Wavelet Based Multi-Spectral Image Analysis of Corn Leaf Chlorophyll Content

Abstract

With recent advancement in precision farming, the need for variable rate technology has become apparent. Variable rate technology can improve the efficiency of farm operations and lessen the environmental impact farms have. To implement effective variable rate applications, it is essential to gather and process information on crop nitrogen level reliably. This research intended to develop an image processing method to assess corn nitrogen level based multi-spectral images of corn plant. This method first removes unnecessary information from the image and then converts the image into a one-dimensional (1-D) signal representing the reflectance of the corn plant across leaves. The obtained data is further processed using wavelet transform to find specific features that correspond to corn nitrogen stress. To implement wavelet analysis, the 1-D signal was deconstructed into some packets of narrows frequency bands to find the lowest level approximations at different levels. The maximum wavelet coefficients were identified for interested signal bands and then compared to SPAD meter readings which were used as the ground-truth corn nitrogen level. Analysis results indicated that the db4 wavelet at a level 8 deconstruction had the highest linear regression coefficient (R2 = 0.78) with a high correlation coefficient (r = 0.88) for corn nitrogen levels.