FPGA BASED IMPLEMENTATION OF DIGIT RECOGNITION
Under Supervision of :
Dr. Pavan Chakaraborty.
Table of Contents
About platforms used: 4
Xilinx ISE: 4
Web Edition: 4
MATLAB: [matlab] 4
Feature extraction: 5
Algorithm speed up using FPGA implementation: 6
[parallization abitlity of NN] 6
Result: [Verilog outputs] 4
About platforms used:
“Xilinx ISE[xilinx] (Integrated Software Environment) is a software tool produced by Xilinx for synthesis and analysis of HDL designs, enabling the developer to synthesize ("compile") their designs, perform timing analysis, examine RTL diagrams, simulate a design 's reaction to…show more content… More than a million engineers and scientists in industry and academia use MATLAB, the language of technical computing. ”
The method of feature extraction is based on the spatial distribution of the black and white pixels in the image space. We are assuming that the difference of distribution of pixels for each digit are sufficient enough to classify them. All of extracted features are integer and could be implemented with only add and subtract operation on FPGA .
We divide the image into multiple horizontal and vertical sections and the analysis of accuracies can be done using this table.
[insert the table of trade off]
It can be observed that as we are increasing the number of sections, the accuracy is also increasing. Taking consideration of efficient use of hardware resources four horizontal and four vertical sections can be chosen safely.
[figure showing 8 blocks]
To count the number of pixels in each section 8 binary ripple Algorithm speed up using FPGA implementation:
[parallization abitlity of NN] Conclusion
For the implementation