Flexible touch sensing structure and handwriting digit recognition method thereof
By optimizing the arrangement of the feature and base regions of the flexible touch sensing structure and combining it with convolutional neural network algorithms, the problem of the inability to encrypt and protect digital input methods in flexible tactile human-computer interfaces has been solved, achieving high security and high accuracy in digital recognition.
Patent Information
- Application Number
- CN202411636119.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-11-15
- Publication Date
- 2025-11-28
- Estimated Expiration
- 2044-11-15
AI Technical Summary
In existing flexible tactile human-machine interfaces, most digital input methods rely on simple pulse signal detection, which cannot achieve information encryption protection.
A flexible touch sensing structure was designed. By optimizing the arrangement of the feature region and the substrate region, utilizing a combination of ion conductor material and flexible insulating polymer, and combining grayscale distribution map to optimize the sensing structure, a digital recognition algorithm based on convolutional neural network was adopted to achieve multiple encryption functions.
It improves the accuracy of digital recognition, enhances the portability and privacy of the authenticator, provides multiple layers of encryption protection, and improves information security.
Smart Images
Figure CN119512402B_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to a flexible touch sensing structure and a handwriting digit recognition method thereof, and belongs to the field of biometric identity authenticators. BACKGROUND
[0002] With the continuous development of electronic devices, the traditional rigid human-computer interface is increasingly unable to meet the growing needs of modern users for portability and comfort. This has driven the rise of flexible human-computer interfaces, which are often used in wearable devices. This flexibility expands the application range of smart devices, enabling them to play a more important role in health monitoring, virtual reality, and other fields. Haptics is one of the most basic means of perceiving the interaction between living beings and the environment, which has enabled haptic interaction to be widely used in the field of flexible human-computer interaction. As an ionic conductor, organic gel has a Young's modulus similar to that of biological tissues and organs, and has excellent deformation ability. In addition, compared with traditional hydrogels, organic gels are more durable. Therefore, various flexible haptic human-computer interfaces based on ionic organic gels have emerged. However, existing research has mainly focused on the basic haptic response of ionic organic gels, with sensitive elements arranged in a full-coverage form in the detection area, and has not optimized the haptic sensing structure for specific application scenarios. Therefore, it is of great significance to further study the response of ionic organic gels to haptic signals and optimize the sensing structure.
[0003] In the field of human-computer interaction, the input function of numbers is an indispensable part. As a globally used number system, Arabic numerals have great significance in daily life and various professional fields such as identity authentication, financial management, and personal communication. Therefore, the security of number input is very important. Information security can seriously threaten our normal life, business development, company operation, and even national security. In existing flexible haptic human-computer interfaces, the number input method is mostly simple pulse signal detection, which cannot achieve encryption protection of information. Therefore, it is necessary to build a flexible haptic human-computer interface with multiple encryption functions. SUMMARY
[0004] In view of the problem that in existing flexible haptic human-computer interfaces, the number input method is mostly simple pulse signal detection, which cannot achieve encryption protection of information, the present application provides a flexible touch sensing structure and a handwriting digit recognition method thereof.
[0005] The flexible touch sensing structure of the present application comprises a feature area and a substrate area.
[0006] The feature area is made of an ionic conductor material, and the substrate area is made of a flexible insulating polymer.
[0007] The gray scale distribution map is obtained by superimposing the gray scales of multiple handwritten digit images.
[0008] The area with the highest and lowest probability distribution of the handwriting in the gray scale distribution map is the base area, and the area with the probability distribution of the handwriting between the highest and the lowest is the feature area.
[0009] As preferred, the handwriting image is derived from the MNIST handwriting database.
[0010] As preferred, the feature area is prepared by the organic gel, and the base area is made of silica gel.
