Automatic Threshold Segmentation Method for Low Quality Shoe Print Images

Abstract

The invention discloses an automatic threshold segmentation method for low-quality shoe print images. Firstly, morphological erosion and dilation operations are used to eliminate the influence of poor exposure or equipment artifacts; then grayscale transformation is performed to enhance image contrast; finally, morphological noise reduction is used to obtain the final shoe print area. This method does not require human interaction, and can segment shoe print images in large batches and fully automatically. It is significantly better than manual segmentation methods and iterative segmentation methods in terms of time efficiency, and the segmentation accuracy is higher than traditional global threshold segmentation methods and iterative segmentation methods.

Description

Technical field [0001] The present invention relates to the field of digital image processing, in particular, an automatic segmentation method that can effectively improve the presence of conventional global threshold segmentation in the case where the acquisition is low, and the segmentation accuracy is high, and the real-time shoe image is automatically divided. Background technique [0002] Shoes printed is one of the most frequent traces of criminal scenes, and is also one of the important basis for investigators to discover cases, disclose and confirm crime. In shoe printing image processing, people tend to extract specific shoe prints, and hardly pay attention to their background area. In this case, it is necessary to divide the shoe print portion from the image. [0003] A case is in the process of detecting two shoe print images: The shoe print image left by the crime extracted by the crime. The shoe print texture pattern in this image is very affected by the ground text...

AI Technical Summary

Problems solved by technology

However, for a class of images with small grayscale differences, little difference between the grayscale values ​​of the target and the background, and complex lighting conditions, the segmentation results are unsatisfactory.

Especially when the stamper imaging equipment is aging or used too many times, the shoe print image will be underexposed, overexposed or imprinted, and the typical automatic threshold segmentation algorithm cannot accurately separate the shoe print pattern from the background

[0005] Although many image segmentation algorithms have been proposed, there is still no general image segmentation algorithm suitable for complex lighting conditions, especially an automatic shoe print image segmentation algorithm with high accuracy, good real-time performance, and no human interaction