Hand target extraction from infrared images with descriptor based on pixel temporal characteristics

An infrared trace image can record the trace left on the surface of objects after our body makes contacts with them, which is a special kind of blurred image with a transition zone. The traditional target extraction methods did not work well on a trace image. This paper presents a target extraction method using an edge-shape descriptor based on pixel temporal characteristics to extract the original contour from sequence infrared images. Firstly, divide all the pixels in the image into three sets. Then use gray level values of a certain pixel in the temporal sequence to describe the variety trend of the pixel and the Pearson correlation coefficient of two trends is used to represent the image feature of the point; Secondly, an edge-shape descriptor is used on the result of preliminary segmentation to judge which class a point belongs to. Finally in further processing, use morphological operation to smooth the edge and remove isolated points. The experimental results show that the extraction performance of the proposed method in this paper is better than that of the traditional target extraction methods.