Information processing device

Abstract

To improve the accuracy of fingerprint matching. [Solution] The information processing device of the present disclosure comprises a generation unit that generates a core wire image by extracting core wires from a fingerprint image, an extraction unit that extracts feature quantities based on the fingerprint image and the core wire image, and a matching unit that compares the feature quantities with registered feature quantities that have been registered in advance.

Description

Technical Field

[0001] The present disclosure relates to an information processing apparatus.

Background Art

[0002] Patent Document 1 describes that a skeleton image is generated from a fingerprint image, and feature points of a fingerprint are extracted from the skeleton image to perform collation. Patent Document 1 also describes that the skeleton image can be edited.

Prior Art Literature

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problem to be Solved by the Invention

[0004] However, since the skeleton in the skeleton image is a line indicating the center in the width direction of the ridge of a fingerprint, when the quality of the original fingerprint image is low, the quality of the skeleton image also decreases, and the quality of feature points may also decrease. As a result, there arises a problem that it is impossible to improve the accuracy of fingerprint collation using the skeleton image.

[0005] Therefore, one object of the present disclosure is to solve the above-mentioned problem that improvement of fingerprint collation accuracy cannot be achieved.

Means for Solving the Problem

[0006] An information processing apparatus according to one aspect of the present disclosure includes: a generation unit configured to generate a skeleton image obtained by extracting a skeleton from a fingerprint image; an extraction unit configured to extract a feature quantity based on the fingerprint image and the skeleton image; a collation unit configured to collate the feature quantity with a pre-registered registered feature quantity; with the above configuration. ​Furthermore, the information processing method, which is one form of this disclosure, Information processing device, A core wire image is generated by extracting the core wires from the fingerprint image. A feature quantity is extracted based on the fingerprint image and the core wire image. The aforementioned feature is compared with a pre-registered registered feature. This is the structure it takes. Furthermore, one form of this disclosure is a program, In an information processing device, A core wire image is generated by extracting the core wires from the fingerprint image. A feature quantity is extracted based on the fingerprint image and the core wire image. The aforementioned feature is compared with a pre-registered registered feature. To execute the process This is the structure it takes. [Effects of the Invention]

[0007] This disclosure, when configured as described above, can improve the accuracy of fingerprint matching. [Brief explanation of the drawing]

[0008] [Figure 1] This block diagram shows an example of the configuration of the information processing device in this disclosure. [Figure 2] This flowchart shows an example of processing operations by the information processing device described in this disclosure. [Figure 3] This figure shows an example of processing by the information processing device described in this disclosure. [Figure 4] This figure shows an example of processing by the information processing device described in this disclosure. [Figure 5] This is a block diagram showing an example of the hardware configuration of the information processing device in this disclosure. [Figure 6] This block diagram shows an example of the configuration of the information processing device in this disclosure. [Figure 7] This flowchart shows an example of processing operations by the information processing device described in this disclosure. DESCRIPTION OF EMBODIMENTS

[0009] <First Embodiment> A first embodiment of the present disclosure will be described with reference to the drawings. Note that the drawings can be related to any of the embodiments.

[0010] As an example, the information processing apparatus of the present disclosure is used for collating fingerprints. Specifically, the information processing apparatus generates a skeleton image from a fingerprint image, extracts a feature amount using the fingerprint image and the skeleton image, and collates the extracted feature amount with a fingerprint registered in a database. Examples of situations for fingerprint collation include a situation where a latent fingerprint collected at the scene of an incident or accident is collated with a fingerprint registered in a database in advance. However, the present disclosure is applicable to fingerprint collation in any situation.

[0011] An example of the configuration and operation of the information processing apparatus according to the present embodiment will be described below. The information processing apparatus is configured by one or a plurality of information processing apparatuses including an arithmetic device and a storage device. As shown in FIG. 1, the information processing apparatus 10 includes a skeleton image extraction unit 11, a feature amount extraction unit 12, a feature amount registration unit 13, a collation unit 15, a candidate display unit 16, a similarity display unit 17, a skeleton superimposition display unit 18, and a skeleton image correction unit 19. Each function of the skeleton image extraction unit 11, the feature amount extraction unit 12, the feature amount registration unit 13, the collation unit 15, the candidate display unit 16, the similarity display unit 17, the skeleton superimposition display unit 18, and the skeleton image correction unit 19 can be realized by the arithmetic device executing a program stored in the storage device for realizing each function. The information processing apparatus 10 also includes a feature amount database 14 implemented by a storage device.

[0012] First, information on fingerprints of a large number of persons is registered in advance in the feature quantity database 14. Specifically, registered feature quantities, which are feature quantities extracted from fingerprint images collected from persons, are registered in the feature quantity database 14. The registered feature quantities are feature quantities extracted based on a fingerprint image and a skeleton image, as will be described later. In addition, registered skeleton feature quantities, which are feature quantities extracted based on skeleton images, are also registered in the feature quantity database 14. Furthermore, in the feature quantity database 14, together with the registered feature quantities and the registered skeleton feature quantities, the fingerprint image and the skeleton image from which each feature quantity is extracted, and information on the person from whom the fingerprint was collected and the finger are associated and registered.

[0013] The skeleton image extraction unit 11 (generation unit) accepts input of a fingerprint image D1 to be collated (step S1 in Fig. 2). For example, the skeleton image extraction unit 11 accepts input of a fingerprint image obtained using an imaging device, a scanner, or the like. Note that the fingerprint image D1 is, for example, an image of a latent fingerprint collected at the site of an incident or accident. Here, since latent fingerprints often have low quality due to defects, blurring, or the like, this may result in low collation accuracy, so the present disclosure performs the following processing.

[0014] The skeleton image extraction unit 11 generates a skeleton image D2 by extracting a skeleton from the fingerprint image D1 (step S2 in Fig. 2). For example, the skeleton image extraction unit 11 performs image analysis on the fingerprint image D1, extracts a skeleton indicating the center in the width direction of fingerprint ridges, and generates a skeleton image on which the extracted skeleton is drawn.

[0015] The feature extraction unit 12 (extraction unit) extracts feature quantities D3 using the original fingerprint image D1 and the generated core line image D2 (step S3 in Figure 2). Specifically, as an intermediate process, the feature extraction unit 12 extracts fingerprint features from the fingerprint image D1 and core line features from the core line image D2, and then extracts the final feature quantity D3 based on the fingerprint features and core line features. At this time, the fingerprint features are extracted as vectors representing the features of the entire fingerprint image, for example, using local features such as ridge ends and branching points in the fingerprint image, or using a fingerprint feature extraction model constructed by a neural network. The core line features are extracted as vectors representing the features of the entire core line image, for example, using features based on the core line pattern, such as the number of core lines, the arrangement of intersections and branching points, the length and angle distribution of the core lines, or using a core line feature extraction model constructed by a neural network. The feature extraction unit 12 then integrates the fingerprint features and the core wire features to extract the final feature D3 based on the fingerprint image D1 and the core wire image D2. The integration of the fingerprint features and the core wire features can be performed in any way, such as simply concatenating the vectors or calculating them by performing calculations using the vectors according to a pre-set calculation formula.

[0016] Furthermore, the fingerprint features and wireframe features are not limited to the features ultimately output by the fingerprint feature extraction model and wireframe feature extraction model, but may also be features output by the intermediate layers of each model. Also, the fingerprint features and wireframe features are not necessarily limited to being represented as vectors and may be represented in any data format. Accordingly, the final integrated feature D3 is also not limited to being represented as a vector and may be represented in any data format.

[0017] Furthermore, the feature extraction unit 12 may assign weights to the fingerprint features and the core line features respectively, depending on the extraction status of the fingerprint features and the core line features, and extract the final feature D3 based on the weighted fingerprint features and core line features. In this case, the feature extraction unit 12 may extract feature D3 by assigning weights to each region of the fingerprint image and core line image. That is, the feature extraction unit 12 may calculate feature D3 by increasing the weight of the fingerprint features in regions with high weight in the fingerprint image, and by increasing the weight of the core line features in regions with high weight in the core line image. For example, in regions of low quality such as those with defects or blurring in the fingerprint image, feature extraction becomes difficult, and the weight of the fingerprint features is set low in such regions. Also, for example, in regions where the core lines are clearly visible and the probability is high, the weight of the core line features is set high. However, weights may be assigned to each region according to any criteria. As a more generalized example of this weighting, one could use a neural network structure called a cross-attention module, where fingerprint images and wireframe images are two different inputs.

[0018] The feature extraction unit 12 does not necessarily need to extract fingerprint features and core wire features; it may also extract feature D3. For example, the feature extraction unit 12 may extract feature D3 based on an image obtained by integrating the fingerprint image and the core wire image. Alternatively, the feature extraction unit 12 may be constructed using a machine learning model that takes the fingerprint image and the core wire image as input and outputs feature D3.

[0019] Furthermore, the feature extraction unit 12 may perform a preprocessing step to correct the position and orientation of each image before extracting feature D3 from the fingerprint image and the core line image. For example, the feature extraction unit 12 may refer to the core line image to estimate and correct the position and orientation of the fingerprint image and the core line image, and then extract feature D3 based on the corrected fingerprint image and the core line image.

[0020] The feature registration unit 13, as necessary, registers the feature D3 extracted from the input fingerprint image as described above, along with the person information, in the feature database 14. For example, if the person in the input fingerprint image is identified, the extracted feature D3 may be registered in the feature database 14. In this case, in addition to feature D3, the original fingerprint image and core line image, and further core line features extracted from the core line image, may also be registered in the feature database 14.

[0021] The matching unit 15 compares the feature quantities D3 extracted from the fingerprint image and the core wire image with the registered feature quantities stored in the feature quantity database 14 (step S4 in Figure 2). Specifically, the matching unit 15 calculates a matching score that represents the similarity or match between the extracted feature quantities D3 and the registered feature quantities stored in the feature quantity database 14. For example, if the feature quantities D3 are represented as vectors, the distance between the vectors may be calculated as the matching score. In this case, the matching score is calculated so that the value is higher for registered feature quantities that match feature quantities D3 to a higher degree.

[0022] The matching unit 15 may calculate a matching score for each region of the fingerprint. For example, the matching unit 15 divides the fingerprint image into multiple regions and calculates a matching score for each region by matching the corresponding feature quantity D3 with the registered feature quantity. In this case, the matching unit 15 may calculate a matching score for each pixel of the fingerprint image. In this case, the matching score between the feature quantity D3 and the registered feature quantity may be calculated including a predetermined range of regions surrounding the pixel for which the matching score is to be calculated, and this may be used as the matching score for the target pixel.

[0023] The candidate display unit 16 (matching unit) displays fingerprint images corresponding to registered features that are candidates that match the extracted feature quantity D3 on the display device according to the matching result (step S5 in Figure 2). For example, as shown in the "candidates" column in Figure 3, the candidate display unit 16 displays multiple matching candidate fingerprint images in descending order of matching score. In the example in Figure 3, the fingerprint image and core line image of the fingerprint from which the feature quantity D3 to be matched has been extracted are superimposed in the "query" column on the left, and when the "search" button is operated, the top three fingerprint images with the highest matching scores are displayed in the "candidates" column on the right, with the fingerprint image with the highest matching score displayed at the top.

[0024] The candidate display unit 16 may display only one fingerprint image, or it may display many more fingerprint images. In this case, the candidate display unit 16 may also display core wire images in addition to fingerprint images, for example, by displaying them in parallel or superimposed on each other. Furthermore, the candidate display unit 16 may display thumbnail images of fingerprint images, or it may display identification information for fingerprint images. Moreover, the candidate display unit 16 is not necessarily required to display fingerprint images, and may instead display person information associated with the fingerprint images.

[0025] The similarity display unit 17 (matching unit) outputs information on the matching score for the fingerprint image along with the displayed fingerprint image according to the matching result (step S6 in Figure 2). As an example, as shown in Figure 3, the similarity display unit 17 overlays the matching score for each region of the fingerprint image onto the fingerprint image, represented by grayscale values. By overlaying the local matching score as a heatmap onto the fingerprint image in this way, it is easy to understand which regions of the fingerprint image have high similarity and which parts have low similarity. The similarity display unit 17 may also display matching score information for all fingerprint images displayed as candidates, as shown in the "candidates" column in Figure 3. Furthermore, the similarity display unit 17 is not necessarily limited to displaying local matching scores, but may also display the overall matching score.

[0026] The core wire superimposed display unit 18 (correction unit) displays the input fingerprint image and the generated core wire image as described above (step S7 in Figure 2). In particular, the core wire superimposed display unit 18 displays the fingerprint image and the core wire image superimposed, as shown in the "query" column in Figure 3. At this time, the core wire superimposed display unit 18 displays an "edit" button and a "search" button below the superimposed display, as shown in Figure 3. When the "search" button is operated, matching is performed as described above, and candidate fingerprint images that match are displayed in the "candidates" column. When the "edit" button is operated, the core wire image correction unit 19 can correct the core wire image.

[0027] The core wire superimposed display unit 18 is not necessarily limited to displaying the fingerprint image and the core wire image superimposed. The core wire superimposed display unit 18 may display the fingerprint image and the core wire image on the same screen, such as by displaying them side by side, or it may display only the fingerprint image or only the core wire image.

[0028] The core wire image correction unit 19 (correction unit) accepts corrections to core wires from the user on the displayed core wire image (step S8 in Figure 2). For example, the core wire image correction unit 19 accepts instructions from the user to add or delete core wires on a superimposed display of the fingerprint image and core wire image as shown in Figure 3. For example, the core wire image correction unit 19 adds or deletes core wires to the core wire image in response to input from the user, such as dragging with a mouse or stylus pen, or operation of the add or delete instruction buttons. Here, Figure 4 shows an example of the superimposed display of the fingerprint image and core wire image before correction and the superimposed display of the fingerprint image and core wire image after correction. By checking the superimposed display of the fingerprint image and core wire image before correction, the user can recognize missing or excessive core wires and correct them to create a more appropriate core wire image.

[0029] The core wire image correction unit 19 may display the fingerprint image and the core wire image side by side in the image display before correction, and may accept corrections to the core wire image in this situation. Alternatively, the core wire image correction unit 19 may display only the core wire image in the image display before correction, and may accept corrections to the core wire image in this situation.

[0030] Then, as described above, the corrected core wire image may be used again to calculate feature quantity D3. In other words, the feature extraction unit 12 may calculate feature quantity D3 using the fingerprint image and the corrected core wire image in the same manner as described above (step S3 in Figure 2). Accordingly, the matching unit 15 may perform matching again and display the fingerprint image, etc., based on the matching result (steps S4 to S6 in Figure 2).

[0031] As described above, this disclosure extracts features using both fingerprint images and core line images, allowing for the extraction of appropriate features for each fingerprint through mutual complementation, thereby improving matching accuracy. Furthermore, by displaying both the fingerprint image and core line image, the core line image can be modified, allowing for the extraction of even more appropriate features. In addition, the similarity of candidate fingerprints is visualized, enabling efficient narrowing down of candidates.

[0032] <Second Embodiment> Next, a second embodiment of the present disclosure will be described. The information processing device in this embodiment has the same configuration as the first embodiment described above. In addition, the information processing device has the following configuration. The following will mainly describe the configuration that differs from the above.

[0033] In this embodiment, the matching unit 15 of the information processing device performs matching in two stages. Specifically, in the first stage, the matching unit 15 performs matching using the core line feature quantities of the core line image generated from the input fingerprint image. That is, the matching unit 15 compares the extracted core line feature quantities with the registered core line feature quantities stored in the feature quantity database 14. The feature quantity database 14 is assumed to contain registered feature quantities based on the fingerprint image and core line image, as well as registered core line feature quantities based on the core line image, as information on each person's fingerprint. However, the registered core line feature quantities may be generated from the registered fingerprint image and extracted from the core line image.

[0034] The matching unit 15 then identifies and narrows down a predetermined number of registered core wire feature quantities that have high matching scores based on their matching with the core wire feature quantities. For example, the matching unit 15 identifies the top 100 registered core wire feature quantities based on their matching scores and narrows down the fingerprints of these registered core wire feature quantities as candidates. This excludes fingerprints from the candidates that are clearly judged to be dissimilar to the core wire feature quantities.

[0035] Next, in the second stage, the matching unit 15 performs a comparison between the feature quantity D3 based on the fingerprint image and core wire image being matched and the registered feature quantity registered in relation to the narrowed-down registered core wire feature quantity. The matching method at this time is the same as described above. Then, depending on the matching result, the matching unit 15 displays the fingerprint image with the highest matching score or displays the local matching score as a heat map, as described above.

[0036] As described above, this disclosure ensures accuracy while reducing the load by performing feature matching in stages. As a result, fingerprint matching can be performed efficiently even on large databases.

[0037] <Third Embodiment> Next, a third embodiment of this disclosure will be described with reference to the drawings. The drawings may be relevant to any of the embodiments.

[0038] The information processing device in this embodiment has the same configuration as in embodiments 1 and 2 described above. The candidate display unit 16 in this embodiment has the function of generating and outputting information based on the matching results, for example, a matching report. For example, the candidate display unit 16 is configured by fine-tuning a VLM (Vision-Language Model) using a set of fingerprint images and core wire images and corresponding text data (for example, a report summarizing the matching results) as training data. In this case, the text data includes information such as the content of the matching results, supplementary explanations for the matching results, the status of local matching scores, the status of feature extraction, and the modification history of the core wires.

[0039] As a result, the candidate display unit 16 can output text data of the report content regarding the matching results, etc., by inputting the fingerprint image and core wire image that are the subject of matching. Therefore, a matching report is automatically generated, reducing operational costs and improving user convenience.

[0040] <Fourth Embodiment> Next, a fourth embodiment of this disclosure will be described with reference to the drawings. This embodiment shows an outline of the information processing device, etc., described in the embodiments described above. Note that the drawings may be relevant to any of the embodiments.

[0041] First, the hardware configuration of the information processing device 100 in this disclosure will be described. The information processing device 100 is composed of a general information processing device, and as an example, it is equipped with the following hardware configuration as shown in Figure 5. ·CPU(Central Processing Unit)101(Arithmetic unit) ROM (Read Only Memory) 102 (Storage Device) • RAM (Random Access Memory) 103 (Storage Device) • Program group 104 loaded into RAM 103 • Storage device 105 for storing the program group 104 • Drive device 106 for reading and writing to external storage medium 110 of the information processing device. • Communication interface 107 connecting to a communication network 111 outside the information processing device. • Input / output interface 108 for data input and output. • Bus 109 connecting each component

[0042] Figure 5 shows an example of the hardware configuration of the information processing device 100, and the hardware configuration of the information processing device is not limited to the case described above. For example, the information processing device may consist of only a part of the configuration described above, such as not having a drive device 106. In addition, the information processing device may use a GPU (Graphic Processing Unit), DSP (Digital Signal Processor), MPU (Micro Processing Unit), FPU (Floating point number Processing Unit), PPU (Physics Processing Unit), TPU (Tensor Processing Unit), quantum processor, microcontroller, or a combination thereof instead of the CPU described above.

[0043] The information processing device 100 can be equipped with the generation unit 121, extraction unit 122, and verification unit 123 shown in Figure 6 by having the CPU 101 acquire the program group 104 and execute it. The program group 104 is, for example, stored in advance in a storage device 105 or ROM 102, and the CPU 101 loads it into RAM 103 and executes it as needed. The program group 104 may also be supplied to the CPU 101 via a communication network 111, or it may be stored in advance in a storage medium 110, and the drive device 106 reads the program and supplies it to the CPU 101. However, the generation unit 121, extraction unit 122, and verification unit 123 described above may be constructed with dedicated electronic circuits to realize such means.

[0044] The generation unit 121 generates a core wire image by extracting the core wire from the fingerprint image (step S101 in Figure 7). The extraction unit 122 extracts feature quantities based on the fingerprint image and the core wire image (step S102 in Figure 7). The matching unit 123 compares the feature quantities with pre-registered registered feature quantities (step S103 in Figure 7).

[0045] In the above configuration, the information processing device 100 first extracts feature quantities using both the fingerprint image and the core wire image. Then, the information processing device 100 compares the extracted feature quantities with registered feature quantities. In this way, the present disclosure makes it possible to extract appropriate feature quantities for a fingerprint by mutual complementation of the fingerprint image and the core wire image, thereby improving the matching accuracy.

[0046] Furthermore, at least one of the functions of the generation unit 121, extraction unit 122, and matching unit 123 described above may be performed on an information processing device installed and connected to any location on the network, that is, it may be performed using so-called cloud computing.

[0047] Furthermore, the aforementioned programs can be stored and supplied to a computer using various types of non-transitory computer-readable media. Non-transitory computer-readable media include various types of tangible storage media. Examples of non-transitory computer-readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-R / Ws, and semiconductor memory (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (Random Access Memory)). Programs may also be supplied to a computer using various types of transient computer-readable media. Examples of transient computer-readable media include electrical signals, optical signals, and electromagnetic waves. Transitory computer-readable media can be supplied to a computer via wired communication channels such as electric wires and optical fibers, or via wireless communication channels.

[0048] Although the present disclosure has been described above with reference to embodiments, the present disclosure is not limited to the embodiments described above. Various modifications to the structure and details of the present disclosure are possible, as can be understood by those skilled in the art within the scope of the present disclosure. Furthermore, each of the embodiments described above can be combined with other embodiments as appropriate.

[0049] <Note> Some or all of the above embodiments may also be described as follows. The general configuration of the information processing apparatus, information processing method, and program in this disclosure is described below. However, this disclosure is not limited to the configurations described below. Furthermore, some or all of the configurations and functions described in Appendices 2 to 8, which are dependent on Appendice 1 below, may also be dependent on Appendices 9 and 10 in the same way as Appendices 2 to 8. Moreover, not limited to Appendices 1, 9, and 10, some or all of the configurations and functions described as appendices may also be dependent on similar hardware, software, various recording means for recording software, or systems, without departing from the embodiments described above. (Note 1) A generation unit that generates a core wire image by extracting the core wire from a fingerprint image, An extraction unit that extracts feature quantities based on the fingerprint image and the core wire image, A matching unit that compares the aforementioned feature quantity with a pre-registered registered feature quantity, Equipped with an information processing device. (Note 2) The information processing device described in Appendix 1, The system includes a correction unit that displays the fingerprint image and the core wire image and accepts corrections to the core wire image, The extraction unit extracts the feature quantities based on the fingerprint image and the modified core wire image. Information processing device. (Note 3) The information processing device described in Appendix 2, The correction unit superimposes the fingerprint image and the core wire image and accepts corrections to the core wire image. Information processing device. (Note 4) The information processing device described in Appendix 1, The extraction unit extracts the feature quantities based on the fingerprint feature quantities extracted from the fingerprint image and the core wire feature quantities extracted from the core wire image. Information processing device. (Note 5) The information processing device described in Appendix 4, The extraction unit assigns weights to the fingerprint feature and the core wire feature, respectively, according to the extraction status of the fingerprint feature and the core wire feature, and extracts the feature based on the weighted fingerprint feature and the core wire feature. Information processing device. (Note 6) The information processing device described in Appendix 1, The extraction unit extracts core wire features from the core wire image, The matching unit performs a comparison between the core wire feature quantity and the registered core wire feature quantity associated with the registered feature quantity, identifies the registered feature quantity based on the comparison result, and further performs a comparison between the feature quantity and the identified registered feature quantity. Information processing device. (Note 7) The information processing device described in Appendix 1, The matching unit compares the feature quantity with the registered feature quantity, calculates the similarity for each fingerprint location, and outputs it. Information processing device. (Note 8) The information processing device described in Appendix 7, The matching unit outputs the fingerprint image corresponding to the matched registered feature quantity, with the similarity at each fingerprint position superimposed on it. Information processing device. (Note 9) Information processing device, A core wire image is generated by extracting the core wire from the fingerprint image. A feature quantity is extracted based on the fingerprint image and the core wire image. The aforementioned feature is compared with a pre-registered feature. Information processing methods. (Note 9.1) The information processing method described in Appendix 9, The aforementioned information processing device The fingerprint image and the core wire image are displayed, and a modification of the core wire image is accepted. The feature quantities are extracted based on the fingerprint image and the modified core wire image. Information processing methods. (Note 10) In an information processing device, A core wire image is generated by extracting the core wire from the fingerprint image. A feature quantity is extracted based on the fingerprint image and the core wire image. The aforementioned feature is compared with a pre-registered feature. A program that executes a process. [Explanation of Symbols]

[0050] 11 Core wire image extraction unit 12 Feature Extraction Unit 13 Feature Registration Section 14 Feature Database 15. Verification section 16 Candidate display area 17 Similarity display area 18. Core wire superimposed display section 19 Core wire image correction section 100 Information Processing Devices 101 CPU 102 ROM 103 RAM 104 Program Groups 105 Storage device 106 Drive unit 107 Communication Interface 108 Input / Output Interfaces 109 Bus 110 Storage medium 111 Communication Network 121 Generation part 122 Extraction part 123 Verification section

Claims

1. A generation unit that generates a core wire image by extracting the core wire from a fingerprint image, An extraction unit that extracts feature quantities based on the fingerprint image and the core wire image, A matching unit that compares the aforementioned feature quantity with a pre-registered registered feature quantity, Equipped with an information processing device.

2. An information processing apparatus according to claim 1, The system includes a correction unit that displays the fingerprint image and the core wire image and accepts corrections to the core wire image, The extraction unit extracts the feature quantities based on the fingerprint image and the modified core wire image. Information processing device.

3. An information processing apparatus according to claim 2, The correction unit superimposes the fingerprint image and the core wire image and accepts corrections to the core wire image. Information processing device.

4. An information processing apparatus according to claim 1, The extraction unit extracts the feature quantities based on the fingerprint feature quantities extracted from the fingerprint image and the core wire feature quantities extracted from the core wire image. Information processing device.

5. An information processing apparatus according to claim 4, The extraction unit assigns weights to the fingerprint feature and the core wire feature, respectively, according to the extraction status of the fingerprint feature and the core wire feature, and extracts the feature based on the weighted fingerprint feature and the core wire feature. Information processing device.

6. An information processing apparatus according to claim 1, The extraction unit extracts core wire features from the core wire image, The matching unit performs a comparison between the core wire feature quantity and the registered core wire feature quantity associated with the registered feature quantity, identifies the registered feature quantity based on the comparison result, and further performs a comparison between the feature quantity and the identified registered feature quantity. Information processing device.

7. An information processing apparatus according to claim 1, The matching unit compares the feature quantity with the registered feature quantity, calculates the similarity for each fingerprint location, and outputs it. Information processing device.

8. An information processing apparatus according to claim 7, The matching unit outputs the fingerprint image corresponding to the matched registered feature quantity, with the similarity at each fingerprint position superimposed on it. Information processing device.

9. Information processing device, A core wire image is generated by extracting the core wire from the fingerprint image. A feature quantity is extracted based on the fingerprint image and the core wire image. The aforementioned feature is compared with a pre-registered feature. Information processing methods.

10. In an information processing device, A core wire image is generated by extracting the core wire from the fingerprint image. A feature quantity is extracted based on the fingerprint image and the core wire image. The aforementioned feature is compared with a pre-registered feature. A program that executes a process.

Images