A humidity-dependent optical storage device-based wet latent fingerprint identification method, system, terminal and medium

Abstract

This invention discloses a method, system, terminal, and medium for wet latent fingerprint recognition based on a humidity-adaptive optical storage device. The method includes: acquiring an original wet latent fingerprint image; converting the original wet latent fingerprint image into an ultraviolet light pulse sequence adapted to the optical response characteristics of the humidity-adaptive optical storage device; constructing a reservoir array based on the humidity-adaptive optical storage device; receiving the ultraviolet light pulse sequence based on the reservoir array; outputting a current amplitude signal matching the fingerprint features of the corresponding pixel based on the humidity-adaptive optical storage device's adjustable and adaptive characteristics; and outputting a feature vector carrying the core features of the wet latent fingerprint based on the current amplitude signal; inputting the feature vector into a neural network for fingerprint recognition; and outputting the fingerprint recognition result based on the readout layer of the neural network. This invention effectively solves the core problems of low recognition accuracy, high latency, and high energy consumption in high humidity environments, significantly improving the efficiency and reliability of wet latent fingerprint recognition.

Description

Technical Field

[0001] This invention relates to the field of fingerprint recognition technology, and in particular to a wet fingerprint recognition method, system, terminal and medium based on a humidity-adaptive optical storage device. Background Technology

[0002] Wet fingerprint recognition is crucial in forensic investigations, identity verification, and public safety. It can provide key evidence for case solving and identity verification, while also supporting access control and security scenarios. The accurate and efficient recognition technology plays an important role in promoting the development of related fields.

[0003] Currently, ultraviolet (UV) irradiation is the preferred technology for latent fingerprint detection and recognition. It leverages the low autofluorescence of common substrates and the strong UV absorption of organic fingerprint residues, offering advantages such as ease of operation and rapid detection. However, this technology is significantly affected by humidity; high humidity leads to blurred fingerprint latent images and decreased recognition accuracy. Furthermore, existing neural network reservoir architectures require extracting and fusing features based on different humidity levels, resulting in complex structures, high energy consumption, and low recognition accuracy under unknown humidity conditions.

[0004] Therefore, existing technologies still have shortcomings. Summary of the Invention

[0005] To address the aforementioned deficiencies in existing technologies, this invention provides a method, system, terminal, and medium for wet fingerprint recognition based on a humidity-adaptive optical storage device. The technical solution adopted by this invention is as follows:

[0006] In a first aspect, the present invention provides a wet fingerprint recognition method based on a humidity-adaptive optical storage device, the method comprising:

[0007] Acquire the original wet latent fingerprint image and convert the original wet latent fingerprint image into an ultraviolet light pulse sequence adapted to the optical response characteristics of the humidity-adaptive optical storage device;

[0008] A reservoir array is constructed based on the humidity-adaptive optical storage device. The ultraviolet light pulse sequence is received based on the reservoir array. Based on the humidity-adaptive optical storage device's adjustable and adaptive characteristics, a current amplitude signal matching the corresponding pixel fingerprint features is output. Based on the current amplitude signal, a feature vector carrying the core features of the wet latent fingerprint is output.

[0009] The feature vector is input into a neural network for fingerprint recognition, and the fingerprint recognition result is output based on the readout layer of the neural network. The readout layer of the neural network is pre-trained using a backpropagation algorithm to establish a mapping relationship between the feature vector and the fingerprint identity.

[0010] In one implementation, the fabrication process of the humidity-adaptive optical storage device includes:

[0011] Using a silicon wafer as a substrate, the silicon wafer is pretreated, and ultraviolet lithography is used to imprint a double layer of photoresist to define the patterned area for the deposition of the bottom electrode film.

[0012] A bottom electrode film is deposited on the pretreated silicon wafer through a thermal evaporation process. The bottom electrode film is a composite electrode layer of chromium and silver.

[0013] Excess metal layer was removed using an N-methylpyrrolidone extraction process to obtain a bottom electrode pattern with regular edges;

[0014] The wurtzite nanowires were transferred onto the prepared bottom electrode pattern, and polyvinyl alcohol was selected as the support layer to fix and protect the wurtzite nanowires and the bottom electrode pattern, thus obtaining the assembled sample.

[0015] The assembled sample was immersed in ultrapure water for 25 minutes to remove residual impurities on the sample surface and to fully dissolve the support layer, thus obtaining a humidity-adaptive optical storage device.

[0016] In one implementation, the chromium-silver composite electrode layer has a chromium layer thickness of 4-6 nm and a silver layer thickness of 40-60 nm.

[0017] In one implementation, the original wet latent fingerprint image is converted into a sequence of ultraviolet light pulses adapted to the optical response characteristics of a humidity-adaptive optical storage device, including:

[0018] The original wet latent fingerprint image was cropped, scaled, and binarized sequentially to obtain a 64×4 pixel fingerprint image.

[0019] Based on a preset pixel matching relationship, optical pulse encoding is performed on a 64×4 pixel fingerprint image to convert the 64×4 pixel fingerprint image into an ultraviolet light pulse sequence that adapts to the optical response characteristics of a humidity-adaptive optical storage device. The pixel matching relationship corresponds to a 4-bit ultraviolet light pulse sequence for each pixel.

[0020] In one implementation, the ultraviolet light intensity is fixed at 0.95 mW·cm² during the optical pulse coding process. -2 .

