Quality assessment of leaves quality using texture and DWT based local feature extraction analysis

Abstract

The economy of any country depends highly on agriculture productivity, and plant leave disease detection plays an important role in this field. If plant leaves disease is not detected timely then it degrades both the quality and quantity of plants. Therefore, precise and timely detection of disease is one of the major challenges in terms of agricultural productivity. The traditional manual systems of disease detection are inconsistent, laborious, costly, and subjective. To overcome the limitations of the manual system, a lot of smart technologies have been proposed by researchers for the automatic detection of leave disease. In this letter, we are proposing a computer vision-based technique to detect plant leave disease using a combination of two feature extraction algorithm. In the first stage, features are extracted using a discrete wavelet transform with different orientations of the Gabor filter. Histogram binning pattern is then used in the second stage. Finally, a combination of extracted features is given to the Gaussian classifier for final prediction. The proposed system gives promising results with an accuracy of 98.45%, 96.45%, 99.85%, 99.83, and 99.75% on different data sets.