A Novel Filtering Method for Infrared Image

摘要

The image filtering technology is widely used in many fields, such as environmental monitoring and assessment, space remote sensing, recognition and tracking of infrared target. In this paper, aiming at the problem of poor generalization capability and over-fitting with artificial neutral network for infrared image filtering, a new filtering method is presented. The structure elements are used to set up the training samples. And then, based on support vector machine theory, it builds the learning ma-chine with proper model and trains the samples. The result can be used to suppress the background SNR of following image. The experimental result with infrared image shows that the method can obtain higher SNR than conventional neutral network and fixed Top-Hat operator method, especially in low SNR.