[0021] In one implementation, the ultraviolet light pulse sequence is received based on the reservoir array, and a current amplitude signal matching the corresponding pixel fingerprint features is output based on the humidity-adjustable and adaptive characteristics of the humidity-adaptive optical storage device, including:

[0022] Each humidity-adaptive optical storage device in the reservoir array receives a 4-bit ultraviolet light pulse sequence and generates 16 high-resolution conductivity states to convert the pixel fingerprint features encoded by optical pulses into the physical conductivity states of the device itself. The reservoir array consists of 64 humidity-adaptive optical storage devices.

[0023] Based on the humidity-adaptive optical storage device's adjustable and adaptive characteristics, each humidity-adaptive optical storage device dynamically adjusts its electrical response according to the actual ambient humidity, and outputs a current amplitude signal that matches the fingerprint features of the corresponding pixel by regulating the physical state of electrical conductance.

[0024] In one implementation, a feature vector carrying the core features of a wet latent fingerprint is output based on the current amplitude signal, including:

[0025] The reservoir array integrates the current amplitude signals output by each of the 64 humidity-adaptive optical storage devices in an orderly manner according to the correspondence of pixels, forming a complete set of current amplitude signals, and obtaining a feature vector carrying the core features of the wet latent fingerprint.

[0026] Secondly, embodiments of the present invention also provide a wet fingerprint recognition system based on a humidity-adaptive optical storage device, the system being used to implement the steps of the wet fingerprint recognition method based on a humidity-adaptive optical storage device as described in any of the above solutions, the system comprising:

[0027] The ultraviolet light pulse conversion module is used to acquire the original wet latent fingerprint image and convert the original wet latent fingerprint image into an ultraviolet light pulse sequence adapted to the optical response characteristics of the humidity-adaptive optical storage device.

[0028] The reservoir array module is used to build a reservoir array based on the humidity-adaptive optical storage device, receive the ultraviolet light pulse sequence based on the reservoir array, output a current amplitude signal that matches the fingerprint features of the corresponding pixel based on the humidity-adaptive optical storage device, and output a feature vector carrying the core features of the wet latent fingerprint based on the current amplitude signal.

[0029] The readout network module is used to input the feature vector into the neural network for fingerprint recognition, and output the fingerprint recognition result based on the readout layer of the neural network. The readout layer of the neural network is pre-trained using the backpropagation algorithm to establish a mapping relationship between the feature vector and the fingerprint identity.

[0030] Thirdly, embodiments of the present invention also provide a terminal, wherein the terminal includes a memory, a processor, and a wet fingerprint recognition program based on a humidity-adaptive light storage device stored in the memory and executable on the processor. When the processor executes the wet fingerprint recognition program based on the humidity-adaptive light storage device, it implements the steps of the wet fingerprint recognition method based on the humidity-adaptive light storage device of any of the above solutions.

[0031] Fourthly, embodiments of the present invention also provide a computer-readable storage medium, wherein a wet fingerprint recognition program based on a humidity-adaptive optical storage device is stored on the computer-readable storage medium, and the wet fingerprint recognition program based on the humidity-adaptive optical storage device implements the steps of the wet fingerprint recognition method based on a humidity-adaptive optical storage device as described in any of the above schemes on the computer-readable storage medium.

[0032] Beneficial Effects: Compared with existing technologies, this invention provides a wet latent fingerprint recognition method based on a humidity-adaptive optical storage device. First, an original wet latent fingerprint image is acquired and converted into an ultraviolet light pulse sequence adapted to the optical response characteristics of the humidity-adaptive optical storage device. Next, a reservoir array is constructed based on the humidity-adaptive optical storage device. The ultraviolet light pulse sequence is received by the reservoir array. Based on the humidity-adaptive optical storage device's adjustable and adaptive characteristics, a current amplitude signal matching the fingerprint features of the corresponding pixels is output, and a feature vector carrying the core features of the wet latent fingerprint is output based on the current amplitude signal. Finally, the feature vector is input into a neural network for fingerprint recognition. The fingerprint recognition result is output based on the readout layer of the neural network. The readout layer of the neural network is pre-trained using a backpropagation algorithm to establish a mapping relationship between the feature vector and the fingerprint identity.

[0033] This invention uses a humidity-adaptive optical storage device as its core, and utilizes its controllable conductivity modulation characteristics to construct a humidity-adaptive optical storage and computing architecture within the sensor. The fingerprint image is converted into an ultraviolet light pulse sequence and projected onto a reservoir array built by the humidity-adaptive optical storage device. The reservoir array can dynamically adjust its electrical response to adapt to different humidity environments. Humidity adaptation, feature extraction, and fusion can be completed simultaneously without manual intervention. Furthermore, fingerprint recognition can be achieved simply by training the readout layer of the neural network. This effectively solves the core problems of low recognition accuracy, high latency, and high energy consumption in high humidity environments, significantly improving the efficiency and reliability of wet fingerprint recognition. Attached Figure Description

[0034] Figure 1 This is a flowchart of a preferred embodiment of the wet fingerprint recognition method based on a humidity-adaptive optical storage device according to an embodiment of the present invention.

[0035] Figure 2 This is a schematic diagram illustrating the process of fabricating a humidity-adaptive optical storage device in the wet latent fingerprint recognition method based on a humidity-adaptive optical storage device according to an embodiment of the present invention.

[0036] Figure 3 The image shows the photoresponse current of the humidity-adaptive optical storage device under different read voltages and illumination times in an embodiment of the present invention.

[0037] Figure 4 This is a diagram showing the response current distribution of the humidity-adaptive optical storage device under different read voltages and humidity levels in an embodiment of the present invention.

[0038] Figure 5 This is a schematic diagram of the humidity-adaptive sensing computing architecture in the humidity-adaptive optical storage device-based wet fingerprint recognition method according to an embodiment of the present invention.

