Method for processing footprint by multi-angle acquisition and integrated extraction

Abstract

The invention provides a method for processing footprint by multi-angle acquisition and integrated extraction. The flash light is used to obtain multiple footprint images with dark field illumination and background image with bright field illumination. High frequency information of each image in multiple footprint images is fused through wavelet fusion method to reduce the loss of footprint image details. Then the fused footprint images and background images can be handled respectively through the lightning correction method based on the block to solve uneven illumination. Subtraction can be made between the footprint image and background image after lightning correction, which can not only reduce noise but also extract the footprint texture, edge and other significant information more effectively, leading the effective area of footprint image more complete and the details more clearly.

Description

technical field [0001] The invention relates to the field of footprint processing, in particular to a footprint processing method of multi-angle acquisition and integrated extraction. Background technique [0002] At present, there are mainly three methods of footprint collection: (1) The suspect’s footprint collection based on pressure information. The main idea is: the collection device uses an elastic transparent film to image, and the light and dark features of the formed image reflect the pressure characteristics of the footprint. Analysis of the footprint by the technician provides pressure information. (2) The method of taking pictures of footprints on the spot with glancing light. The main idea of ​​this method is: using the illumination of glancing light, images with footprints can be photographed, and images of footprint-bearing objects without footprints can be captured at a fixed angle in the diffuse reflection lighting environment. , the two shots form two imag...

AI Technical Summary

Problems solved by technology

[0003] The problems existing in the current footprint collection and extraction methods are: 1) The light source of the collection device is fixed on both sides of the chassis, which makes the collected footprint image unevenly illuminated, part of the information is lost, and the footprint is incomplete, which increases the difficulty of image extraction

2) The collected image is easily affected by the background environment, contains more noise, the image quality is low, the footprint is not clear, and it is difficult to extract the footprint

3) After the image is collected, the extraction of the footprint pattern is completed by manual labeling, which is inefficient and time-consuming, and has not achieved true integration

Images