The computation results show that this method may not only keep the characteristics of the image edge,but also obtain the clearer image of pests in stored grain to pick up the image characteristics of pest in stored grain effectively.

Based on wavelet transformation,the image of pests in stored grain based on machine vision is decomposed in various scales.

Generally, a digital image may consist of several different objects, and the research interest for an insect image is the insect region in the image.

Insect image processing and analysis technology and methods including image acquisition, image enhancement , image segmentation and feature extraction and measurement were introduced.

Based on analyzing the pictures,this research uses iterative threshold method to obtain the threshold of grain insect in order to solve the problem how to obtain the optimal threshold in online detecting and controlling system of grain storage in this paper.