CN-122024291-A - Wet latent fingerprint identification method, system, terminal and medium based on humidity self-adaptive optical storage device

CN122024291ACN 122024291 ACN122024291 ACN 122024291ACN-122024291-A

Abstract

The invention discloses a wet latent fingerprint identification method, a system, a terminal and a medium based on a humidity self-adaptive optical storage device, wherein the method comprises the steps of acquiring an original wet latent fingerprint image, and converting the original wet latent fingerprint image into an ultraviolet pulse sequence adapting to the optical response characteristic of the humidity self-adaptive optical storage device; building a reservoir array based on a humidity self-adaptive optical storage device, receiving an ultraviolet pulse sequence based on the reservoir array, outputting a current amplitude signal matched with fingerprint features of corresponding pixels based on humidity adjustable and self-adaptive characteristics of the humidity self-adaptive optical storage device, outputting a feature vector carrying core features of wet latent fingerprints based on the current amplitude signal, inputting the feature vector into a neural network for fingerprint identification, and outputting a fingerprint identification result based on a readout layer of the neural network. The invention effectively solves the core problems of low recognition precision, high delay and high energy consumption of the traditional system in a high humidity environment, and remarkably improves the efficiency and reliability of wet latent fingerprint recognition.

Inventors

Lv Ziyu
LIN ZHIKAI
Yi Zezhuang
DUAN JUNHAO
GUO YU
ZHAI YONGBIAO
WANG YAN
ZHOU YE
HAN SUTING

Assignees

深圳大学

Dates

Publication Date: 20260512
Application Date: 20260415

Claims (10)

