Smartphone image based digital chlorophyll meter to estimate the value of citrus leaves chlorophyll using Linear Regression, LMBP-ANN and SCGBP-ANN

Abstract

The chlorophyll of leaf can be determined using soil plant analysis development meter or spectrophometer by agriculture scientists, agriculture experts, and farmers. Usually, these methods are very costly and may not be available to all the farmers and experts. Low greenness of leaf indicates low photosynthesis in the plant and it creates many problems in the plant. This paper forwards a low-cost smartphone image-based digital chlorophyll meter to predict the chlorophyll of citrus leaf. The chlorophyll of citrus leaf is predicted using Linear Regression (LR) and Artificial Neural Network (ANN). Here, ANN provides more accuracy as compared to LR in citrus chlorophyll prediction. Both methods are validated with the actual chlorophyll of the citrus leaf. The proposed method can be used as a reasonable method for chlorophyll prediction of citrus.

Keywords

• Chlorophyll
• Linear Regression
• ANN
• Image processing
• Spectrophotometer
• SPAD