[0039] Figure 6 This is a schematic diagram of the preprocessing process of the original wet latent fingerprint image in the wet latent fingerprint recognition method based on humidity adaptive optical storage device according to an embodiment of the present invention.

[0040] Figure 7 This is a schematic diagram of the mode-dependent reservoir response of the humidity-adaptive optical storage (HAOR) device in an embodiment of the present invention at different humidity levels (60%, 70%, 80%).

[0041] Figure 8 This is a confusion matrix for processing images at all humidity levels (60%, 70%, 80%) using the Humidity Adaptive Light Storage (HAOR) device in this embodiment of the invention.

[0042] Figure 9 This is a schematic diagram of the structure of a wet fingerprint recognition system based on a humidity-adaptive optical storage device according to an embodiment of the present invention.

[0043] Figure 10 A schematic diagram of a terminal provided in an embodiment of the present invention. Detailed Implementation

[0044] To make the objectives, technical solutions, and effects of this invention clearer and more explicit, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0045] The flowchart shown in the attached diagram is for illustrative purposes only and does not necessarily include all content, operations, or steps, nor does it require execution in the described order. For example, some operations or steps can be broken down, combined, or partially merged, so the actual execution order may change depending on the actual situation.

[0046] It should be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise.

[0047] It should be understood that, in order to clearly describe the technical solutions of the embodiments of the present invention, the terms "first" and "second" are used in the embodiments of the present invention to distinguish identical or similar items with essentially the same function and effect. For example, "first control information" and "second control information" are only used to distinguish different control information and do not limit their order.

[0048] Those skilled in the art will understand that the words "first" and "second" do not limit the quantity or the order of execution, and that the words "first" and "second" do not necessarily imply that they are different.

[0049] It should also be understood that the term “and / or” as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0050] Traditional wet fingerprint recognition systems employ a separate design for sensors, memory, and processors, resulting in high decision latency and heavy computational burden. Furthermore, ultraviolet recognition technology is significantly affected by humidity, with fingerprint latent images becoming blurred and recognition accuracy decreasing under high humidity. Meanwhile, the existing neural network reservoir architecture requires the extraction and fusion of different humidity features, leading to structural complexity, high energy consumption, and low recognition accuracy under unknown humidity conditions. Moreover, existing related devices struggle to balance environmental adaptability with high integration requirements.

[0051] To address the problems of existing technologies, this invention provides a wet latent fingerprint recognition method based on a humidity-adaptive optical storage device. Leveraging the dual-spectrum and humidity-tunable characteristics of humidity-adaptive optical storage (HAOR) devices, an integrated sensing and computing architecture is constructed to achieve humidity-adaptive recognition of wet latent fingerprints. This design not only overcomes the latency and power consumption limitations of traditional discrete architectures and resolves the contradiction between environmental adaptability, integration, and recognition accuracy in existing technologies, but also innovatively applies HAOR devices to the field of wet latent fingerprint recognition, filling the technical gap in accurate recognition under high humidity environments.

[0052] The wet fingerprint recognition method based on humidity-adaptive optical storage devices in this embodiment can be applied to terminals, such as computers and other intelligent product terminals. Figure 1As shown in the figure, the wet fingerprint recognition method based on humidity-adaptive optical storage device in this embodiment specifically includes the following steps:

[0053] Step S100: Obtain the original wet latent fingerprint image and convert the original wet latent fingerprint image into an ultraviolet light pulse sequence that adapts to the optical response characteristics of the humidity-adaptive optical storage device.

[0054] In practical applications, the humidity-adaptive optical storage (HAOR) device in this embodiment is a planar dual-terminal memristor. Its core innovation lies in precisely controlling the fabrication process to enable wurtzite-phase ZnO (zinc oxide) nanowires to possess both light and humidity-sensitive characteristics, while ensuring stable contact between the electrodes and the nanowires. This provides the hardware foundation for three-mode signal fusion and humidity-adaptive regulation. The fabrication process strictly controls key steps such as substrate cleaning, electrode pattern definition, electrode deposition, nanowire transfer, and post-processing shaping, combined with... Figure 2 The specific steps and technical details are as follows:

[0055] First, a silicon wafer is used as the substrate for pretreatment. In this embodiment, a p-type boron-doped silicon wafer with a 300 nm thermally grown SiO2 coating is used as the substrate. This substrate has both good insulation and mechanical stability, effectively avoiding the impact of substrate leakage on the electrical performance of the device. The pretreatment process strictly follows standardized cleaning procedures: First, the silicon wafer is cut into 1 cm × 1 cm square chips and placed sequentially into ultrasonic cleaning tanks containing anhydrous ethanol and deionized water. Each chip is ultrasonically cleaned for 15 minutes, with the ultrasonic power set at 100 W and the frequency at 40 kHz. The cavitation effect of the ultrasound thoroughly removes contaminants such as oil, dust, and metal ions from the substrate surface. After ultrasonic cleaning, the substrate is placed in an oven and dried at 80°C for 30 minutes to remove residual moisture. Finally, high-purity N2 (purity ≥ 99.999%) is used to purge the substrate surface at a pressure of 0.3 MPa for 5 minutes to ensure a clean, flat surface free of any impurities, providing excellent substrate conditions for subsequent photolithography and electrode deposition.

