PROJECT TITLE :

An Adaptive and Robust Edge Detection Method Based on Edge Proportion Statistics

ABSTRACT:

One of the most important preprocessing steps for high-level tasks in the field of image analysis and computer vision is edge detection. Because each image is unique, it is impossible to give a universal threshold that works for all photographs. This study proposes a real-time edge detector that is adaptive, robust, and effective. The images can be divided into three categories using 2D entropy and assigned a reference % based on edge proportion data for each category. Anchor points were more likely to be edge pixels than attached points in the gradient direction. Each of these points was then connected to another edge segment, each of which was a clean, contiguous, 1-pixel wide chain of pixels. The proposed edge detector outperforms traditional edge following methods in terms of detection accuracy, according to the findings of the experiments. It's also possible to use the real-time detection findings as input information for applications such as post-processing.