1. A method for identifying wet latent fingerprints based on a humidity adaptive optical storage device, the method comprising: Acquiring an original wet latent fingerprint image, and converting the original wet latent fingerprint image into an ultraviolet light pulse sequence adapting to the optical response characteristic of the humidity self-adaptive optical storage device; building a reservoir array based on the humidity self-adaptive optical storage device, receiving the ultraviolet pulse sequence based on the reservoir array, outputting a current amplitude signal matched with the fingerprint characteristics of the corresponding pixels based on the humidity adjustable and self-adaptive characteristics of the humidity self-adaptive optical storage device, and outputting a feature vector bearing the core characteristics of the wet latent fingerprints based on the current amplitude signal; and inputting the feature vector into a neural network for fingerprint identification, and outputting a fingerprint identification result based on a reading layer of the neural network, wherein the reading layer of the neural network is trained by adopting a back propagation algorithm in advance so as to establish a mapping relation between the feature vector and the fingerprint identity.
2. The method for identifying wet latent fingerprints based on a humidity adaptive optical storage device of claim 1, wherein the preparing process of the humidity adaptive optical storage device comprises: the method comprises the steps of adopting a silicon wafer as a substrate, preprocessing the silicon wafer, and imprinting double-layer photoresist by utilizing an ultraviolet lithography process to define a pattern area deposited by a bottom electrode film; Depositing a layer of bottom electrode film on the pretreated silicon wafer by a thermal evaporation process, wherein the bottom electrode film adopts a chromium and silver composite electrode layer; Removing the redundant metal layer by adopting an N-methyl pyrrolidone lift-off process to obtain a bottom electrode pattern with a regular edge; Transferring wurtzite phase nanowires onto the prepared bottom electrode pattern, selecting the polychloroethanol as a supporting layer, and fixing and protecting the wurtzite phase nanowires and the bottom electrode pattern to obtain an assembled sample; And (3) placing the assembled sample into ultrapure water for soaking for 25 minutes, removing residual impurities on the surface of the sample through a soaking process, and fully dissolving the supporting layer to obtain the humidity-adaptive optical storage device.
3. The method for identifying the wet latent fingerprints of the humidity-based adaptive optical storage device according to claim 2, wherein the thickness of the chromium layer in the chromium and silver composite electrode layer is 4-6 nm, and the thickness of the silver layer is 40-60nm.
4. A method of wet latent fingerprint identification based on a humidity adaptive optical storage device according to claim 3, wherein converting the original wet latent fingerprint image into a sequence of ultraviolet light pulses that adapt the optical response characteristics of the humidity adaptive optical storage device comprises: Sequentially performing cutting, scaling and binarization operations on the original wet latent fingerprint image to obtain a 64 multiplied by 4 pixel fingerprint image; And carrying out optical pulse coding on the 64 multiplied by 4 pixel fingerprint image based on a preset pixel matching relation, and converting the 64 multiplied by 4 pixel fingerprint image into an ultraviolet light pulse sequence adapting to the optical response characteristic of the humidity self-adaptive optical storage device, wherein the pixel matching relation is that each pixel point corresponds to the 4-bit ultraviolet light pulse sequence.
5. The method for identifying wet latent fingerprints based on a humidity adaptive optical storage device according to claim 4, wherein the fixed ultraviolet light intensity in the optical pulse encoding process is 0.95 mW cm -2 .
6. The method of claim 5, wherein receiving the ultraviolet light pulse train based on the reservoir array, outputting a current magnitude signal matching a corresponding pixel fingerprint characteristic based on a humidity-tunable and adaptive characteristic of the humidity-adaptive optical storage device, comprises: Receiving a 4-bit ultraviolet light pulse sequence based on each humidity adaptive optical storage device in the reservoir array, wherein each humidity adaptive optical storage device generates 16 high-resolution conductivity states to convert the pixel fingerprint characteristics of optical pulse codes into the conductivity physical states of the device, and the reservoir array consists of 64 humidity adaptive optical storage devices; Based on the humidity adjustable and self-adaptive characteristics of the humidity self-adaptive optical storage devices, each humidity self-adaptive optical storage device dynamically adjusts the electric response according to the actual environment humidity and outputs a current amplitude signal matched with the fingerprint characteristics of the corresponding pixel by regulating and controlling the electric conduction physical state.
7. The method for wet latent fingerprint identification based on a humidity adaptive optical storage device according to claim 6, wherein outputting a feature vector carrying a wet latent fingerprint core feature based on the current amplitude signal comprises: the reservoir array orderly integrates the current amplitude signals output by the 64 humidity self-adaptive optical storage devices according to the corresponding relation of the pixel points to form a complete current amplitude signal set, and a feature vector bearing the core features of the wet latent fingerprints is obtained.
8. A wet latent fingerprint identification system based on a humidity adaptive optical storage device, characterized in that the system is adapted to implement the steps of the wet latent fingerprint identification method based on a humidity adaptive optical storage device according to any one of claims 1-7, the system comprising: the ultraviolet light pulse conversion module is used for acquiring an original wet latent fingerprint image and converting the original wet latent fingerprint image into an ultraviolet light pulse sequence adapting to the optical response characteristic of the humidity self-adaptive optical storage device; the reservoir array module is used for building a reservoir array based on the humidity self-adaptive optical storage device, receiving the ultraviolet light pulse sequence based on the reservoir array, outputting a current amplitude signal matched with the fingerprint characteristics of the corresponding pixels based on the humidity adjustable and self-adaptive characteristics of the humidity self-adaptive optical storage device, and outputting a characteristic vector bearing the core characteristics of the wet latent fingerprints based on the current amplitude signal; And the reading network module is used for inputting the feature vector into a neural network for fingerprint identification and outputting a fingerprint identification result based on a reading layer of the neural network, wherein the reading layer of the neural network is trained by adopting a back propagation algorithm in advance so as to establish a mapping relation between the feature vector and the fingerprint identity.
9. A terminal comprising a memory, a processor and a humidity adaptive optical storage device based wet latent fingerprint identification program stored in the memory and operable on the processor, the processor implementing the steps of the humidity adaptive optical storage device based wet latent fingerprint identification method according to any one of claims 1-7 when executing the humidity adaptive optical storage device based wet latent fingerprint identification program.
10. A computer readable storage medium, characterized in that it has stored thereon a wet latent fingerprint identification program based on a humidity adaptive optical storage device, said wet latent fingerprint identification program based on a humidity adaptive optical storage device implementing the steps of the wet latent fingerprint identification method based on a humidity adaptive optical storage device according to any one of claims 1-7 on said computer readable storage medium.