[0056] Then, a combined process of ultraviolet lithography and electron beam lithography was used to imprint the double-layer photoresist to define the patterned area for the bottom electrode film deposition. First, a double-layer photoresist was uniformly coated onto the pretreated substrate surface. The bottom layer was a 3μm thick SU-82002 photoresist, and the top layer was a 0.5μm thick photoresist. The coating speed was 3000 r / min, and the coating time was 45 seconds. Subsequently, it was soft-baked at 115℃ for 60 seconds to ensure a tight bond between the photoresist and the substrate, preventing photoresist detachment during subsequent processes. Next, ultraviolet lithography was performed. The coated chip was placed in an ultraviolet lithography machine (exposure wavelength 365nm), and the large-area contact pads and probe line patterns were exposed through a mask. The amount of photoresist is 100 mJ / cm². After exposure, the chip is developed in SU-8 developer for 3 minutes to remove the photoresist in the unexposed areas, thus defining the channel width with a 2 μm electrode spacing. Finally, electron beam lithography is performed to transfer the chip to an electron beam lithography machine (accelerating voltage 30 kV, beam current 100 pA). Symmetric Ag source and drain electrode patterns are drawn within the predefined probe lines to obtain the patterned area of ​​the bottom electrode film deposition. The electrode length is 5 μm and the width is 2 μm. The electrode spacing is strictly controlled to 2 μm to ensure that the subsequent nanowires can accurately bridge the electrodes.

[0057] Next, a bottom electrode film is deposited on the pretreated silicon wafer using a thermal evaporation process. The bottom electrode film is a composite electrode layer of chromium (Cr) and silver (Ag). In this embodiment, the photolithographically etched chip is placed in the vacuum chamber of a thermal evaporation coating machine, and the vacuum level is evacuated to 5 × 10⁻⁶. -4 To avoid insufficient vacuum leading to oxidation or contamination during electrode deposition, a Cr transition layer was deposited first. The Cr evaporation source current was set to 80 A, the deposition rate was 0.1 nm / s, and the deposition thickness was 5 nm. The Cr layer can chemically bond with the SiO2 substrate and the Ag layer, significantly improving electrode adhesion and preventing electrode detachment in subsequent processes. Subsequently, an Ag electrode layer was deposited. The Ag evaporation source current was set to 100 A, the deposition rate was 0.5 nm / s, and the deposition thickness was 50 nm. Ag is a highly conductive metal (resistivity 1.6 × 10⁻⁶). -8 Ω (m) ensures low contact resistance of the electrodes, reducing signal transmission loss.

[0058] Next, an N-methyl-2-Pyrrolidone (NMP) extraction process is used to remove excess metal layers, resulting in a bottom electrode pattern with regular edges. In this embodiment, the deposited chip is immersed in an NMP solution at 50°C for 3 hours to allow the photoresist to fully swell and decompose. Subsequently, it is ultrasonically cleaned with deionized water (50W power, 5 minutes) to remove residual photoresist and metal debris. Finally, it is dried by blowing with high-purity N2, and the electrode pattern is observed under an optical microscope to ensure that the electrode edges are regular, free of burrs, short circuits, and other defects, and that the electrode spacing deviation is controlled within ±0.1μm.

[0059] Next, the wurtzite nanowires were transferred onto the prepared bottom electrode pattern, and polyvinyl alcohol (PVA) was selected as the support layer to fix and protect the wurtzite nanowires and the bottom electrode pattern, thus obtaining the assembled sample. In this embodiment, wurtzite ZnO nanowires (purity ≥99.9%) with a diameter of 50-100 nm and a length of 2-5 μm were selected and dispersed in deionized water. The dispersion was ultrasonically dispersed for 10 minutes to prepare a nanowire dispersion with a concentration of 0.1 mg / mL. PVA (molecular weight 100,000) was dissolved in deionized water to prepare a 5% PVA solution, which was uniformly coated onto a glass slide and dried at 60°C to form a 1 μm thick PVA film. The wurtzite ZnO nanowire dispersion was then added dropwise to the surface of the PVA film using a micropipette and allowed to dry naturally at room temperature, ensuring uniform adhesion of the nanowires to the PVA film. The PVA film with the attached nanowires was then placed over an Ag electrode pattern. The position was observed and adjusted using an optical microscope to ensure precise bridging of the 2 μm spacing Ag source and drain electrodes by the ZnO nanowires. The PVA film was then wetted with deionized water to ensure close adhesion to the substrate and dried at 100°C for 5 minutes to enhance the contact between the nanowires and the electrodes.

[0060] Finally, the assembled sample was immersed in ultrapure water for 25 minutes to remove residual impurities from the sample surface and to fully dissolve the support layer, resulting in a humidity-adaptive optical storage device. In this embodiment, the assembled sample was placed in a beaker containing ultrapure water and immersed for 25 minutes. The PVA film was fully dissolved in the water, releasing wurtzite-phase ZnO nanowires. The ultrapure water was replaced, and the sample was immersed again for 10 minutes to remove residual PVA molecules and impurities from the surface. The sample was then removed, dried by blowing with high-purity N2, and then placed in a vacuum oven for annealing at 100°C for 30 minutes to further improve the contact stability between the wurtzite-phase ZnO nanowires and the Ag electrode and reduce the contact resistance.

