Image Analysis-based System for Estimating Cotton Leaf Area

Abstract

Leaf area is important for estimating biomass productivity, adaptation to the environment, nutrition, and soil-water relations. It also plays an important role in determining the proper application rates of insecticides and fungicides. Image processing is considered one of the best methods for estimating the leaf area of a plant as it is inexpensive and saves time. In the image processing method, leaf area is calculated through pixel number statistics by counting the number of pixels in the leaf area region of digital images. In this study, a simple system based on image analysis using the ImageJ software application was developed to estimate cotton leaf area. Two hundred and forty Egyptian cotton (Giza 86) leaves were captured using a digital camera. These leaves were collected randomly from different heights and different fields at Kafer El-Dawar center, El-Behera Governorate, Egypt. The results obtained using the proposed method was then compared with those obtained using the graphical method. There were only minor differences between both sets of results. The proposed method is feasible and practicable for estimating cotton leaf area as it has only a small overall average absolute relative error of 3.46% compared to the graphical method. Further, the proposed method is rapid, simple, and inexpensive.