Title :
Orientation Detection and Attention Selection based Unit-linking PCNN
Author :
Gu, Xiaodong ; Zhang, Liming
Author_Institution :
Dept. of Electron. Eng., Fudan Univ., Shanghai
Abstract :
A new model of orientation detection and attention selection based on unit-linking PCNN (pulse coupled neural network), which is a kind of spiking neural network exhibiting synchronous pulse bursts and has biological support, is introduced. This new model, including two layers (the orientation detection layer and the attention selection layer), mimics orientation detection of the biological visual cortex, and realizes attention selection with TOP-DOWN mechanism by the periodical oscillation of the contour of the interesting object. In the attention selection layer, the chain code of the interesting object contour is used to express the prior knowledge
Keywords :
neural nets; object detection; attention selection; orientation detection; pulse coupled neural network; spiking neural network; synchronous pulse bursts; unit-linking PCNN; Biological information theory; Biological system modeling; Brain modeling; Image edge detection; Image processing; Joining processes; Neural networks; Neurons; Object detection; Personal communication networks;
Conference_Titel :
Neural Networks and Brain, 2005. ICNN&B '05. International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-9422-4
DOI :
10.1109/ICNNB.2005.1614877