[0061] The fabricated humidity-adaptive optical storage (HAOR) device needs to undergo a series of characterization methods to verify its structure and performance, ensuring that it meets the design requirements: For structural characterization, scanning electron microscopy was used to observe the morphology and electrode contact of wurtzite ZnO nanowires, ensuring that the nanowires were free of breakage and had good bridging; X-ray diffraction (XRD) was used to characterize the crystal structure of the wurtzite ZnO nanowires, confirming that it is a pure wurtzite phase (corresponding to 2θ=31.77°, 34.42°, 36.25°). (100), (002), (101) crystal planes); X-ray photoelectron spectroscopy (XPS) was used to analyze the surface chemical state of wurtzite ZnO nanowires, confirming the presence of oxygen vacancy defects (the characteristic peak at 531.5 eV in the O1s spectrum corresponds to an oxygen vacancy); in terms of electrical performance verification, under dark conditions and 50% RH, with a readout voltage of 0.01~1V applied, the device dark current was less than 1nA, exhibiting a high-resistivity state; when a 375nm ultraviolet light pulse (intensity 0.95mW) was applied... cm - ², pulse width 0.1s), peak photocurrent exceeding 100nA, on / off ratio exceeding 3 orders of magnitude, verifying the optical response characteristics of the device; in terms of humidity control performance verification, within the range of 10%~80%RH, with a fixed readout voltage of 1V and unchanged ultraviolet light pulse parameters, the photocurrent relaxation dynamics were tested, confirming that the relaxation time constant decreased from 730.0ms (humidity at 10%RH) to 6.3ms (humidity at 80%RH), with the humidity control range exceeding 1 order of magnitude, verifying the ability of humidity to control reservoir dynamics.

[0062] In other implementations, this embodiment may also select an optical-humidity dual-sensitive material as the core functional layer of the humidity adaptive optical storage (HAOR) device, and may also use electrode materials such as silver, platinum, copper, etc. In addition, it may be fabricated on different substrates, such as silicon wafers or flexible substrates.

[0063] For the humidity-adaptive optical storage (HAOR) device fabricated in this embodiment, the device performance is jointly controlled by a semiconductor parameter analyzer, an optical control module, and a self-made humidity control device. First, the photoresponse current is studied; this humidity-adaptive optical storage device achieves a photoresponse current of 0.95 mW·cm⁻¹ in 0.1 seconds. -2 Under the influence of ultraviolet light pulses, the higher the reading voltage, the stronger the photocurrent. For example... Figure 3 As shown, Figure 3 The photoresponse current diagrams are shown under different readout voltages and illumination durations. When light pulses of different readout voltages and illumination durations (including 0.01, 0.05, 0.1, 0.3, and 0.5 seconds) are applied, changes in postsynaptic current and a transition from short-term to long-term enhancement can be observed. The optical and humidity response characteristics of the humidity-adaptive optical storage device in this embodiment are as follows: Figure 4 As shown, Figure 4 The diagram shows the response current distribution under different reading voltages and humidity levels. Figure 4 These represent the fixed ultraviolet light intensity of 0.95 mW·cm² under controlled environments with humidity levels of 80%, 70%, 60%, and 50%, respectively. -2 This study investigated the distribution of the photocurrent response under different readout voltages and humidity conditions. Experimental results show that the photocurrent response of the device is jointly regulated by the readout voltage and ambient humidity: the higher the readout voltage, the higher the peak photocurrent; the higher the ambient humidity, the shorter the relaxation time of the device response. These results provide a performance basis for wet fingerprint recognition.

[0064] The humidity-adaptive optical storage (HAOR) device in this embodiment possesses dual-spectral response and humidity-tunable characteristics. Its controllable conductivity modulation capability can dynamically adapt to changes in environmental humidity, providing a solid physical foundation for constructing a humidity-adaptive sensing computing architecture. Specifically, as follows... Figure 5 As shown, the humidity adaptive sensing computing architecture constructed in this embodiment includes an ultraviolet light pulse conversion module, a HAOR reservoir array module, and a readout network module. The modules work together to achieve efficient processing of the entire process from wet latent fingerprint image acquisition to final recognition result output. This breaks the limitations of the traditional discrete system design and achieves a high degree of integration of sensing, storage, and computing functions.

[0065] Based on this, this embodiment applies a humidity-adaptive optical storage device to a wet fingerprint recognition method. This embodiment first acquires a raw wet fingerprint image and converts it into an ultraviolet light pulse sequence adapted to the optical response characteristics of the humidity-adaptive optical storage device. Specifically, this embodiment performs preprocessing on the raw wet fingerprint image sequentially, including cropping, scaling, and binarization. Cropping removes invalid edge areas; scaling reconstructs the image to 64×4 pixels to meet subsequent pulse input requirements; and binarization highlights fingerprint texture features and removes image noise, ultimately obtaining a 64×4 pixel fingerprint image, as shown below. Figure 6As shown, this lays the foundation for subsequent signal conversion and feature extraction. Next, the one-to-one mapping relationship between each pixel in the preprocessed 64×4 pixel fingerprint image and a set of 4-bit ultraviolet light pulse sequences is determined, thus obtaining the pixel matching relationship. This pixel matching relationship allows the position of fingerprint pixels and texture features to be accurately mapped through the corresponding pulse sequences. Then, based on the preset pixel matching relationship, this embodiment performs optical pulse encoding on the 64×4 pixel fingerprint image, converting the 64×4 pixel fingerprint image into an ultraviolet light pulse sequence adapted to the optical response characteristics of humidity-adaptive optical storage devices. In optical pulse encoding, this embodiment uses a 4-bit pulse sequence of 0000-1111 to optically encode the fingerprint pixel features, defining the encoding rule as "0 represents no ultraviolet light pulse" and "1" represents the presence of ultraviolet light pulse. This rule converts the texture features of the fingerprint pixels into signals indicating the presence or absence of ultraviolet light pulses, completing the optical encoding of the fingerprint texture features. In this embodiment, the ultraviolet light intensity is stably fixed at 0.95 mW·cm². -2 This parameter is consistent with the optical response parameter determined in the performance study of humidity-adaptive optical storage (HAOR) devices, ensuring that the encoded ultraviolet light pulse sequence can be stably and without deviation projected onto the subsequent HAOR reservoir array, avoiding distortion of feature information transmission caused by light intensity fluctuations, and preparing the HAOR reservoir array to accurately receive feature signals.

