Identification of Stem Borer Attack in Rice Crop using Fuzzy Inference System

Abstract

Stem borer, bores into rice plant stems. This is any insect larva. Stem borers can destroy rice at any stage of the plant from seedling to maturity. Excessive boring through the sheath can destroy the crop. Its damage can reduce the number of reproductive tillers. At late infection, plants develop whiteheads. Visual inspection has been done in rice crop for dead hearts in the vegetative stages and whiteheads in reproductive stages to confirm stem borer damage. In present day applications, visual inspection can be done by doing automation of the process to interprets and analyze the information by using various kinds of images and pictures as source of information. The fuzzy set theory is incorporated to handle uncertainties and fuzzy clustering is a powerful method of data mining. FIS is an expert system to approximate input-output mapping according to defined rules. In this proposed approach, whiteheads image of rice crop, caused by stem borer, captured by digital camera. In preprocessing steps, image cropping and image segmentation has been performed with captured images. After that, 24 features of normal and whiteheads rice crop images has been extracted. On the basis of this extracted feature, Mamdani fuzzy models has been implemented, to automate the process, to identify whiteheads caused by stemborer in mid of normal rice crop.

Keywords: Stem Borer, Whiteheads Rice Crop Image, Image Acquisition, Image Segmentation, Fuzzy Inference System

View PDF