Digital image processing (2nd ed.)
Digital image processing (2nd ed.)
Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations
A scrubbing technique for the automatic detection of victims in urban search and rescue video
Proceedings of the 6th International Wireless Communications and Mobile Computing Conference
A suitable neural network to detect textile defects
ICONIP'06 Proceedings of the 13th international conference on Neural Information Processing - Volume Part II
| Hi-index | 0.00 |
This paper addresses the use of a multi-layer fully-connected perceptron neural network for implementing a pattern recognizer. The input of the neural network is a set of seven standardized invariant moments in both the training procedure and recognition procedure. This standardization results in significantly increasing the accuracy of recognition. The neural network in this paper can recognize the shape of patterns regardless of the size, location or brightness. Images are captured and transformed to binary images through a global threshold technique. The weights of the network are computed using the back propagation algorithm. An example is given to demonstrate this neural network pattern recognizer.