[0066] Step S200: Construct a reservoir array based on the humidity-adaptive optical storage device, receive the ultraviolet light pulse sequence based on the reservoir array, output a current amplitude signal matching the corresponding pixel fingerprint features based on the humidity-adaptive optical storage device's adjustable and adaptive characteristics, and output a feature vector carrying the core features of the wet latent fingerprint based on the current amplitude signal.

[0067] Specifically, in this embodiment, a reservoir array is constructed using 64 humidity-adaptive optical storage (HAOR) devices. According to the "pixel-pulse sequence" matching relationship established during the signal conversion stage, each humidity-adaptive optical storage (HAOR) device in the reservoir array accurately receives the 4-bit ultraviolet light pulse sequence corresponding to the fingerprint pixel, thereby realizing the physical reception of the optical pulse signal and establishing a direct connection from optical input to device electrical response.

[0068] Next, leveraging the excellent multi-level programmability of humidity-adaptive optical storage (HAOR) devices, each HAOR device in the reservoir array can generate 16 high-resolution conductivity states after receiving a 4-bit ultraviolet light pulse sequence from 0000 to 1111. This converts the pixel fingerprint features encoded by optical pulses into the device's own conductivity physical states, such as... Figure 7 As shown, Figure 7The model-dependent reservoir response under different humidity levels demonstrates that the HAOR device can encode the spatiotemporal features of fingerprints with high fidelity and avoid feature loss. It also has good humidity adaptability and can dynamically adjust the electrical response according to the ambient humidity.

[0069] Based on this, this embodiment utilizes the adjustable and adaptive characteristics of humidity-adaptive optical storage devices (HAORs). Each HAOR dynamically adjusts its electrical response according to the actual ambient humidity (including the typical humidity range of 60%-80% and unknown humidity), and changes the output current amplitude by regulating the physical state of conductivity. This current amplitude serves as the reservoir state, simultaneously carrying the core fingerprint features and environmental humidity adaptation information. Furthermore, the HAOR devices can distinguish discrete current states under sixteen different humidity conditions, possessing high-dimensional feature encoding capabilities and strong environmental adaptability. This ensures accurate extraction of the core features of the wet latent fingerprint from the optical pulse signal under various humidity conditions. At this point, each of the 64 HAOR devices in the reservoir array outputs a current amplitude signal that matches the fingerprint feature of its corresponding pixel. Finally, the reservoir array integrates the current amplitude signals output by the 64 humidity-adaptive HAOR devices according to the pixel correspondence, forming a complete set of current amplitude signals to obtain the feature vector carrying the core features of the wet latent fingerprint (i.e., the current amplitude signal output by each HAOR device). Finally, the array accurately outputs the feature vector to the subsequent readout network module, providing the core electrical signal data foundation for establishing the mapping relationship between "feature vector and fingerprint identity" during the training of the readout network.

[0070] Step S300: Input the feature vector into the neural network for fingerprint recognition, and output the fingerprint recognition result based on the readout layer of the neural network. The readout layer of the neural network is pre-trained using the backpropagation algorithm to establish a mapping relationship between the feature vector and the fingerprint identity.

[0071] In this embodiment, the current amplitude signals output by each HAOR device are input into a neural network for fingerprint recognition. The fingerprint recognition result is output based on the readout layer of the neural network. The readout layer of this neural network is pre-trained using the backpropagation algorithm to establish a mapping relationship between feature vectors and fingerprint identity. This embodiment eliminates the need to train the entire reservoir array, reducing computational and training costs, improving network response speed, and completing the training of the readout network, thus laying the foundation for accurate fingerprint identity recognition. The specific training process is as follows:

[0072] Step 1: Training data preparation. Select wet latent fingerprint samples from 5 subjects in the database, covering typical humidity levels of 60%, 70%, and 80%, as well as some samples with unknown humidity. Label each fingerprint sample with a unique identity tag (corresponding to 5 subjects) to form a training set of "HAOR feature vector + identity tag".

[0073] Step 2: Use a simplified neural network, only initialize the weights and bias parameters of the readout layer of the neural network; fix all parameters of the reservoir array composed of HAOR devices, the array does not participate in training, and is only responsible for outputting feature vectors, which greatly reduces the training cost.

[0074] Step 3: Define input: the feature vector of the 64-dimensional current amplitude signal output by the reservoir array composed of HAOR devices (carrying fingerprint features + humidity information); Define output: 5-class fingerprint identity prediction results (corresponding to 5 subjects).

[0075] Step 4: Input the 64-dimensional feature vector from the training set into the neural network. The readout layer of the neural network calculates the predicted probability of fingerprint identity by multiplying the weights by the feature vector and then the bias. Next, compare the predicted result with the real identity label, calculate the classification error (i.e., the loss value), and quantify the mapping deviation.

[0076] Step 5: Backpropagate the classification error to the readout layer of the neural network and calculate the gradients of the weights and biases. Then, based on the gradients, update the readout layer weights and biases using an optimization algorithm to reduce the prediction error. Throughout the process, the HAOR device and array parameters are not adjusted; only the readout layer is optimized, ensuring efficient training with low computational cost.

