Download presentation
Presentation is loading. Please wait.
Published byBarnard Dawson Modified over 8 years ago
1
Digit Recognition Using SIS Testbed Mengjie Mao
2
Overview Cycle 1: sequential component AAM training Cycle 2: sequential components Identifier 0 Ten perfect digit image for training Randomly generated digit images with defects for testing Identifier 9 Ten weight matrixes for next cycle ……
3
Cycle 1: AAM training Training input Hand-written pixel images for digit 0~9, the size is 20x15 Implement a tool outside Testbed to extract the pixel data, by which a image can be represented by a binary matrix with size 20x15(1 for black, 0 for white) Training output Ten weight matrixes, each of which is for one digit Algorithm Hopfield network Give up the MNIST dataset
4
Cycle 2: Testing Testing input Randomly generate the digit images with defect pixels (black white) Testing procedure Each digit identifier initializes its owe weight matrix which is output from cycle 1 All identifier take a defected image as input The best identifier is the one which converges fastest
5
Demo & Conclusion With 1 defect pixel With 15 defect pixels With 45 defect pixels The digit recognition prototype can be used for any recognition tasks: face, car, fingerprint…… Using parallel components in cycle 2 is more preferable
6
Acknowledgment Thanks for Prof. Chang’s lecture and consultancy Thanks for Haifeng Xu and Angen Zheng, for their helps on the Java program
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.