Pest Detection on Leaf using Image Processing

A survey report showed that 70% Indian population depends on agriculture sector. Numerous heterogeneous diseases and various kind of pests affect the production of crops which leads to quality and quantitative loss. Automatic in-field pest detection using computer vision technique is an important topic in modern intelligent agriculture but suffers from serious challenges including complexity of wild environment, detection of tiny size pest and classification into multiple classes of pests. In the literature attention is mostly focused on machine learning based techniques and image processing has not received equal attention. This paper illustrates an automatic approach for pest detection using Wavelet transformation and Oriented FAST and rotated BRIEF (ORB). The core objective of the research is to enhance feature extraction phase to improve the detection efficiency. The proposed approach is implemented on images of fluffy caterpillar pests on mustard crop and fava bean collected from farms in Rajasthan. The experimental results affirm the efficiency of the proposed approach.