A Contour-Based Feature Extraction Algorithm

Abstract

Human body recognition is a common problem in computer vision. Currently, most artificial intelligence methods are dependent on the scale of the extracted feature values from the target images during classification, thereby limiting the image size. However, in image recognition, the object’s contour alone is sufficient for humans to distinguish image content. This paper proposes a feature extraction algorithm based on image contours. By utilizing only the contour features of the target image and combining them with machine learning algorithms for classification, it achieves good results even on relatively complex images.