Identification method of identification system

Abstract

The present invention provides an identification method for an identification system. The identification system includes a sensing area and an image sensor. First, the object to be detected approaches the sensing area, causing the image sensor to generate a dynamic image. Then, the object to be detected gradually pressurizes the sensing area. After that, the object to be detected completely covers the sensing area, and the image sensor further generates a perspective image. Finally, the identification module determines whether the dynamic image is a biological image based on the perspective image, and at the same time, performs a subtraction operation on the dynamic image as a basis for determining whether the identification system is unlocked. Therefore, the identification system of the present invention, in addition to achieving real-time determination of whether a dynamic image is a biological image by using the identification method, also performs a subtraction operation on the dynamic image through the identification method, thereby greatly improving the acceptance error rate and rejection error rate of the identification system, thereby achieving the goals of high accuracy and wide applicability.

Description

Technical Field

[0001] The present invention relates to an identification system, and in particular to an identification method of the identification system. Background Art

[0002] Fingerprint recognition technology has developed to the point where it's standard in most smartphones. Its advantages lie in the fact that fingerprints are unique to the human body and are complex enough for authentication. Furthermore, to increase reliability, simply register and authenticate more fingerprints, up to ten fingers, each unique. Furthermore, today's fingerprint scanning is incredibly fast and easy to use, a key reason why fingerprint recognition technology has captured a significant portion of the market.

[0003] However, fingerprint recognition isn't completely secure. People leave their fingerprints in public places every day, making it easy for someone to obtain or copy them. Once a fingerprint is recovered and used, personal devices and information could be compromised. Furthermore, while passwords can be reset even if they're cracked, fingerprints can't be reset. Therefore, improving the security and recognition capabilities of fingerprint recognition is a challenge researchers must address.

[0004] Furthermore, the recognition capability index is a key metric in fingerprint recognition technology. It represents an indicator for evaluating or comparing the performance of biometric security systems, including the False Acceptance Rate (FAR) and the False Rejection Rate (FRR). It should be further explained that the False Acceptance Rate (FAR) indicates the probability that a biometric system mistakenly identifies an illegitimate user as a legitimate one, effectively representing the system's security level; the False Rejection Rate (FRR) indicates the probability that a biometric system mistakenly identifies a legitimate user as an illegitimate one, effectively representing the system's convenience level. Therefore, reducing the False Acceptance Rate (FAR) and increasing the False Rejection Rate (FRR) remain key challenges for researchers.

[0005] Therefore, the inventors of this case came up with the present invention after observing the above-mentioned deficiencies. Summary of the Invention

[0006] The object of the present invention is to provide an identification method, which uses an image sensor to generate a dynamic image of an object to be detected within a time range. The dynamic image includes multiple interval images, wherein the time range includes multiple exposure intervals, and the multiple interval images become clearer as the time range becomes later, so that the image sensor further generates a perspective image. Whether the dynamic image has a change process and the perspective image are used to determine whether the dynamic image is a biological image. In this way, it is effectively prevented from others using fingerprint images, pictures, or any models to crack the identification system, and the security and identification capabilities of the identification system are greatly increased.

[0007] Another object of the present invention is to provide an identification method. This method, through a processing module executing an algorithm that performs a subtraction operation on dynamic images from different exposure intervals, significantly improves the ridge valley value (RV) of the dynamic images, resulting in improved fingerprint identification results. Consequently, the acceptance error rate (FAR) and rejection error rate (FRR) of the identification system according to the present invention are significantly improved, achieving high accuracy and wide applicability.

[0008] To achieve the above-mentioned purpose, the present invention provides an identification method, which is applied to an identification system, wherein the identification system includes a sensing area, an image sensor and an identification module, and the identification module is coupled to the sensing area and the image sensor. The identification method includes the following steps: a startup step, when the object to be detected contacts the sensing area, the image sensor is activated and generates a dynamic image for the object to be detected; a sensing step, when the object to be detected goes from contacting to covering the sensing area, so that the image sensor further generates a perspective image; and an identification step, if the object to be detected has one of the changing processes of the dynamic image and the perspective image, the identification module determines that the dynamic image is a biological image, otherwise, the identification module determines that the dynamic image is a non-biological image.

[0009] Preferably, according to the identification method of the present invention, the dynamic image includes multiple interval images generated by the object to be tested within a time range, and the identification module determines whether the dynamic image has the change process based on whether the clarity values ​​of the multiple interval images exceed a threshold value. When one of the clarity values ​​exceeds the threshold value, the identification module determines that the dynamic image has the change process.

[0010] Preferably, according to the identification method of the present invention, the clarity value is calculated by one of the image difference value method and the image gradient value.

[0011] Preferably, according to the recognition method of the present invention, the image sensor further includes: a plurality of photosensors arranged in an array, the plurality of photosensors being used to generate a plurality of image intensity information and generate the dynamic image through the plurality of image intensity information; a plurality of complementary metal-oxide semiconductors (CMOS) coupled to the plurality of photosensors, the plurality of CMOS being used to control the output of the plurality of image intensity information, however, the present invention is not limited thereto.

[0012] Preferably, according to the identification method of the present invention, the image sensor is disposed below the sensing area, and the image sensor has a shutter mechanism for controlling the exposure interval. However, the present invention is not limited thereto.

[0013] Preferably, according to the identification method of the present invention, the shutter mechanism is a global shutter (GS), so that the multiple light sensors are exposed simultaneously to generate the multiple image intensity information, but the present invention is not limited thereto.

[0014] In addition, to achieve the above-mentioned purpose, the present invention further provides an identification method for executing the above-mentioned identification system based on the above-mentioned identification system, which includes: an object to be detected approaches the sensing area, when the object to be detected contacts the sensing area, the image sensor is activated and generates a dynamic image for the object to be detected, and the dynamic image includes multiple interval images; a subtraction step, a processing module executes an algorithm to perform subtraction operations on the multiple interval images and generate multiple subtraction signals; a signal amplification step, an operation module amplifies the multiple subtraction signals by a multiple so that the peaks and troughs of the amplified multiple subtraction signals are clear and within the signal processing range; and an identification step, an identification module uses the amplified multiple subtraction signals as a basis for determining whether the identification system is unlocked.

[0015] Preferably, according to the identification method of the present invention, after executing the signal amplification step, the identification method further includes: an averaging step, wherein the calculation module takes an average value of the multiple subtraction signals; wherein the identification step further uses the average value as a basis for determining whether the identification system is unlocked through the identification module.

[0016] Preferably, the recognition method according to the present invention further includes a selection step, wherein the processing module uses one of the multiple interval images as a background interval image; wherein the subtraction step further performs a subtraction operation on the background interval image and the multiple interval images, and generates the multiple subtraction signals.

[0017] In summary, the identification method provided by the present invention mainly utilizes the image sensor of the present invention to generate a dynamic image for the object to be detected within a time range, wherein the time range includes multiple exposure intervals, and the longer the exposure interval, the clear value of the interval image of the dynamic image exceeds the threshold, and the image sensor further generates a perspective image to determine whether the dynamic image is a biological image based on whether the dynamic image has the said change process and the perspective image. In this way, it effectively prevents others from cracking the identification system with the image, picture, or any model of the fingerprint, and greatly increases the security and identification ability of the identification system. In addition, the algorithm is executed by the processing module, and the algorithm performs a subtraction operation on the dynamic images of different exposure intervals and then takes the average value, so that the RV value (ridge valley value) of the dynamic image according to the present invention is greatly improved, resulting in a better fingerprint recognition effect. Therefore, the acceptance error rate FAR and the rejection error rate FRR of the identification system according to the present invention are greatly improved, achieving the goals of high accuracy and wide applicability.

[0018] In order to enable those skilled in the art to understand the purpose, features and effects of the present invention, the present invention is described in detail below through the following specific embodiments and in conjunction with the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a schematic diagram of an identification system according to the present invention;

[0020] Figure 2 A block diagram illustrating the steps of executing the identification method of the present invention;

[0021] Figure 3 A flowchart illustrating the actual execution process of the identification method according to the present invention;

[0022] Figure 4 is a schematic diagram of an identification system according to a first embodiment of the present invention;

[0023] Figure 5 is a schematic diagram of an image sensor according to a first embodiment of the present invention;

[0024] Figure 6 A block diagram illustrating the steps of the identification method according to the first embodiment of the present invention;

[0025] Figure 7 A block diagram illustrating another step of executing the identification method according to the first embodiment of the present invention;

[0026] Figure 8 A flowchart illustrating the actual execution process of the identification method according to the first embodiment of the present invention;

[0027] Figure 9 is a schematic diagram of an identification system according to a second embodiment of the present invention;

[0028] Figure 10 A block diagram illustrating steps of an identification method according to a second embodiment of the present invention;

[0029] Figure 11A A schematic diagram illustrating an interval image according to a second embodiment of the present invention;

[0030] Figure 11B A schematic diagram illustrating the execution of an algorithm for interval images according to the second embodiment of the present invention;

[0031] Figure 12 A block diagram illustrating steps of an identification method according to a third embodiment of the present invention;

[0032] Figure 13A A schematic diagram illustrating the execution of an algorithm for interval images according to the third embodiment of the present invention;

[0033] Figure 13B This is another schematic diagram illustrating the execution of the algorithm for interval images according to the third embodiment of the present invention.

[0034] Description of reference numerals:

[0035] 100: Identification system; 11: Sensing area; 12: Image sensor; 121: Light sensor; 122: Complementary metal oxide semiconductor; 13: Identification module; 14: Processing module; 15: Calculation module; 21: Dynamic image; 22: Perspective image; 23, 23-1, 23-2, 23-3, 23-4, 23-5, 23-6: Interval image; 31: Time range; 32: Exposure interval; 200: Object to be tested; S11: Startup step; S12: Sensing step; S13: Identification step; S 21: Start step; S22: Subtraction step; S23: Identification step; S11': Start step; S12': Sensing step; S13': Calculation step; S14': Identification step; S21': Start step; S22': Subtraction step; S23': Signal amplification step; S24': Averaging step; S25': Identification step; S21': Start step; S22': Selection step; S23': Subtraction step; S24': Signal amplification step; S25': Averaging step; S26': Identification step. DETAILED DESCRIPTION

[0036] The present invention will now be described more fully below with reference to the accompanying drawings in which exemplary embodiments of the present invention are shown. The advantages and features of the present invention and how they are achieved will become apparent from the exemplary embodiments described in more detail below with reference to the accompanying drawings. However, it should be noted that the present invention is not limited to the following exemplary embodiments, but can be implemented in various forms. Therefore, the exemplary embodiments are provided only to disclose the present invention and to enable those skilled in the art to understand the categories of the present invention. In the drawings, exemplary embodiments of the present invention are not limited to the specific examples provided herein and are exaggerated for clarity.

[0037] The terms used herein are intended only to illustrate specific embodiments and are not intended to limit the present invention. Unless the context clearly indicates otherwise, the singular forms of the terms "a," "an," and "the" used herein are intended to include plural forms. The terms "and / or" used herein include any and all combinations of one or more of the relevant listed items. It should be understood that when a component is said to be "connected" or "coupled" to another component, the component may be directly connected or coupled to the other component or there may be intervening components.

[0038] Similarly, it should be understood that when a component (e.g., a layer, region, or substrate) is referred to as being "on" another component, the component can be directly on the other component or intervening components may be present. In contrast, the term "directly" means that there are no intervening components. It should be further understood that when the terms "include" and "comprising" are used herein, they indicate the presence of stated features, integers, steps, operations, components, and / or elements, but do not preclude the presence or addition of one or more other features, integers, steps, operations, components, elements, and / or groups thereof.

[0039] Furthermore, exemplary embodiments in the detailed description will be illustrated using cross-sectional views that serve as idealized exemplary views of the inventive concept. Accordingly, the shapes of the exemplary views may be modified based on manufacturing techniques and / or tolerable errors. Therefore, exemplary embodiments of the inventive concept are not limited to the specific shapes shown in the exemplary views but may include other shapes that may be produced based on manufacturing processes. The illustrated regions in the drawings are of a general nature and are used to illustrate specific shapes of components. Therefore, they should not be considered as limiting the scope of the inventive concept.

[0040] It should also be understood that although the terms "first," "second," "third," etc. may be used herein to describe various components, the components should not be limited by these terms. These terms are used only to distinguish between the various components. Thus, a first component in some embodiments may be referred to as a second component in other embodiments without departing from the teachings of the present invention. The exemplary embodiments of the aspects of the inventive concepts illustrated and described herein include their complementary counterparts. Throughout this specification, the same reference numerals or the same indicators represent the same components.

[0041] Furthermore, exemplary embodiments are described herein with reference to cross-sectional and / or plan views, which are idealized, exemplary illustrations. Therefore, deviations from the illustrated shapes due to, for example, manufacturing techniques and / or tolerances are to be expected. Therefore, exemplary embodiments should not be considered limited to the shapes of regions illustrated herein, but are intended to encompass deviations in shape due to, for example, manufacturing. Therefore, the regions illustrated in the figures are schematic, and their shapes are not intended to illustrate the actual shape of regions of a device or to limit the scope of exemplary embodiments.

[0042] See also Figures 1 to 4 As shown, Figure 1 is a schematic diagram of an identification system according to the present invention; Figure 2 A block diagram illustrating the steps of executing the identification method of the present invention; Figure 3 A flowchart illustrating the actual execution process of the identification method according to the present invention. Figure 1 As shown, the recognition system 100 according to the present invention includes a sensing area 11 , an image sensor 12 , and a recognition module 13 .

[0043] Specifically, the sensing area 11 according to the present invention is used for the object to be detected 200 to approach for sensing. In some embodiments, the sensing area 11 can serve as an isolation structure of the identification system 100. In the present invention, the term "isolation" covers both electrical isolation and physical isolation. The identification system 100 can be a single layer of inorganic packaging material, a multi-layer stack of inorganic packaging material, or a stack of paired inorganic packaging material and organic packaging material. The inorganic packaging material used is, for example, but not limited to, silicon nitride (SiNx), silicon oxide (SiOx), silicon oxynitride (SiONx), aluminum oxide (AlOx), or titanium oxide (TiOx), but the present invention is not limited thereto.

[0044] Specifically, the image sensor 12 according to the present invention is disposed below the sensing area 11. The image sensor 12 has a shutter mechanism (not shown). The image sensor 12 is used to generate a dynamic image 21 for the object under test 200 within a time range 31. The dynamic image 21 includes a plurality of interval images 23 ( Figure 423-1 to 23-8), the time range 31 includes multiple exposure intervals 32, the shutter mechanism is used to control the exposure intervals 32, and the exposure intervals 32 correspond to the interval images 23. In some embodiments, the image sensor 12 according to the present invention can be a complementary metal-oxide semiconductor (CMOS) image sensor, and can be selected from a back-illuminated CMOS image sensor or a front-illuminated CMOS image sensor, but the present invention is not limited thereto.

[0045] It should be further explained that in some embodiments, the image sensor 12 according to the present invention may have either a rolling shutter mechanism or a global shutter mechanism. When using a rolling shutter mechanism, due to the timing difference in exposure, when the image sensor 12 captures a dynamic image, the upper and lower halves of the interval image 23 may be exposed at different times. This may cause the upper half of the interval image 23 to appear before the lower end of the interval image 23, resulting in image distortion of the interval image 23. In a preferred embodiment of the present invention, since the present invention primarily targets the generation of dynamic images 21 of the object under test 200 within a time range 31, a global shutter mechanism is employed to avoid the jello effect in the interval images 23 of the dynamic image 21. Specifically, each pixel in all pixel arrays on the image sensor 12 simultaneously acquires the interval image 23 during the same exposure interval 32. However, the present invention is not limited to this embodiment.

[0046] Specifically, the recognition module 13 according to the present invention is coupled to the image sensor 12, and the recognition module 13 determines whether the dynamic image 21 is a biometric image based on the X-ray image 22. It should be further explained that in some embodiments, the object to be detected 200 may be a human fingerprint, and the X-ray image 22 may be a human vein or be associated with a human vein. The recognition module 13 may capture the X-ray image 22 of the finger vein via the image sensor 12, and use the X-ray image 22 as the basis for determining whether the dynamic image 21 is a biometric image. However, the present invention is not limited to this. In the present invention, the term "biometric image" refers to preventing others from using fingerprint images, pictures, or any other model to crack the recognition system 100.

[0047] It is worth noting that in some embodiments, the recognition system 100 according to the present invention can execute an algorithm (not shown) to perform a subtraction operation on the interval images 23 of different exposure intervals 32. This significantly improves the RV (ridge valley value) of the dynamic image 21 according to the present invention, resulting in better fingerprint recognition results. Furthermore, the subtraction operation described herein may refer to an operation that reduces noise by subtracting one of the multiple interval images 23. In a preferred embodiment of the present invention, the subtraction operation is performed by subtracting the interval image 23 of the previous exposure interval 32 from the interval image 23 of the next exposure interval 32, and the resulting values ​​are averaged after the subtraction operation is performed. It is understandable that conventional fingerprint recognition systems simply add interval images 23 from different exposure intervals 32 and then calculate the average value, or simply add the interval images 23 after subtracting the background value of nothing and then calculate the average value. However, due to the large difference between the subtracted background value and the interval images 23, the noise in the interval images 23 cannot be effectively subtracted. As a result, when the interval images 23 are amplified, the noise is also amplified simultaneously. In summary, the recognition system according to the present invention significantly improves the acceptance error rate (FAR) and rejection error rate (FRR) of the recognition system according to the present invention by executing an algorithm to perform a subtraction operation on the interval images 23 from different exposure intervals, thereby achieving high accuracy and wide applicability.

[0048] To further understand the structural features, applied technical means, and intended effects of the present invention, the following description of the use of the present invention is provided. It is believed that this description will provide a deeper and more detailed understanding of the present invention, as follows:

[0049] See also Figure 2 , and match Figure 4 As shown, the present invention is based on the above-mentioned identification system 100 and further provides an identification method of the identification system 100, comprising the following steps:

[0050] In the start step S11 , when the object to be tested 200 contacts the sensing area 11 , the image sensor 12 is started and generates a dynamic image 21 for the object to be tested 200 . The dynamic image 21 includes a plurality of interval images 23 , and then the sensing step S12 is performed.

[0051] In the sensing step S12 , the object to be detected 200 contacts and then completely covers the sensing area 11 , so that the image sensor 12 further generates a perspective image 22 , and then the recognition step S13 is executed.

[0052] In the recognition step S13 , if the object to be detected 200 has a dynamic image change process and a perspective image 22 , the recognition module 13 determines that the dynamic image 21 of the object to be detected 200 is a biological image.

[0053] It is worth mentioning that Figure 3 As shown, the identification system 100 according to the present invention can use the interval images 23 of different exposure intervals 32 within the time range 31 to identify the authenticity of the dynamic image 21 generated by the object 200 within the time range 31. For example, a disguised fingerprint may not be able to gradually increase in size and clarity within the time range 31 to produce a perspective image 22 like a fingerprint of a biological image. Therefore, if the change process of the dynamic image 21 within the time range 31 is abnormal, the identification system 100 according to the present invention can confirm that the dynamic image 21 is not a living thing, thereby further improving the identification accuracy of the present invention.

[0054] It should be further explained that in some embodiments, the recognition module 13 further determines whether the dynamic image 21 is a biological image based on whether the clarity value (not shown) of the interval image 23 of the dynamic image 21 during the change process exceeds a threshold value (not shown). The clarity value is calculated using either an image difference method or an image gradient method. The threshold value can be set by the user or generated by various algorithms (e.g., average calculation) and the clarity values ​​of past interval images 23. The image difference method primarily calculates the average value of the entire interval image 23. The image value of each point in the entire interval image 23 is subtracted from the average value and the absolute value is taken to obtain the difference between adjacent pixels. The difference is then averaged to obtain the clarity value. A larger clarity value indicates a clearer image. The image gradient value primarily uses a discrete differentiation operator to perform vertical and horizontal convolution operations on each image value of the interval image 23. The resulting image gradient value is used as the clarity value. A larger clarity value indicates a clearer image. However, the present invention is not limited to this method.

[0055] Therefore, the identification system 100 according to the present invention uses the image sensor 12 to generate a dynamic image 21 for the object to be detected 200 within a time range 31. The dynamic image 21 includes multiple interval images 23, wherein the time range 31 includes multiple exposure intervals 32. The interval images 23 become clearer as the time range 31 becomes later, so that the image sensor 12 further generates a perspective image 22. Based on the change process of the dynamic image 21 (not shown) and the perspective image 22, it is confirmed whether the dynamic image 21 is a biometric image. In this way, it is effectively prevented from others using fingerprint images, pictures, or any models to crack the identification system, and the security and identification capabilities of the identification system 100 are greatly increased.

[0056] See also Figure 4-8 As shown, Figure 4 is a schematic diagram of an identification system according to a first embodiment of the present invention;

[0057] Figure 5 is a schematic diagram of an image sensor according to a first embodiment of the present invention; Figure 6 A block diagram illustrating the steps of the identification method according to the first embodiment of the present invention; Figure 7 A block diagram illustrating another step of executing the identification method according to the first embodiment of the present invention; Figure 8 The following is a flowchart illustrating the actual execution process of the identification method according to the first embodiment of the present invention. Figure 4 As shown, the recognition system 100 according to the present invention includes a sensing area 11 , an image sensor 12 , a recognition module 13 , and a processing module 14 .

[0058] Specifically, see Figure 4 As shown, the recognition system 100 according to the first embodiment of the present invention further includes a processing module 14, which is coupled to the recognition module 13. The processing module 14 is used to execute an algorithm, which performs subtraction operations on the interval images 23 and generates multiple subtraction signals (not shown in the figure). However, the present invention is not limited to this.

[0059] Specifically, see Figure 5 As shown, the image sensor 12 according to the first embodiment of the present invention further includes a photosensor 121 and a complementary metal oxide semiconductor 122. The photosensors 121 are arranged in an array and are used to generate image intensity information (not shown) and generate a dynamic image 21 based on the image intensity information. The complementary metal oxide semiconductor 122 is coupled to the photosensor and is used to control the output of the image intensity information. It should be further explained that the image sensor 12 according to the first embodiment of the present invention can convert the image received by the image sensor 12 into red light, green light, and blue light through a color filter array (CFA), and generate image intensity information through the corresponding photosensors 121 to obtain stable dynamic image 21 quality. However, the present invention is not limited to this.

[0060] See also Figure 6 and Figure 8 As shown, according to the present invention, based on the identification system 100 of the first embodiment, a further identification method for executing the identification system 100 of the first embodiment is provided, which includes the following steps:

[0061] In the activation step S11 ′, when the object under test 200 contacts the sensing area 11 , the image sensor 12 is activated and generates a dynamic image 21 for the object under test 200 . The dynamic image 21 includes a plurality of interval images 23 , and then the sensing step S12 ′ is performed.

[0062] In the sensing step S12 ′, the object to be detected 200 moves from contacting to covering the sensing area 11 , causing the image sensor 12 to further generate a perspective image 22 , and then the calculation step S13 ′ is executed.

[0063] In the calculation step S13 ′, the processing module 14 calculates the clarity value of the interval image 23 within the time range 31 by using one of an image difference value method and an image gradient value, and then performs the identification step S14 ′.

[0064] In the identification step S14', the identification module 13 further determines whether the dynamic image 21 has a change process based on whether the clarity value of the interval image 23 exceeds a threshold. If the object to be tested 200 has a change process and has a perspective image 22, the identification module 13 determines that the dynamic image 21 is a biological image. Otherwise, the identification module 13 determines that the dynamic image 21 is not a biological image.

[0065] To further understand the structural features, applied technical means, and intended effects of the present invention, the actual implementation process of the first embodiment of the present invention is described below. It is believed that this will provide a deeper and more detailed understanding of the present invention, as described below:

[0066] See also Figure 8 , and match Figures 4 to 6 The actual execution process of the recognition system 100 according to the present invention is described as follows: First, the activation step S11' is executed. When the exposure interval 32 is 1, the object under test 200 contacts the sensing area 11, causing the image sensor 12 to be activated and generate the interval image 23-1 corresponding to the exposure interval 32 of 1 for the object under test 200. Next, the sensing step S12' is executed. When the exposure intervals 32 are 3 and 4, the object under test 200 contacts and completely covers the sensing area 11 to generate interval images 23-3 and 23-4, and the image sensor 12 further generates the perspective image 22. Then, a calculation step S13' is executed, in which the processing module 14 calculates the clarity value of the interval image 23 within the time range 31 using either an image difference value method or an image gradient value method. Finally, an identification step S14' is executed, in which the identification module 13 further determines whether the dynamic image 21 has a change process based on whether the clarity value of the interval image 23 exceeds a threshold value. If the object under test 200 has a change process and a perspective image 22, the identification module 13 determines that the dynamic image 21 is a biological image. Otherwise, the identification module 13 determines that the dynamic image 21 is not a biological image.

[0067] Therefore, as can be seen from the above description, the recognition system 100 according to the first embodiment of the present invention can determine whether the dynamic image 21 is a biometric image through the recognition module 13. Unlike the prior art that uses vascular vein recognition as an identification method, the recognition module 13 determines whether the dynamic image 21 is a biometric image based on whether the clarity value of the image 23 of the interval from the start step S11' to the sensing step S12 exceeds a threshold, and is combined with the perspective image 22 to determine whether the dynamic image 21 is a biometric image. This effectively prevents others from cracking the recognition system 100 using fingerprint images, pictures, or any other models. At the same time, the recognition results do not need to go through complex machine learning mechanisms and accumulate a large number of recognition features, which greatly improves the feasibility of offline recognition and has both wide applicability and high security.

[0068] See also Figure 7 , and match Figure 8 As shown, in this embodiment, the present invention further provides an identification method of the identification system 100 based on the identification system 100 of the first embodiment, comprising the following steps:

[0069] In the start step S21 , when the object to be detected 200 contacts the sensing area 11 , the image sensor 12 is started and generates a dynamic image 21 . The dynamic image 21 includes a plurality of interval images 23 , and then a subtraction step S22 is performed.

[0070] In the subtraction step S22 , the processing module 14 executes an algorithm to perform a subtraction operation on the interval image 23 and generate a subtraction signal (not shown), and then executes the recognition step S23 .

[0071] In the identification step S23 , the identification module 13 uses the subtraction signal as a basis for identifying whether the system is unlocked.

[0072] To further understand the structural features, technical means, and intended effects of the present invention, the actual implementation process of the present invention is described below. It is believed that this will provide a deeper and more detailed understanding of the present invention, as described below:

[0073] See also Figure 8 , and match Figures 4 to 7The actual execution process of the recognition system 100 according to the first embodiment of the present invention is described as follows: First, the activation step S11 is executed. When the exposure interval 32 is 1, the object under test 200 contacts the sensing area 11, causing the image sensor 12 to activate and generate interval images 23-5 to 23-8 corresponding to the exposure intervals 32 of 5 to 8. Next, the subtraction step S22 is executed. The interval image 23-8 is clearer than the previous interval images 23-5 to 23-7, and an algorithm is executed on the interval image 23. The algorithm performs a subtraction operation on the interval images 23 and generates a subtraction signal. Finally, the recognition module 13 uses the subtraction signal as the basis for determining whether the recognition system is unlocked.

[0074] It should be further explained that the interval image 23 may include multiple single-frame images generated within the exposure interval 32, and the subtraction signals generated by performing a subtraction operation on the interval images 23 may include multiple subtraction signals, not just a single one. The present invention can use any of these subtraction signals as the basis for determining whether the recognition system 100 is unlocked. In some embodiments, when multiple subtraction signals are present, the average of these subtraction signals can be used as the basis for determining whether the recognition system 100 is unlocked, but the present invention is not limited to this.

[0075] As can be seen from the above description, the recognition system 100 according to the first embodiment of the present invention further utilizes the processing module 14 to execute an algorithm that performs a subtraction operation on the interval images 23 of different exposure intervals 32. This significantly improves the RV (ridge valley value) of the dynamic image according to the present invention, resulting in better fingerprint recognition results. Consequently, the acceptance error rate (FAR) and rejection error rate (FRR) of the recognition system 100 according to the present invention are significantly improved, achieving high accuracy and wide applicability.

[0076] Hereinafter, with reference to the drawings, a first embodiment of the identification system 100 of the present invention will be described to enable a person skilled in the art to more clearly understand possible variations. Components indicated by the same reference numerals as above are substantially the same as those in the above reference numerals. Figure 1 The components, features, and advantages that are the same as those of the identification system 100 will not be described in detail.

[0077] The following provides other examples of the identification system 100 so that those skilled in the art can more clearly understand the possible variations. Figure 1 、 Figure 2 The components, features, and advantages that are the same as those of the identification system 100 will not be described in detail.

[0078] See also Figure 9-11B As shown, Figure 9 is a schematic diagram of an identification system according to a second embodiment of the present invention;

[0079] Figure 10 A block diagram illustrating steps of an identification method according to a second embodiment of the present invention; Figure 11A A schematic diagram illustrating an interval image according to a second embodiment of the present invention; Figure 11B This is a schematic diagram illustrating the execution of the algorithm for interval images according to the second embodiment of the present invention. Figure 9 As shown, the recognition system 100 according to the present invention includes: a sensing area 11 , an image sensor 12 , a recognition module 13 , a processing module 14 , and a calculation module 15 .

[0080] Specifically, the identification system 100 according to the second embodiment of the present invention further includes a computing module 15. The computing module 15 according to the second embodiment of the present invention amplifies the subtraction signal to ensure that the peaks and valleys of the amplified subtraction signal are clear and within the signal processing range. The computing module 15 can be either hardware or software with computing functions, but the present invention is not limited thereto.

[0081] It should be further explained that the processing module 14 according to the second embodiment of the present invention executes an algorithm to perform a subtraction operation on the interval images 23 of different exposure intervals 32 within the time range 31. The algorithm subtracts the interval image 23 of the subsequent exposure interval 32 within the time range 31 from the dynamic image of the previous exposure interval 31 and then calculates the average value. This differs from the prior art method of simply adding the interval images 23 of different exposure intervals 32 to calculate the average value, or simply adding the interval images 23 after subtracting the background value of nothing. The recognition system 100 according to the present invention can effectively eliminate noise in the dynamic image 21, significantly improving the ridge valley value (RV) of the dynamic image 21, and thus achieving better fingerprint recognition results.

[0082] It is worth mentioning that since both the processing module 14 and the computing module 15 are used to process the interval images 23, in some embodiments, the product of the algorithm that can perform subtraction operations on the interval images 23 usually also has the function of amplifying the subtraction signal. Therefore, the processing module 14 and the computing module 15 can be combined into the same role, but the present invention is not limited to this.

[0083] See also Figure 10 As shown, according to the present invention, based on the identification system 100 of the second embodiment, a further identification method for executing the identification system 100 of the second embodiment is provided, which includes the following steps:

[0084] In the activation step S21 ′, when the object to be detected 200 contacts the sensing area 11 , the image sensor 12 is activated and generates a dynamic image 21 . The dynamic image 21 includes a plurality of interval images 23 . Then, a subtraction step S22 ′ is performed.

[0085] In the subtraction step S22 ′, the processing module 14 executes an algorithm to perform a subtraction operation on the interval image 23 and generate a subtraction signal, and then performs a signal amplification step S23 ′.

[0086] In the signal amplification step S23 ′, the subtraction signal is amplified by the calculation module 15 so that the peaks and valleys of the amplified subtraction signal are clear and within the signal processing range. Then, the averaging step S24 ′ is performed.

[0087] In the averaging step S24 ′, the subtraction signal is averaged by the calculation module 15 , and then the identification step S25 ′ is performed.

[0088] In the identification step S25 ′, the identification module 13 takes an average value of the amplified subtraction signal as a basis for determining whether the system is unlocked.

[0089] Specifically, see Figure 11A and Figure 11B As shown, and with Figures 8 to 10 The actual execution of the algorithm process of the identification system 100 according to the second embodiment of the present invention is described as follows: Figure 11A As shown, Figure 11A To illustrate the intensity of the interval images 23-0, 23-4 to 23-8 when the exposure interval 32 is 60 microseconds, it should be further explained that the interval image 23-0 is the image intensity information generated when there is no object on the image sensor 12, which is the background value in the prior art. Figure 11B As shown, Figure 11B For the purpose of illustrative purposes, the interval images 23 (23-4 to 23-8) after executing the algorithm according to the second embodiment of the present invention and the interval image 23-0 after deducting the background value of nothing are compared. It can be understood that, since the fingerprint recognition system of the prior art only deducts the background value of nothing (i.e., 23-8 minus 23-0), the difference between the deducted background value and the interval image 23 is too large, resulting in the inability to effectively deduct the noise in the interval image 23, and the image intensity information does not decrease significantly. On the contrary, using the algorithm of the second embodiment of the present invention, the interval image 23 of the next exposure interval 32 within the time range 31 is subtracted from the interval image 23 of the previous exposure interval 32 (e.g., Figure 11BAs shown in FIG2 (23-5 minus 23-4, 23-7 minus 23-6, and 23-8 minus 23-7), effective noise removal in interval image 23 results in a significant decrease in image intensity information, significantly improving the RV (ridge valley value) of dynamic image 21 according to the present invention, resulting in better fingerprint recognition results. Consequently, the acceptance error rate (FAR) and rejection error rate (FRR) of the recognition system 100 according to the present invention are significantly improved, achieving high accuracy and wide applicability.

[0090] See also Figure 12-13B As shown, Figure 12 A block diagram illustrating steps of an identification method according to a third embodiment of the present invention; Figure 13A A schematic diagram illustrating a dynamic image after executing an algorithm according to a third embodiment of the present invention; Figure 13B This is another schematic diagram illustrating the execution algorithm of the dynamic image according to the third embodiment of the present invention. Figure 12 As shown, according to the present invention, based on the above-mentioned identification system 100, a recognition method for executing the recognition system 100 of the third embodiment is further provided, which includes the following steps:

[0091] In the starting step S21 ″, when the object to be detected 200 contacts the sensing area 11 , the image sensor 12 is started and generates a dynamic image 21 . The dynamic image 21 includes a plurality of interval images 23 . Then, the selecting step S22 ″ is executed.

[0092] After selecting step S22 ″, the processing module 14 uses an algorithm to select one of the interval images 23 as a background interval image (not shown), and then performs a comparison and subtraction step S23 ″.

[0093] In the subtraction step S23 ″, the processing module 14 executes an algorithm, which further performs a subtraction operation on the background interval image and the interval image 23 and generates a subtraction signal, and then performs a signal amplification step S24 ″.

[0094] In the signal amplification step S24 ″, the computing module 15 amplifies the subtraction signal by a multiple. The peaks and valleys of the amplified subtraction signal are clear and within the signal processing range. Then, the averaging step S25 ″ is performed.

[0095] In the averaging step S25 ″, the subtraction signal is averaged by the computing module 15 , and then the identification step S26 ″ is executed.

[0096] In the identification step S25 ″, the identification module 13 uses the amplified subtraction signal as a basis for identifying whether the system 100 is unlocked.

[0097] Specifically, see Figure 13A and Figure 13B As shown, and with Figure 12 The actual execution algorithm process of the recognition system 100 according to the third embodiment of the present invention is described as follows: Figure 13A As shown, Figure 13A To illustrate how the algorithm according to the third embodiment of the present invention selects different interval images 23 as background interval images, when the exposure interval 32 is 60 microseconds, the interval images 23 are deducted from different background interval images and compared with each other. It can be understood that, compared with the interval image 23 after deducting the background value of nothing in the prior art (i.e., 23-8 minus 23-0), when one of the better interval images 23 is selected as the background interval image through the selection step S22", the noise in the interval image 23 can be effectively eliminated, resulting in a significant decrease in image intensity information. It is worth mentioning that the algorithm according to the present invention can self-learn through a machine learning algorithm or a deep learning algorithm to automatically determine and select one of the better interval images 23 as the background dynamic image. The algorithm can be, but is not limited to, K-means clustering analysis (K-Means Clustering), ant colony optimization (ACO), and particle swarm optimization (PSO). Figure 13B As shown, Figure 13B To illustrate the amplification operation after deducting different background interval images from the interval image 23 according to the third embodiment of the present invention, since one of the better interval images 23 is selected as the background interval image in the selection step S22", the peaks and valleys of the image signal of the amplified interval image 23 are clear and within the signal processing range (such as Figure 13B The (23-8 minus 23-6)*4 and (23-8 minus 23-7)*4) shown in the figure effectively eliminate the noise in the interval image 23, resulting in a significant decrease in the image intensity information, so that the RV value (ridge valley value) of the dynamic image 21 after the amplification operation according to the present invention is further improved.

[0098] Therefore, the present invention has the following implementation effects and technical effects:

[0099] First, based on the identification system 100 of the present invention and in conjunction with the identification method provided by the present invention, the image sensor 12 generates a dynamic image 21 and a perspective image 22. The dynamic image 21 and the perspective image 22 are used to determine whether the dynamic image 21 is a biometric image. This effectively prevents others from cracking the identification system using fingerprint images, pictures, or any other model, and significantly increases the security and identification capabilities of the identification system.

[0100] Secondly, based on the recognition system 100 of the present invention and in conjunction with the recognition method provided by the present invention, an algorithm is executed that performs a subtraction operation on the interval images 23 of different exposure intervals 32 and then calculates the average value. This significantly improves the RV (ridge valley value) of the dynamic image according to the present invention, resulting in better fingerprint recognition results. Consequently, the acceptance error rate (FAR) and rejection error rate (FRR) of the recognition system 100 of the present invention are significantly improved, achieving high accuracy and wide applicability.

[0101] Third, unlike the prior art that uses vascular vein recognition as an identification method, the identification module 13 of the present invention determines whether the dynamic image 21 is a biometric image based on the changes in the dynamic image 21 and the fluoroscopic image 22. This dual authentication effectively prevents others from cracking the identification system 100 using fingerprint images, pictures, or arbitrary models. At the same time, the identification results do not require complex machine learning mechanisms and the accumulation of a large number of identification features, which greatly improves the feasibility of offline identification and combines wide applicability with high security.

[0102] Fourthly, in the third embodiment of the present invention, by selecting one of the better interval images 23 as the background interval image in step S23 ″, noise in the interval image 23 is effectively eliminated, resulting in a significant decrease in image intensity information, thereby further improving the RV value (ridge valley value) of the dynamic image 21 after the amplification operation according to the present invention.

[0103] The above describes the implementation of the present invention through specific embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification.

[0104] The above description is only a preferred embodiment of the present invention and is not intended to limit the scope of the present invention. Any equivalent changes or modifications that do not depart from the spirit disclosed by the present invention should be included in the following patent scope.

Claims

1. An identification method, characterized in that: The invention is applied to an identification system, wherein the identification system includes a sensing area, an image sensor, and an identification module. The identification module is coupled to the sensing area and the image sensor. The identification method includes the following steps: an activation step, wherein when the object to be detected contacts the sensing area, the image sensor is activated and generates a dynamic image of the object to be detected; a sensing step, wherein the object to be detected contacts and covers the sensing area, so that the image sensor generates a perspective image; and an identification step, wherein if the object to be detected has the changing process of the dynamic image and the perspective image, the identification module determines that the dynamic image is a biological image; Among them, the dynamic image includes: multiple interval images generated by the object to be tested within a time range, and the recognition module determines whether the dynamic image has the change process based on whether the clarity values ​​of the multiple interval images exceed a threshold. When one of the clarity values ​​exceeds the threshold, the recognition module determines that the dynamic image has the change process.

2. The identification method according to claim 1, characterized in that: The clarity value is calculated by one of an image difference value method and an image gradient value method.

3. The identification method according to claim 1, characterized in that: The image sensor further includes: a plurality of light sensors arranged in an array, the plurality of light sensors being used to generate a plurality of image intensity information, and generating the dynamic image through the plurality of image intensity information; A plurality of complementary metal oxide semiconductors are coupled to the plurality of light sensors, and the plurality of complementary metal oxide semiconductors are used to control the output of the plurality of image intensity information.

4. The identification method according to claim 3, characterized in that: The image sensor is disposed below the sensing area and has a shutter mechanism for controlling an exposure interval.

5. The identification method according to claim 4, characterized in that: The shutter mechanism is a global shutter, so that the multiple light sensors are exposed simultaneously to generate the multiple image intensity information.

6. An identification method, characterized in that: Applied to the identification system according to claim 1, the identification method comprises the following steps: an activation step, wherein when the object to be detected contacts the sensing area, the image sensor is activated and generates a dynamic image for the object to be detected, wherein the dynamic image includes a plurality of interval images; a subtraction step, wherein a processing module executes an algorithm to perform a subtraction operation on the plurality of interval images and generates a plurality of subtraction signals; a signal amplification step, wherein a computing module amplifies the plurality of subtraction signals by a multiple, so that the peaks and valleys of the amplified plurality of subtraction signals are clear and within a signal processing range; as well as an identification step, wherein the identification module uses the amplified subtraction signals as a basis for determining whether the identification system is unlocked; After executing the signal amplification step, the identification method further includes: an averaging step, wherein the calculation module calculates an average value of the multiple subtraction signals; and the identification step further uses the average value as a basis for determining whether the identification system is unlocked by the identification module.

7. The identification method according to claim 6, characterized in that: After executing the starting step, the identification method further includes: a selection step, wherein the processing module uses one of the plurality of interval images as a background interval image; The subtraction step further performs a subtraction operation on the background interval image and the plurality of interval images, and generates the plurality of subtraction signals.

Images