Designing an FPGA Synthesizable Computer Vision Algorithm to Detect the Greening of Potatoes
This addresses potato quality control for agricultural automation, but it is incremental as it applies existing methods to a specific domain.
The study designed a computer vision algorithm to grade potatoes based on surface greening by calculating the ratio of green pixels to total pixels, and synthesized it on an FPGA, achieving a thousand times speed improvement.
Potato quality control has improved in the last years thanks to automation techniques like machine vision, mainly making the classification task between different quality degrees faster, safer and less subjective. In our study we are going to design a computer vision algorithm for grading of potatoes according to the greening of the surface color of potato. The ratio of green pixels to the total number of pixels of the potato surface is found. The higher the ratio the worse is the potato. First the image is converted into serial data and then processing is done in RGB colour space. Green part of the potato is also shown by de-serializing the output. The same algorithm is then synthesized on FPGA and the result shows thousand times speed improvement in case of hardware synthesis.