Title :
A neural network extracting road segments from maps using necessary and sufficient features
Author :
Kim, Wookhyun ; Hirai, Yuzo ; Furukawa, Takashi ; Arita, Hidenobu
Author_Institution :
Tsukuba Univ., Ibaraki, Japan
Abstract :
A feature-extracting neural network system which integrates the necessary- and sufficient-feature networks is proposed and applied to the extraction of road segments from maps. The system extends incomplete road segments of the necessary-feature network by following the complete information contained in the output of the sufficient-feature network. It is shown that the system can extract road segments from various areas of maps successfully. The necessary- and sufficient-feature system architecture can be applied to a wide range of image processing problems. The system is applied to 1/25000 scale maps
Keywords :
cartography; computerised picture processing; neural nets; image processing problems; necessary-feature network; neural network; road segments; sufficient-feature network; system architecture; Data mining; Feature extraction; Filtering; Image processing; Image segmentation; Laboratories; Neural networks; Research and development; Roads; Steel;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170476
