【Project source code】Implementation of digital recognition based on FPGA

小梅哥

【Project source code】Implementation of digital recognition based on FPGA [Copy link]

 

Implementation of digital recognition based on FPGA
1 Implementation of digital recognition based on digital feature algorithm
We use an algorithm based on digital features to recognize numbers. We collect images through the image acquisition module, grayscale and binarize them, and then extract and count digital features to complete the recognition of numbers. Finally, they are displayed on the digital tube to complete the conversion of image information to digital information.

The extraction of digital feature information is based on the printed text, as shown in Figure 1 above. Taking the number 5 in Figure 1 as an example, the red box is the horizontal and vertical upper, lower, left, and right boundaries of the number 5. X1 is a horizontal line at 2/5 of the vertical direction, x2 is a horizontal line at 2/3 of the vertical direction, and y is a horizontal line at 1/2 of the horizontal direction. We use this feature to count the intersections of x1, x2, y and the number 5.
The features of distinguishing the numbers 0-9 by the cross-statistic method are shown in Table 1 below:

In this way, the numbers 0-9 can be completely distinguished by digital statistics. Then the real-time digital recognition system is built using the FPGA system.
2 Implementation of digital recognition based on FPGA

As shown in Figure 2, we use the ov5640 cmos 500W pixel camera for image acquisition. The collected color RGB image is first stored in SDRAM, and then the image data is read out by the TFT display control terminal. After reading the RGB image data, we first perform the RGB to YCbcr algorithm operation, and then perform threshold segmentation on the grayscale image to form a binary image. Digital recognition is performed on the basis of boundary tracking of the binary digital image, and finally the boundary is displayed on the TFT5-inch screen, and the recognized digital information is displayed on the digital tube.
Digital recognition x1, x2, y core code:

Results:

Outlook: Recognition based on machine vision is the inevitable path to artificial intelligence, and character recognition is the stepping stone to this path. The results of this experiment have completed the correct recognition of the position of numbers on the screen regardless of their size. Based on this, we can develop face position recognition, face template matching recognition, license plate recognition and other popular machine vision and artificial intelligence.