vision; feature extraction; fractal model; image description; image segmentation; knowledge-based scene recognition; natural scene description system; pattern recognition; Computer vision; Fractals; Geometry; Image analysis; Image recognition; Image segmentation; Intelligent robots; Intelligent systems; Layout; Shape;
Conference_Titel :
Industrial Electronics, Control and Instrumentation, 1991. Proceedings. IECON '91., 1991 International Conference on
Conference_Location :
Kobe
Print_ISBN :
0-87942-688-8
DOI :
10.1109/IECON.1991.239104