Title :
Recognition of printed sequential plural patterns using the 3-layered BP model with feedback connections
Author :
Imai, Katsuji ; Gouhara, Kazutoshi ; Uchikawa, Yoshiki
Author_Institution :
Toyota Motor Corp., Japan
Abstract :
The authors propose a method for recognizing printed sequential plural patterns using the three-layered backpropagation (BP) model with feedback connections. It enables segmentation and recognition concurrently independent of the order of the individual patterns. Segmentation and recognition are carried out concurrently by parallel distributed processing. Experiments involved recognizing original charge coupled device (CCD) camera images where stamped three-figured numerals were placed. These numerals were on very small electronic components. Experimental results show the recognition ability of the proposed method under the following three bad conditions in the original CCD camera images, i.e., when the numerals have lacked parts, blurred parts, or shaded parts, when two numerals next to each other are in contact, and when lumped noises are also included
Keywords :
backpropagation; image recognition; image segmentation; parallel processing; 3-layered BP model; feedback connections; parallel distributed processing; printed sequential plural patterns; recognition; segmentation; Charge coupled devices; Charge-coupled image sensors; Content addressable storage; Feedback; Image recognition; Image segmentation; Neural networks; Neurofeedback; Pattern recognition; Recurrent neural networks;
Conference_Titel :
Neural Networks, 1992. IJCNN., International Joint Conference on
Conference_Location :
Baltimore, MD
Print_ISBN :
0-7803-0559-0
DOI :
10.1109/IJCNN.1992.227061