Description

Wet latent fingerprint identification method, system, terminal and medium based on humidity self-adaptive optical storage device Technical Field The invention relates to the technical field of fingerprint identification, in particular to a wet latent fingerprint identification method, a wet latent fingerprint identification system, a wet latent fingerprint identification terminal and a wet latent fingerprint identification medium based on a humidity self-adaptive optical storage device. Background Wet fingerprint identification is vital in the fields of forensic investigation, identity authentication, public safety and the like, can provide key evidence for case detection and identity verification, supports scenes such as entrance guard management and control, safety prevention and control and the like, and has an important pushing effect on the development of related fields by accurate and efficient identification technology. At present, ultraviolet irradiation is the first choice technology for detecting and identifying latent fingerprints, and has the advantages of simple operation and rapid detection by relying on the characteristics of low autofluorescence of common base materials and strong ultraviolet absorption of fingerprint organic residues. However, the technology is obviously affected by humidity, and high humidity can cause blurring of a fingerprint latent image and degradation of recognition accuracy. In addition, the existing neural network reservoir architecture needs to extract different humidity characteristics respectively for fusion, and has the advantages of complex structure, high energy consumption and low recognition accuracy under unknown humidity. Therefore, the prior art has drawbacks. Disclosure of Invention Aiming at the defects in the prior art, the invention provides a wet latent fingerprint identification method, a system, a terminal and a medium based on a humidity self-adaptive optical storage device, and the technical scheme adopted by the invention is as follows: In a first aspect, the present invention provides a method for identifying wet latent fingerprints based on a humidity adaptive optical storage device, the method comprising: Acquiring an original wet latent fingerprint image, and converting the original wet latent fingerprint image into an ultraviolet light pulse sequence adapting to the optical response characteristic of the humidity self-adaptive optical storage device; building a reservoir array based on the humidity self-adaptive optical storage device, receiving the ultraviolet pulse sequence based on the reservoir array, outputting a current amplitude signal matched with the fingerprint characteristics of the corresponding pixels based on the humidity adjustable and self-adaptive characteristics of the humidity self-adaptive optical storage device, and outputting a feature vector bearing the core characteristics of the wet latent fingerprints based on the current amplitude signal; and inputting the feature vector into a neural network for fingerprint identification, and outputting a fingerprint identification result based on a reading layer of the neural network, wherein the reading layer of the neural network is trained by adopting a back propagation algorithm in advance so as to establish a mapping relation between the feature vector and the fingerprint identity. In one implementation, the humidity adaptive optical storage device manufacturing process includes: the method comprises the steps of adopting a silicon wafer as a substrate, preprocessing the silicon wafer, and imprinting double-layer photoresist by utilizing an ultraviolet lithography process to define a pattern area deposited by a bottom electrode film; Depositing a layer of bottom electrode film on the pretreated silicon wafer by a thermal evaporation process, wherein the bottom electrode film adopts a chromium and silver composite electrode layer; Removing the redundant metal layer by adopting an N-methyl pyrrolidone lift-off process to obtain a bottom electrode pattern with a regular edge; Transferring wurtzite phase nanowires onto the prepared bottom electrode pattern, selecting the polychloroethanol as a supporting layer, and fixing and protecting the wurtzite phase nanowires and the bottom electrode pattern to obtain an assembled sample; And (3) placing the assembled sample into ultrapure water for soaking for 25 minutes, removing residual impurities on the surface of the sample through a soaking process, and fully dissolving the supporting layer to obtain the humidity-adaptive optical storage device. In one implementation, in the chromium and silver composite electrode layer, the thickness of the chromium layer is 4-6 nm, and the thickness of the silver layer is 40-60nm. In one implementation, converting the raw wet latent fingerprint image into an ultraviolet light pulse train that adapts the optical response characteristics of the humidity adaptive optical storage device, comprises: