Image Processing Device
The image processing device calculates distortion coefficients from a two-dimensional code to correct image distortions, enhancing authentication accuracy without requiring camera-specific calibration, addressing the inefficiencies of traditional calibration methods.
Patent Information
- Application Number
- JP2020185948
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2020-11-06
- Publication Date
- 2024-11-14
- Estimated Expiration
- 2040-11-06
AI Technical Summary
Existing camera calibration processes are time-consuming and difficult to implement for each camera, especially in fisheye and wide-angle cameras, due to variations in camera parameters, necessitating a solution that allows distortion correction without prior camera calibration.
An image processing device that calculates distortion coefficients using a two-dimensional code with embedded facial feature point information, allowing distortion correction based on pixel and three-dimensional coordinates, without the need for a dedicated calibration chart.
Enables efficient distortion correction of captured images, including fisheye images, by calculating distortion coefficients directly from the two-dimensional code, improving authentication accuracy and reducing the need for camera-specific calibration.
Smart Images

Figure 0007583250000004 
Figure 0007583250000005 
Figure 0007583250000006
Abstract
Description
[Technical field]
[0001] The present invention relates to an image processing device that corrects distortion in a captured image and performs processing using the corrected image. [Background technology]
[0002] In a captured image of a subject captured by a fisheye camera using a fisheye lens, the subject is captured in a distorted manner, and depending on the processing using the captured image, the distortion in the captured image may need to be corrected. As a technique for correcting the distortion in a captured image in this way, for example, a calibration system disclosed in Patent Document 1 below is known. In this calibration system, a calibration device is configured to obtain image data of a calibration chart captured by the imaging device, and perform calibration calculations based on the data, thereby deriving camera parameters such as a distortion correction coefficient, internal parameters, and external parameters of the camera of the imaging device. By using the camera parameters derived in this way, a correction process can be performed to suppress distortion in the captured image of the imaging device. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] Patent No. 6764533 Summary of the Invention [Problem to be solved by the invention]
[0004] However, since individual differences in cameras can cause variations in inherent camera parameters, the variations become large, and therefore camera calibration may be required for calculating distortion correction coefficients and the like for each camera. That is, camera calibration may be required for each camera in advance, such as before product shipment, which may make it difficult to shorten process work time. Such camera calibration problems may occur not only in fisheye cameras using fisheye lenses and wide-angle cameras using wide-angle lenses, but also in cameras using general imaging lenses.
[0005] The present invention has been made to solve the above-mentioned problems, and an object of the present invention is to provide a configuration capable of correcting distortion in a captured image without performing camera calibration for each camera in advance. [Means for solving the problem]
[0006] In order to achieve the above object, an image processing device (20) according to claim 1 of the present invention comprises: an imaging section (23) having an imaging lens and an imaging element that captures an image through the imaging lens; a distortion coefficient calculation unit (21) that calculates a distortion coefficient for correcting distortion of an image captured by the imaging unit; a distortion correction unit (21) that corrects distortion of the captured image of the imaging unit based on the distortion coefficient calculated by the distortion coefficient calculation unit; a processing unit (21) that performs processing using a corrected image whose distortion has been corrected by the distortion correction unit; Equipped with The distortion coefficient calculation unit calculates the distortion coefficient based on pixel coordinates of each of the coordinate comparison cells that are at least a part of the multiple cells in an image captured by the imaging unit of a two-dimensional code (C) in which a multiple number of cells are arranged, and based on three-dimensional position coordinates of each of the cells of the two-dimensional code that correspond to the coordinate comparison cells. death, a decoding unit that performs a decoding process for decoding the two-dimensional code on an image of the two-dimensional code captured by the imaging unit, In the two-dimensional code, facial feature point information regarding facial feature points extracted from a facial image of a user is recorded, The processing unit performs authentication processing for the user by using the facial feature point information obtained as a result of decoding by the decoding unit and facial feature points extracted from the facial image of the user captured by the imaging unit and whose distortion has been corrected by the distortion correction unit. It is characterized by: The symbols in parentheses above indicate the corresponding relationship with the specific means described in the embodiments described later. Effect of the Invention
[0007] In the invention of claim 1, the distortion of the image captured by the imaging unit is corrected by the distortion correction unit based on the distortion coefficient calculated by the distortion coefficient calculation unit, and the processing unit performs processing using this corrected image. The distortion coefficient calculation unit calculates distortion coefficients based on pixel coordinates that are the coordinates of each of the coordinate comparison cells that are at least a part of the multiple cells in the captured image captured by the imaging unit of a two-dimensional code consisting of an array of multiple cells, and each of the three-dimensional position coordinates of the cells of the two-dimensional code that correspond to the coordinate comparison cells.
[0008] In this way, since the distortion coefficient is calculated using the captured two-dimensional code, the distortion coefficient can be easily calculated without preparing a dedicated calibration chart, etc. Therefore, since the two-dimensional code can be captured and the distortion coefficient can be calculated every time processing using the captured image is performed, the distortion of the captured image can be corrected based on the calculated distortion coefficient without performing camera calibration for each camera in advance.
[0009] Claim 4 Even in a configuration in which the imaging unit functions as a fisheye camera by using a fisheye lens as the imaging lens, as in the invention described above, by calculating a distortion coefficient using the captured two-dimensional code each time processing using a fisheye image is performed, the distortion of the fisheye image can be corrected based on the calculated distortion coefficient.
[0010] Claim 1In the invention, a decoding unit is provided that performs a decoding process for decoding the two-dimensional code on the captured image of the two-dimensional code captured by the imaging unit, and a processing unit performs processing using the correction image using the decoding result by the decoding unit. This allows the distortion coefficient to be calculated from the captured image of the two-dimensional code in order to obtain the decoding result, and there is no need to capture a two-dimensional code that does not need to be decoded just to calculate the distortion coefficient, making the processing more efficient.
[0011] Claim 1 In the invention, facial feature point information relating to facial feature points extracted from the user's face image is recorded in the two-dimensional code, and the processing unit performs user authentication processing using the facial feature point information obtained as a result of decoding by the decoding unit and the facial feature points extracted from the user's face image captured by the imaging unit and whose distortion has been corrected by the distortion correction unit. This not only makes it possible to calculate a distortion coefficient from the captured image of the two-dimensional code captured to obtain the facial feature point information, but also to correct the distortion of the user's face image from which the facial feature points are extracted based on the distortion coefficient, thereby improving the authentication accuracy of the authentication processing.
[0012] Claim 2 In the invention, since information on the size of the cells of the two-dimensional code is recorded in the two-dimensional code, the actual shape of the captured two-dimensional code can be accurately grasped. This makes it easier to accurately calculate the three-dimensional position coordinates of each cell of the two-dimensional code corresponding to the coordinate comparison cell, thereby improving the calculation accuracy of the distortion coefficient, i.e., the distortion correction accuracy of the captured image.
[0013] Claim 5 In the invention, the distortion coefficient calculation unit calculates the distortion coefficient based on the pixel coordinates and three-dimensional position coordinates of the two-dimensional code captured multiple times. This makes it easier to suppress the influence of camera shake during image capture compared to when the distortion coefficient is calculated based on the pixel coordinates and three-dimensional position coordinates of the two-dimensional code from a single captured image, thereby improving the calculation accuracy of the distortion coefficient, i.e., the distortion correction accuracy of the captured image.
[0014] Claim 6 In the invention, the two-dimensional code is displayed on a screen, and therefore there is no risk of the two-dimensional code itself being distorted when imaged due to being printed on paper or the like, thereby improving the accuracy of calculation of the distortion coefficient, i.e., the accuracy of distortion correction of the captured image. [Brief description of the drawings]
[0015] [Figure 1] FIG. 1 is an explanatory diagram illustrating a schematic configuration of an authentication system including an image processing device according to a first embodiment. [Diagram 2] 1 is an explanatory diagram illustrating a part of an example of a portion from which facial feature points are extracted from captured facial image data; [Diagram 3] FIG. 2 is a block diagram illustrating an electrical configuration of the image processing device. [Figure 4] FIG. 2 is a block diagram illustrating an electrical configuration of the mobile terminal. [Diagram 5] 11 is a part of a flowchart illustrating a flow of authentication processing by the image processing device. [Figure 6] 11 is a part of a flowchart illustrating a flow of authentication processing by the image processing device. [Figure 7] FIG. 2 is an explanatory diagram illustrating the relationship between a camera coordinate system and a pixel coordinate system. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS
[0016] [First embodiment] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment of an authentication system including an image processing device according to the present invention will be described below with reference to the drawings. The authentication system 10 shown in FIG. 1 mainly includes an image processing device 20, and is configured as a system for performing personal authentication of a user by utilizing a two-dimensional authentication code (hereinafter also referred to as authentication code C) in which facial feature points extracted from a face image of the user, personal information, etc. are recorded.
[0017] In this embodiment, the authentication system 10 is employed in, for example, an entrance / exit management system in which a user who has successfully passed face authentication is permitted to enter a specific room. The user carries a mobile terminal 30 as an information code recording medium having an authentication code C, and is permitted to enter the specific room when authentication is successful by performing an operation to cause an image processing device 20 installed at the entrance to the specific room to capture an image of the authentication code C displayed on the screen of the mobile terminal 30. Specifically, authentication success information is transmitted from the image processing device 20 to a locking / unlocking control device that controls the locking / unlocking of an electric lock installed at the door at the entrance, and the electric lock is unlocked by the locking / unlocking control device, thereby permitting entry into the specific room.
[0018] The authentication code C is configured as a two-dimensional code, specifically, a QR code (registered trademark), in which a plurality of light-colored cells and dark-colored cells are arranged, and is generated by a predetermined code generating device that acquires face image data from a user who applies for personal authentication. This code generating device extracts facial feature points from the facial image data acquired from the user, and generates the authentication code C by encoding facial feature point information related to the facial feature points and personal information of the user as well as information on the size of the cells (hereinafter, simply referred to as cell size) and the like. In this embodiment, items such as the size and shape of each of the facial organs such as the eyes, eyebrows, nose, ears, and mouth, the outline, and the arrangement positions of the facial organs relative to each other are adopted as the facial feature points. Then, according to a facial feature point extraction process for extracting known facial feature points performed by the code generating device, for example, for the acquired facial image data D as exemplified in FIG. 2, features for each item, such as data such as "D1: long, narrow eyes" and "D2: large mouth", are calculated and extracted as facial feature points. Then, in accordance with a known information code generation process performed by a code generation device, an authentication code C is generated by encrypting the information related to the facial feature points extracted as described above, personal information, cell size, etc. in a decryptable manner using a decryption key (encryption key).
[0019] Next, the image processing device 20 will be described with reference to FIGS. The image processing device 20 is configured as an authentication device that authenticates a user by using an authentication code C displayed on the screen of the mobile terminal 30, and is installed at the entrance to the specific room, specifically, at a position at eye level of the user on a wall surface near the door provided at the entrance. As shown in Fig. 3, the image processing device 20 includes a control unit 21, a storage unit 22, an imaging unit 23, a display unit 24, an illumination unit 25, an operation unit 26, a communication unit 27, etc.
[0020] The control unit 21 is mainly configured with a microcomputer, and performs overall control of the image processing device 20 and various calculations, and functions to execute the authentication process described below. The storage unit 22 is configured with known storage media such as ROM, RAM, HDD, non-volatile memory, and has application programs for executing the authentication process, a predetermined database, and the like stored in advance so as to be usable by the control unit 21. The storage unit 22 also stores a decryption key for decrypting the authentication code C in advance.
[0021] The imaging unit 23 is configured as a camera having an imaging lens and an imaging element (e.g., a C-MOS area sensor, a CCD area sensor, etc.) that captures an image through the imaging lens, and is configured so that image data of the captured image captured through a reading window (imaging window) is output to the control unit 21. In this embodiment, the imaging unit 23 is configured as a fisheye camera that can capture a wider range by employing a fisheye lens as the imaging lens.
