Edge detection and target recognition from complex background

Based on the analysis of traditional edge detection operator of mathematical morphology, a multi-structuring elements edge detection operator of mathematical morphology is proposed. According to the geometric feature of targets, the multi-structuring elements are selected to match image details, which could suppress noise as much as possible while preserving fine details. Threshold acquired by weighted average of gray levels is used to binarize the image, which has a better effect for improving image edge. Several expressions about shape are analyzed in the paper. According to the character of target, the characters of edge pixels, complexity and aspect ratio of minimum enclosing rectangle are obtained. The overall fuzzy evaluating technique is studied, and three types targets are recognize by overall fuzzy evaluating technique through calculating the character evaluating function and membership degree function, and the target needed to be analyzed was recognized in the complex background. Both theoretical and experimental researches are taken in the paper. The results of simulation experiments demonstrate that the proposed method could suppress noise effectively and extract target edge from complex background efficiently, and the target in complex background could be detected reliably by overall fuzzy evaluating technique.