[0011] The application also provides a preparation method of the flexible touch sensing structure, comprising:
[0012] S1, preparing a mold according to the flexible touch sensing structure;
[0013] S2, mixing the silicone oil and the silica gel thoroughly for 5 minutes;
[0014] S3, degassing the mixture in a vacuum dryer for 30 minutes;
[0015] S4, pouring the degassed mixture into the mold and heating to 70℃ for 20 minutes to solidify the mixture in the mold, to obtain the prepared silica gel base;
[0016] S5, soaking the prepared silica gel base in a 10wt% benzophenone / ethanol solution at room temperature for 3 minutes, then cleaning with methanol and thoroughly drying with nitrogen;
[0017] S6, pouring the organic gel precursor solution into the dried silica gel base, and irradiating with a 365nm, 20W ultraviolet lamp for 10 minutes to fully solidify the organic gel and bond with the silica gel base, thereby obtaining the assembly of the organic gel and the silica gel base.
[0018] S7, soaking the obtained assembly in an ethylene glycol solution for 60 minutes to promote solvent replacement, to complete the preparation of the flexible touch sensing structure.
[0019] As preferred, the organic gel precursor solution comprises 16wt% acrylamide, 0.048wt% N,N'-methylenebisacrylamide, 10wt% sodium chloride, 0.1wt% photoinitiator 2-hydroxy-2-methyl-1-phenyl-1-propanone and deionized water.
[0020] As preferred, the organic gel and the silica gel in the flexible touch sensing structure are subjected to dyeing treatment, and the organic gel and the silica gel are different in color.
[0021] As preferred, in S1, the mold of the flexible touch sensing structure is prepared by 3D printing.
[0022] The application also provides a handwriting digit recognition method of the flexible touch sensing structure, comprising:
[0023] An alternating voltage is provided for the flexible touch sensing structure, a handwritten digit acts on the flexible touch sensing structure, and a single-channel sensing signal response of the organic gel is collected to obtain a corresponding voltage signal;
[0024] A training set is constructed using the handwritten digit and the obtained corresponding voltage signal;
[0025] A detection network is trained using the constructed training set, the input of the detection network being a voltage signal and the output being a handwritten digit;
[0026] A handwritten digit to be recognized acts on the flexible touch sensing structure, and a voltage signal of the flexible touch sensing structure is collected,
[0027] The voltage signal is input into the trained detection network for detection, and the detection network outputs a detection result.
[0028] As a preferred embodiment, an alternating signal with a peak voltage of 1V and a frequency of 1MHz is provided for the flexible touch sensing structure by connecting a metal electrode to the corners of the organic gel in the flexible touch sensing structure.
[0029] As a preferred embodiment, the detection network includes an input layer, a convolution layer, a pooling layer, a flattening layer, a fully connected layer, and an output layer connected in sequence.
[0030] The present application has the advantages that the flexible touch sensing structure obtained by the flexible touch sensing structure topology optimization method based on the handwriting probability distribution can promote the development of a flexible touch human-machine interface with multiple encryption functions. The flexible touch sensing structure of the present application can detect the bioelectricity, digital writing trajectory and speed of an individual, thereby realizing double encryption through biometric recognition and handwriting recognition. In addition, the flexible touch sensing structure of the present application has good flexibility and wearability, thereby enhancing the portability and privacy of the authenticator and improving the encryption protection. Compared with the traditional full-coverage sensing structure, the optimized structure increases the digital recognition accuracy by 107.91% when the flexible touch sensing structure of the present application is combined with the corresponding control circuit and the digital recognition algorithm based on the convolutional neural network. BRIEF DESCRIPTION OF DRAWINGS
[0031] Figure 1 A schematic diagram of the principle of the sensing structure topology optimization method of the present application;
[0032] Figure 2 A photo of the flexible touch sensing structure after the sensing structure topology optimization of the present application;
[0033] Figure 3 This is a schematic diagram illustrating the principle of the detection network in the handwritten digit recognition method of the present invention;
[0034] Figure 4 This refers to the change in sensitivity before and after topology optimization in this invention.
[0035] Figure 5 Comparison of handwritten digit recognition accuracy before and after topology optimization;
[0036] Figure 6 Output voltage waveforms when using a flexible touch sensing structure to handwrite digits for different users. Detailed Implementation
[0037] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.
[0038] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other.
[0039] The present invention will be further described below with reference to the accompanying drawings and specific embodiments, but this is not intended to limit the scope of the invention.
[0040] This implementation method is based on the MNIST handwritten digit database, and performs grayscale overlay on 500 sets of handwritten digit images, such as... Figure 1 As shown in the diagram, each image in this database contains a digit written within a standardized square region. After overlaying 5000 images, a grayscale distribution map of this square region was obtained. The higher the grayscale value of the square region, the lower the probability of the digit's handwriting appearing in that region. The grayscale is divided into three parts. The region with the highest grayscale indicates almost no handwriting, while the region with the lowest grayscale indicates that almost every digit's handwriting appears in that region. In the sensing detection of handwritten digits, the regions with the highest and lowest probabilities of handwriting appearance are not the primary focus of sensing detection. Instead, the intermediate regions of the probability distribution can serve as feature regions for more targeted digit handwriting detection. Therefore, the distribution of the organic gel on a two-dimensional plane can be optimized based on the grayscale distribution of handwritten digits. Specifically, a two-dimensional detection plane was constructed using a combination of an ionic conductor and a flexible insulating polymer substrate, with the ionic conductor placed in the feature region and the flexible insulating polymer placed in the regions with the highest and lowest probabilities of handwriting appearance.
[0041] The flexible touch sensing structure of the embodiment comprises a feature region and a substrate region; the feature region is made of an ion conductor material, which can be selected from conductive hydrogel, organic gel and the like, preferably organic gel, and the substrate region is made of a flexible insulating polymer, which can be selected from Ecoflex, silicone, PDMS, preferably; a plurality of handwritten digital images are superimposed in grayscale to obtain a grayscale distribution map;
[0042] The regions with the highest and lowest probability distribution of handwriting in the grayscale distribution map are the substrate regions, and the regions with the probability distribution of handwriting between the highest and the lowest are the feature regions.
[0043] The preparation of the flexible touch sensing structure of the embodiment comprises the following steps:
[0044] First, a 3D printed flexible touch sensing structure is obtained by using a 3D printing flexible touch sensing structure to obtain a 3D printing mold;
[0045] An appropriate amount of silicone oil (500 cSt) is mixed with the A and B components of the silicone (in a weight ratio of 1.25:1:1) for 5 minutes;
[0046] Then, the mixture is degassed in a vacuum dryer for 30 minutes.
[0047] Next, the mixture is poured into the 3D printing mold and heated to 70°C for 20 minutes to allow it to solidify. At this stage, a silicone substrate without organic gel adhesion is obtained.
[0048] To ensure strong adhesion between the silicone and the organic gel and prevent the organic gel from falling off when the flexible touch sensing structure is deformed, a surface treatment is performed in the next step. The prepared silicone substrate is soaked in a 10wt% benzophenone / ethanol solution at room temperature for 3 minutes, then washed with methanol and thoroughly dried with nitrogen. Next, the organic gel precursor solution is poured into the silicone substrate, and irradiated with a 365nm, 20W ultraviolet lamp for 10 minutes to allow the hydrogel to fully solidify and adhere to the silicone substrate. The entire assembly is then soaked in an ethylene glycol solution for 60 minutes to promote solvent replacement, and finally a flexible touch sensing structure is obtained. The organic gel precursor solution in the embodiment comprises 16wt% acrylamide, 0.048wt% N,N'-methylenebisacrylamide, 10wt% sodium chloride, 0.1wt% photoinitiator 2-hydroxy-2-methyl-1-phenyl-1-propanone and deionized water.
[0049] The final flexible touch sensing structure is shown in Figure 2 Since both the organic gel and the silicone are transparent, dyeing treatment is performed for better visualization.
[0050] In addition to the flexible touch sensing structure, the handwriting digit recognition method of the embodiment also needs to be matched with hardware and software to realize the recognition of handwriting digits. The hardware control circuit includes a signal generation module and a signal acquisition module. The signal generation module is connected to the corners of the organic gel in the flexible touch sensing structure through a metal electrode, and provides an alternating current signal with a peak voltage of 1V and a frequency of 1MHz for the organic gel. The signal acquisition module acquires the single-channel sensing signal response of the organic gel during touch, and reflects the touch information in the form of voltage. The handwriting digit recognition method includes:
[0051] providing an alternating voltage for the flexible touch sensing structure, and a handwriting digit acting on the flexible touch sensing structure, while acquiring the single-channel sensing signal response of the organic gel to obtain a corresponding voltage signal;
[0052] constructing a training set by using the handwriting digit and the corresponding voltage signal obtained;
[0053] training a detection network by using the constructed training set, wherein the input of the detection network is the voltage signal, and the output of the detection network is the handwriting digit;
[0054] acquiring a voltage signal of the flexible touch sensing structure when a handwriting digit to be recognized acts on the flexible touch sensing structure,
[0055] inputting the voltage signal into the trained detection network for detection, and outputting a detection result by the detection network.
[0056] In order to classify and recognize handwriting digits, the detection network of the embodiment uses a convolutional neural network signal classification algorithm. As shown in Figure 3 the single-dimensional time series voltage signal acquired by the hardware control circuit is used as the input data of the convolutional neural network, and sequentially passes through the input layer, the convolutional layer, the pooling layer, the flattening layer, and the fully connected layer, and the output layer outputs the classification result of the digit.
[0057] Verification:
[0058] A traditional full-coverage structure organic gel with the same size was prepared using a similar processing method for comparison. The position close to the electrode was defined as the detection origin, and the output voltage at this time was defined as the initial voltage U0. The change of the output voltage relative to the initial voltage at different contact points was recorded, as shown in Figure 4 Compared with the traditional full-coverage structure, the optimized sensing structure shows higher sensitivity. In addition, due to the existence of the non-sensing area, the output potential difference between some adjacent contact points increases, breaking the symmetry and continuity of the output voltage in the traditional full-coverage sensing structure, which helps to more accurately recognize the touch trajectory during handwriting digit.
[0059] The output voltage of different handwritten digits under two sensor structures was collected for convolutional neural network model training. Specifically, for each sensor structure, 40 groups of data were collected for each digit. Of which, 80% of the data was used as the training set, and the remaining data was used as the test set. As shown in Figure 5 Fig. 3, the flexible touch sensor structure after structure optimization achieved a recognition accuracy of 97.53%, while the traditional full-coverage structure only achieved an accuracy of 46.91%. For the optimized sensor structure, the time output signals of different digits were significantly different, while in the traditional full-coverage structure, the time output signals of different digits were similar, making it difficult to effectively distinguish the digits even using the CNN algorithm.
[0060] During the detection of handwritten digits by the flexible touch sensor structure, the human body impedance, writing trajectory and speed, and the change of the digit will all affect the output response signal. Therefore, using the flexible touch sensor structure to input a password provides multiple encryption capabilities. The impedance of the human body is determined by the individual's physiological characteristics. In addition, writing as an important method in criminal investigation and analysis has a high degree of encryption. As shown in Figure 6 Fig. 4, thanks to the multi-layer encryption, when two people write the same digit password, the output voltage waveform shows significant differences, effectively reducing the risk of digit password leakage, demonstrating the feasibility of the flexible touch sensor structure in encrypted information transmission.
