Personnel trace extraction method

Abstract

The invention relates to a method for personnel trace extraction by utilizing image collecting and processing technology. The method mainly includes the steps of image collection, image registration, interested area creating, differential signal thresholding and ecological processing, wherein positioning detection and description of feature points are realized by utilizing a graphic local invariant feature extracting method during image registration; an interested area is created by utilizing a gradient field and a direction field of an integral image to determine trace texture and background image and then utilizing gray level; differential image thresholding refers to solving a maximum threshold value of the interested area through an OSTU algorithm and binarizing according to the maximum threshold value; ecological processing is performed finally. By the personnel trace extraction method, operation quantity can be reduced, and extraction accuracy can be improved; the personnel trace extraction method is suitable for various personnel traces, thereby being high in applicability.

Description

technical field [0001] The invention relates to an extraction method for extracting personnel traces by using image acquisition and processing technology. Background technique [0002] Personnel traces mainly refer to shoe sole trace patterns, barefoot trace patterns, fingerprints, and palm prints. They are image traces formed by people standing and walking in contact with the ground or other bearing surfaces. Patterns have also become an important physical evidence often used in criminal case investigations. [0003] At present, with the development of relevant research topics in my country's personnel trace extraction project, especially the extraction of trace texture images, colleagues engaged in trace inspection technology across the country have done a lot of summarization and research work. my country's trace inspection technology has initially formed its own system from basic theory to inspection methods. Whether it is the test object, test content, test method and...

AI Technical Summary

Problems solved by technology

[0005] However, for the above-mentioned personnel trace extraction scheme, it is still difficult to overcome the following shortcomings:

[0006] 1. The personnel trace texture extraction scheme has high requirements on lighting. Due to the feature requirement for the background to be weakened to the greatest extent, the requirements on lighting are greatly improved, especially the linear cracks on some floors are difficult to avoid, which leads to the use of this scheme to extract Increased difficulty, easy to extract too rough

[0007] 2. The speed is slow, the real-time performance is not strong, and the image processing algorithm is relatively slow due to the high resolution of the captured image. In addition, it runs on an embedded platform, and the execution efficiency is far inferior to that of a PC, resulting in a greatly reduced real-time performance of the algorithm.

[0008] 3. The applicability is not wide. This method is only good for the texture of flat personnel traces, but in fact there are many types of traces, such as flat, three-dimensional, soft and hard objects, objects of different materials, etc. This method can be used for personnel trace texture images on other object traces The extraction effect is not good, so the method is not widely applicable

Images