[0077] Step 6, Iterative Training: Input training samples in batches, repeat the forward propagation → backpropagation → parameter update process until the loss value converges (error stabilizes and meets the target). This embodiment uses samples with 60%-80% humidity and unknown humidity for verification, allowing the readout layer to adapt to humidity fluctuations and ensuring that the mapping relationship is effective under different humidity levels.

[0078] Step 7: The readout layer of the neural network learns a stable mapping rule of "64-dimensional feature vector → fingerprint identity". Based on this mapping rule, new HAOR feature vectors can be received quickly and accurate identity results can be output directly, achieving low latency and high accuracy recognition.

[0079] Therefore, when the current amplitude signals output by each HAOR device (i.e., the feature vectors carrying the core features of wet latent fingerprints) are input into the neural network, the readout layer of the neural network can perform fingerprint recognition and output the fingerprint recognition result. In this embodiment, the fingerprint recognition result can be directly transmitted to the recognition output module, which receives and displays the fingerprint recognition result in real time, retains relevant recognition data, provides traceable evidence for forensic investigations and identity verification, and meets practical application needs. The neural network in this embodiment uses a simple and efficient neural network, including binary neural networks, recurrent neural networks, and convolutional neural networks.

[0080] The HAOR device of this invention can automatically adapt to, extract, and fuse different humidity features. Feature extraction is completed within the reservoir, significantly reducing structural complexity and energy consumption. Quantitative comparative experiments show that traditional artificial neural networks consume approximately 0.3 millijoules to process a 64×4 pixel signal, while the system based on the HAOR device in this embodiment requires an average of only 2.5 nanojoules, with a single pixel energy consumption as low as 10 picojoules. Furthermore, compared to using traditional reservoirs to process 60%, 70%, and 80% humidity data respectively, the scheme of simultaneously extracting and integrating features during a single HAOR period achieves higher recognition accuracy. When processing images under unknown humidity conditions, the accuracy of traditional reservoirs is low (58.5%, 57.0%, and 54.5%, respectively), while the system based on the HAOR device achieves an accuracy of 93.5%. Figure 8 The confusion matrix of images processed by the HAOR device at all humidity levels (including 60%, 70%, and 80%) is shown, clearly demonstrating the superior performance of in-storage computation supported by the HAOR device in wet latent fingerprint recognition.

[0081] Based on the above embodiments, the present invention also provides a wet fingerprint recognition system based on a humidity-adaptive optical storage device, which is used to implement the steps of the above method embodiments. Specifically, as Figure 9 As shown in the diagram, the system of this embodiment includes: an ultraviolet light pulse conversion module 10, a reservoir array module 20, and a readout network module 30. The ultraviolet light pulse conversion module 10 is used to acquire the original wet latent fingerprint image and convert it into an ultraviolet light pulse sequence adapted to the optical response characteristics of the humidity-adaptive optical storage device. The reservoir array module 20 is used to construct a reservoir array based on the humidity-adaptive optical storage device, receive the ultraviolet light pulse sequence based on the reservoir array, output a current amplitude signal matching the corresponding pixel fingerprint features based on the humidity-adaptive optical storage device's adjustable and adaptive characteristics, and output a feature vector carrying the core features of the wet latent fingerprint based on the current amplitude signal. The readout network module 30 is used to input the feature vector into a neural network for fingerprint recognition, and output the fingerprint recognition result based on the readout layer of the neural network. The readout layer of the neural network is pre-trained using a backpropagation algorithm to establish a mapping relationship between the feature vector and the fingerprint identity.

[0082] The principles of each module in the wet fingerprint recognition system based on humidity adaptive optical storage device in this embodiment are the same as the principles of each step in the method embodiment, and will not be elaborated further here.

[0083] Based on the above embodiments, the present invention also provides a terminal, the principle block diagram of which can be as follows: Figure 10 As shown. The terminal may include one or more processors 100 ( Figure 10(Only one is shown in the image), memory 101, and computer program 102 stored in memory 101 and executable on one or more processors 100. For example, a wet fingerprint recognition program based on a humidity-adaptive light storage device. When one or more processors 100 execute computer program 102, they can implement various steps in the wet fingerprint recognition method embodiment based on a humidity-adaptive light storage device. Alternatively, when one or more processors 100 execute computer program 102, they can implement the functions of various modules / units in the wet fingerprint recognition system embodiment based on a humidity-adaptive light storage device, which is not limited here.

[0084] In one embodiment, the processor 100 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0085] In one embodiment, memory 101 can be an internal storage unit of the terminal, such as a hard disk or RAM. Memory 101 can also be an external storage device of the terminal, such as a plug-in hard disk, smart media card (SM), secure digital card (SD), flash card, etc. Furthermore, memory 101 can include both internal and external storage units. Memory 101 is used to store computer programs and other programs and data required by the terminal. Memory 101 can also be used to temporarily store data that has been output or will be output.

[0086] Those skilled in the art will understand that Figure 10 The block diagram shown is merely a partial structural diagram related to the present invention and does not constitute a limitation on the terminal to which the present invention is applied. A specific terminal may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0087] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided by this invention can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), direct memory bus RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0088] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for wet latent fingerprint identification based on a humidity adaptive optical storage device, characterized in that, The method includes: Acquire the original wet latent fingerprint image and convert the original wet latent fingerprint image into an ultraviolet light pulse sequence adapted to the optical response characteristics of the humidity-adaptive optical storage device; A reservoir array is constructed based on the humidity-adaptive optical storage device. The ultraviolet light pulse sequence is received based on the reservoir array. Based on the humidity-adaptive optical storage device's adjustable and adaptive characteristics, a current amplitude signal matching the corresponding pixel fingerprint features is output. Based on the current amplitude signal, a feature vector carrying the core features of the wet latent fingerprint is output. The feature vector is input into a neural network for fingerprint recognition, and the fingerprint recognition result is output based on the readout layer of the neural network. The readout layer of the neural network is pre-trained using a backpropagation algorithm to establish a mapping relationship between the feature vector and the fingerprint identity. Based on the ultraviolet light pulse sequence received by the reservoir array, and based on the humidity-adaptive and humidity-adaptive characteristics of the humidity-adaptive optical storage device, a current amplitude signal matching the corresponding pixel fingerprint features is output, including: Each humidity-adaptive optical storage device in the reservoir array receives a 4-bit ultraviolet light pulse sequence and generates 16 high-resolution conductivity states to convert the pixel fingerprint features encoded by optical pulses into the physical conductivity states of the device itself. The reservoir array consists of 64 humidity-adaptive optical storage devices. Based on the humidity-adaptive optical storage device's adjustable and adaptive characteristics, each humidity-adaptive optical storage device dynamically adjusts its electrical response according to the actual ambient humidity, and outputs a current amplitude signal that matches the fingerprint features of the corresponding pixel by regulating the physical state of electrical conductance. Based on the current amplitude signal, a feature vector carrying the core features of the wet fingerprint is output, including: The reservoir array integrates the current amplitude signals output by each of the 64 humidity-adaptive optical storage devices in an orderly manner according to the correspondence of pixels, forming a complete set of current amplitude signals, and obtaining a feature vector carrying the core features of the wet latent fingerprint.

2. The method of claim 1, wherein the humidity adaptive optical storage device is a humidity-dependent phase change material. The fabrication process of the humidity-adaptive optical storage device includes: Using a silicon wafer as a substrate, the silicon wafer is pretreated, and ultraviolet lithography is used to imprint a double layer of photoresist to define the patterned area for the deposition of the bottom electrode film. A bottom electrode film is deposited on the pretreated silicon wafer through a thermal evaporation process. The bottom electrode film is a composite electrode layer of chromium and silver. Excess metal layer was removed using an N-methylpyrrolidone extraction process to obtain a bottom electrode pattern with regular edges; The wurtzite nanowires were transferred onto the prepared bottom electrode pattern, and polyvinyl alcohol was selected as the support layer to fix and protect the wurtzite nanowires and the bottom electrode pattern, thus obtaining the assembled sample. The assembled sample was immersed in ultrapure water for 25 minutes to remove residual impurities on the sample surface and to fully dissolve the support layer, thus obtaining a humidity-adaptive optical storage device.

3. The method of wet latent fingerprint identification based on a humidity adaptive optical storage device according to claim 2, wherein, In the composite electrode layer of chromium and silver, the thickness of the chromium layer is 4~6nm and the thickness of the silver layer is 40-60nm.

4. The method according to claim 3, wherein the humidity adaptive optical storage device is a humidity-dependent optical storage device. The original wet latent fingerprint image is converted into a sequence of ultraviolet light pulses with optical response characteristics adapted to humidity-adaptive optical storage devices, including: The original wet latent fingerprint image was cropped, scaled, and binarized sequentially to obtain a 64×4 pixel fingerprint image. Based on a preset pixel matching relationship, optical pulse encoding is performed on a 64×4 pixel fingerprint image to convert the 64×4 pixel fingerprint image into an ultraviolet light pulse sequence that adapts to the optical response characteristics of a humidity-adaptive optical storage device. The pixel matching relationship corresponds to a 4-bit ultraviolet light pulse sequence for each pixel.

5. The wet fingerprint recognition method based on a humidity-adaptive optical storage device according to claim 4, characterized in that, The fixed UV light intensity in the optical pulse coding process is 0.95 mW-cm -2 .

6. A wet fingerprint recognition system based on a humidity-adaptive optical storage device, characterized in that, The system is used to implement the steps of the wet fingerprint recognition method based on a humidity-adaptive optical storage device as described in any one of claims 1-5, and the system includes: The ultraviolet light pulse conversion module is used to acquire the original wet latent fingerprint image and convert the original wet latent fingerprint image into an ultraviolet light pulse sequence adapted to the optical response characteristics of the humidity-adaptive optical storage device. The reservoir array module is used to build a reservoir array based on the humidity-adaptive optical storage device, receive the ultraviolet light pulse sequence based on the reservoir array, output a current amplitude signal that matches the fingerprint features of the corresponding pixel based on the humidity-adaptive optical storage device, and output a feature vector carrying the core features of the wet latent fingerprint based on the current amplitude signal. The readout network module is used to input the feature vector into the neural network for fingerprint recognition, and output the fingerprint recognition result based on the readout layer of the neural network. The readout layer of the neural network is pre-trained using the backpropagation algorithm to establish a mapping relationship between the feature vector and the fingerprint identity.

7. A terminal, characterized in that, The terminal includes a memory, a processor, and a wet fingerprint recognition program based on a humidity-adaptive light storage device stored in the memory and executable on the processor. When the processor executes the wet fingerprint recognition program based on the humidity-adaptive light storage device, it implements the steps of the wet fingerprint recognition method based on a humidity-adaptive light storage device as described in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a wet fingerprint recognition program based on a humidity-adaptive optical storage device, and the wet fingerprint recognition program based on the humidity-adaptive optical storage device implements the steps of the wet fingerprint recognition method based on a humidity-adaptive optical storage device as described in any one of claims 1-5 on the computer-readable storage medium.

Images