Crop Identification for Automated Processing, Systems with Wavelet Packet Analysis and Weighted, Bayes Distance

This study proposes a novel approach for crop identification by using wavelet packet transform combined with weighted Bayes distance based on crop texture and leaf features. Automatic processing in agriculture requires accurate identification of crops to target plants for treatment according to their needs. Wavelet analysis, featuring spatial/frequency localization, data compression, denoising, data analysis/data mining, etc., is a good candidate for identifying crops. However, if the energy of wavelet packet coefficients is the sole identifying characteristic, results may vary significantly depending on different factors such as weather, plant density, growth stage, and sunlight, etc. To overcome these variations, the weighted Bayes distance is introduced for an identification criterion, also referred to as the decision distance, where the weighting is based on the statistic of crop texture and leaves´ shapes. By utilizing the decision distance under different climates within three consecutive days of photography, the crop identification can achieve an accuracy of 94.63%