Latent fingerprint image enhancement method for hyperspectral imaging

A technology of hyperspectral imaging and image enhancement, applied in image enhancement, image data processing, instruments, etc., can solve the problems of high operation difficulty and insufficient fingerprint detection efficiency.

Active Publication Date: 2015-12-16
XIAN UNIV OF SCI & TECH
View PDF5 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In addition, there is also MISystem and the fingerprint enhancement method of hybrid spectral decomposition designed by the inventors and collaborators of the present invention, which are widely used in relevant departments such as the Ministry of Public Security Evidence Appraisal Center, but the method in this achievement ignores the effective identification of interference information. Estima

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Latent fingerprint image enhancement method for hyperspectral imaging
  • Latent fingerprint image enhancement method for hyperspectral imaging
  • Latent fingerprint image enhancement method for hyperspectral imaging

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] The latent fingerprint image enhancement method of hyperspectral imaging of the present invention comprises the following steps:

[0067] Step 1. Obtain the fingerprint endmember spectrum set: first, transmit the latent fingerprint image of hyperspectral imaging to the computer, and display it in the computer in a false color enhanced manner; then, operate the mouse to select c different backgrounds The fingerprint area is marked, and the average spectrum of c fingerprint marked areas is calculated, and the average spectrum of c fingerprint marked areas is used to construct the fingerprint endmember spectral set S={s 1 ,s 2 ,...,s c}, where the value of c is a natural number, s j is the average spectrum of the jth fingerprint mark area, and the value of j is a natural number from 1 to c; in specific implementation, the pixels in the selected fingerprint mark areas are relatively pure, that is, the pixels with obvious fingerprint lines; each fingerprint mark area The ...

Embodiment 2

[0085] The difference between this embodiment and Embodiment 1 is that in step 2, based on the combination of the fingerprint endmember spectrum in step 1 and the average spectrum of different background regions marked by the user, the background endmember spectrum is extracted by using orthogonal subspace iteratively The specific process of the set is:

[0086] Step 201, operate the mouse, select k 0 Label different background regions and calculate k 0 The average spectrum of the background labeled region, and with k 0 The average spectrum of each background labeled region constructs a labeled background endmember spectral set Among them, e m is the average spectrum of the mth background marker region, k 0 The value of is a natural number, and the value of m is 1~k 0 ;

[0087] Step 202, assuming that the number of background endmember spectra is k, and the endmember set of fingerprint endmember spectra and background endmember spectra is A; use fingerprint endmember s...

Embodiment 3

[0098]The difference between this embodiment and embodiment 1 is:

[0099] In step 3, according to the difference between the target subspace model and the background subspace model, the fingerprint is extracted using the background constraint interference matching filter, and the specific process of separating the fingerprint from the background to realize fingerprint enhancement is as follows:

[0100] Step 301, establish an orthogonal subspace from the endmember set A={S,B} including the fingerprint endmember spectrum and the background endmember spectrum which is P A ⊥ = I - A × ( A T × A ) - 1 × A T ;

[0101] Step 302, establish an orthogo...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a latent fingerprint image enhancement method for hyperspectral imaging. The method comprises the following steps: step 1, acquiring a fingerprint endmember spectrum set; step 2, acquiring a background endmember spectrum set based on the fingerprint endmember spectrum set in the step 1 or combination of the fingerprint endmember spectrum set in the step 1 and average spectrum of different background regions marked with a user, and adopting orthogonal subspace iteration for extracting the background endmember spectrum set; step 3, separating fingerprints from backgrounds to realize fingerprint enhancement; and step 4, postprocessing fingerprint features: adopting morphological open-close mixed reconstruction for performing morphology-reserving and noise-inhibiting post-processing on the fingerprint features after enhancement in the step 3. The method is simple and practical, greatly lowers the difficulty of user operation, can smooth noises and fill holes on the premise of keeping enhanced fingerprint information, and is high in fingerprint enhancement reliability, high in efficiency and high in practicality and feasibility.

Description

technical field [0001] The invention belongs to the technical field of latent fingerprint detection for criminal material evidence identification, and in particular relates to a latent fingerprint image enhancement method of hyperspectral imaging. Background technique [0002] Fingerprint is one of the most important physical evidence in the field of criminal evidence identification, and is often called the "king of evidence". Among them, fingerprint collection, analysis and identification based on optical technology are the most common. However, the fingerprints obtained by traditional optical imaging methods often fail to achieve the purpose of identification, mainly due to the problems that the fingerprints cannot be seen clearly with the naked eye, the fingerprint signal is weak, the background interference is serious, and the fingerprints are blurred and damaged. With the advancement of technology, David L. Exline et al. published an article "Forensic Applications of Ch...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06T5/00G06K9/00
Inventor 黄远程
Owner XIAN UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap