Real time vision-based implementation of plant disease identification system on FPGA
Plant diseases have turned into a dilemma as it can cause significant reduction in both quality and quantity of agricultural products. To overcome that loss, we implemented a computer vision based real time system that can identify the type of plant diseases. Computer vision-based applications are computationally intensive and time consuming, so FPGA-based implementation is proposed to have a real time identification of plant diseases. In this paper an image processing algorithm is proposed for identifying two types of disease in Potato leaves. The proposed algorithm works well on images taken under different luminance conditions. The hardware/software-based implementation of the proposed algorithm is done on Xilinx ZYNQ SoC FPGA. Results show that our proposed algorithm achieves an accuracy of up to 90%, whereas the hardware implementation takes 0.095 seconds achieving a performance gain of 76.8 times as compared to the software implementation.