[0061] While the application has been described with reference to particular embodiments, it will be understood that the examples are merely illustrative of the principles and applications of the present application. It will be understood that numerous modifications can be made to the illustrative embodiments, and that other arrangements can be devised without departing from the spirit and scope of the present application as defined by the appended claims. It will be understood that the features of the various embodiments can be combined with each other, in different ways than as described herein. It will be understood that features described with respect to one embodiment can be used in other embodiments described herein.
Claims
1. A flexible touch sensing structure, characterized in that, Includes feature regions and basal regions; The feature region is made of an ion-conducting material, and the substrate region is made of a flexible insulating polymer; Multiple handwritten digit images are superimposed in grayscale to obtain a grayscale distribution map; The regions with the highest and lowest handwriting probability distribution in the grayscale distribution image are the base regions, and the regions with handwriting probability distribution between the highest and lowest are the feature regions. The feature region is prepared from an organic gel, and the base region is made of silicone.
2. The flexible touch sensing structure according to claim 1, characterized in that, The handwritten digit images are derived from the MNIST handwritten digit database.
3. The method for fabricating the flexible touch sensing structure according to claim 1, characterized in that, The preparation method includes: S1. Prepare a mold according to the flexible touch sensing structure; S2. Mix the silicone oil and silicone thoroughly for 5 minutes; S3. Degas the mixture in a vacuum dryer for 30 minutes; S4. Pour the degassed mixture into the mold and heat it to 70°C for 20 minutes to solidify the mixture in the mold and obtain the prepared silicone substrate. S5. The prepared silica substrate is immersed in a 10wt% benzophenone / ethanol solution for 3 minutes at room temperature, then washed with methanol and thoroughly dried with nitrogen. S6. Pour the organic gel precursor solution into the dried silicone substrate and irradiate it with a 365nm, 20W ultraviolet lamp for 10 minutes to allow the organic gel to fully solidify and bond with the silicone substrate, thereby obtaining an assembly of organic gel and silicone substrate. S7. Immerse the obtained component in an ethylene glycol solution for 60 minutes to promote solvent replacement and complete the fabrication of the flexible touch sensing structure.
4. The method for fabricating the flexible touch sensing structure according to claim 3, characterized in that, The organogel precursor solution comprises 16 wt% acrylamide, 0.048 wt% N,N'-methylenebisacrylamide, 10 wt% sodium chloride, 0.1 wt% photoinitiator 2-hydroxy-2-methyl-1-phenyl-1-propanone, and deionized water.
5. The method for fabricating the flexible touch sensing structure according to claim 3, characterized in that, The organic gel and silicone in the flexible touch sensing structure were dyed to produce different colors.
6. The method for fabricating the flexible touch sensing structure according to claim 3, characterized in that, In step S1, a mold is prepared by 3D printing according to the flexible touch sensing structure described in claim 1.
7. A handwritten digit recognition method based on the flexible touch sensing structure of claim 1, characterized in that, Handwritten digit recognition methods include: An AC voltage is provided to the flexible touch sensing structure, and handwritten digits are applied to the flexible touch sensing structure. At the same time, the single-channel sensing signal response of the organic gel is collected to obtain the corresponding voltage signal. A training set was constructed using handwritten digits and the corresponding voltage signals. The detection network is trained using the constructed training set. The input of the detection network is a voltage signal, and the output is a handwritten digit. The handwritten digit to be recognized is applied to the flexible touch sensing structure, the voltage signal of the flexible touch sensing structure is collected, and the voltage signal is input into the trained detection network. The detection network outputs the detection result.
8. The handwritten digit recognition method according to claim 7, characterized in that, The flexible touch sensing structure is provided with an AC signal with a peak voltage of 1V and a frequency of 1MHz by connecting metal electrodes to the corners of the organic gel.
9. The handwritten digit recognition method according to claim 7, characterized in that, The detection network comprises an input layer, a convolutional layer, a pooling layer, a flattening layer, a fully connected layer, and an output layer connected in sequence.