FPGA Based Leaf Chlorophyll estimating regression model

Abstract

Architecture of simple, portable, low cost Chlorophyll estimator based on Field Programmable Gate Array (FPGA) is proposed in this paper. Color of leaf can give an indication for assessment of plant health and nutrient. Performance analysis of several regression model shows that multivariate linear regression model with nonlinear terms provides best fit between estimated Chlorophyll values with image data. We find that the residuals are near in baseline and the adjusted coefficient of determination (Raa2 is 0.99 which is very significant. Root mean square error (RMSE) is 3.3 out of 15 leaf image samples with 5 error degrees of freedom (EDF). Hardware architecture is designed as best regression model has less computational complexity and greater accuracy.