[0022] In the control unit 21, as described below, distortion of the user's face image captured by the imaging unit 23 is corrected, and then facial feature points are extracted by performing a facial feature point extraction process on this corrected image in the same manner as in the above-mentioned code generation device. Also, in the control unit 21, a decoding process is performed on the captured image of the authentication code C captured by the imaging unit 23, using a decryption key stored in the storage unit 22 to decode the encrypted authentication code C, thereby obtaining facial feature point information, cell size, and the like recorded in the authentication code C as the decoding result.
[0023] 1, the display unit 24 is configured to be controlled by the control unit 21 so as to change its lit / blinking state depending on the success or failure of extraction of facial feature points, the result of authentication processing, etc. Due to such an arrangement, the imaging unit 23 is placed at a position within the visual field of the user who is looking at the display unit 24.
[0024] The illumination unit 25 includes an illumination light source, an illumination lens, etc., and is configured to be controlled by the control unit 21 to irradiate illumination light toward the imaging range of the imaging unit 23. The operation unit 26 is configured to output an operation signal corresponding to an input operation to the control unit 21, and the control unit 21 receives the operation signal and performs processing corresponding to the input operation. The communication unit 27 is configured as a communication interface for performing data communication with external devices such as the locking / unlocking control device and the entry / exit management server, and is configured to perform communication processing in cooperation with the control unit 21.
[0025] Next, the mobile terminal 30 will be described with reference to FIG. 1 and FIG. The mobile terminal 30 shown in Figures 1 and 4 is, for example, a smartphone, and includes a control unit 31 consisting of a CPU etc., a memory 32, an imaging unit 33 configured as a camera, a touch panel 34 whose display content is controlled by the control unit 31, an operation unit 35 that outputs signals to the control unit 31 in response to touch operations or key operations on the touch panel 34, and a communication unit 36 for communicating with external devices etc.
[0026] The authentication code C generated by the above-mentioned code generating device is stored in advance in the memory 32 of the mobile terminal 30 configured as above. Then, in response to a predetermined operation by the user on the operation unit 35, the authentication code C read from the memory 32 is displayed on the screen of the touch panel 34 (see FIG. 1).
[0027] Next, the authentication process performed by the image processing device 20 will be described in detail with reference to the flowcharts shown in FIGS. When the control unit 21 of the image processing device 20 starts the authentication process, an image capturing process shown in step S101 of Fig. 5 is performed. In this process, an image is captured by the image capturing unit 23 in a state where illumination light is irradiated from the illumination unit 25 through the reading window. Then, in a determination process in step S103, it is determined whether or not a two-dimensional code whose size in the captured image is equal to or larger than a specified value (e.g., 30% of the captured area) has been captured. Here, if the two-dimensional code has not been captured, or if the code has been captured but its size is less than the specified value, it is determined No in step S103, and the process from step S101 is performed.
[0028] On the other hand, if a two-dimensional code whose size occupies the captured image is equal to or larger than the specified value (Yes in S103), the captured image is decoded using the decryption key (S105) on the assumption that the two-dimensional code is authentication code C. Then, if the authentication code C is successfully decoded (Yes in S107), the successfully decoded captured image is saved (stored) in the storage unit 22 (S109). Note that the control unit 21 that performs the above decoding process may correspond to an example of a "decoding unit."
[0029] Next, in the judgment process shown in step S111, it is judged whether the number of captured images stored in the memory unit 22 is a specified number (e.g., 10 images), and if the number of captured images stored has not reached the specified number (No in S111), the process is performed from step S101.
[0030] As the user holds the authentication code C displayed on the screen of the mobile terminal 30 close to the reading window, the authentication code C whose size in the captured image is equal to or larger than the specified value is captured continuously, and when the number of times the captured images are saved reaches the specified number (Yes in S111), a process of acquiring facial feature point information, etc. is performed as shown in step S113. In this process, facial feature point information, cell size, etc. are acquired based on the decoded result of the decoding process.
[0031] Next, a pixel coordinate acquisition process is performed as shown in step S115. In this process, for the captured images of the above-mentioned specified number of authentication codes C stored in the storage unit 22, each dark-colored cell constituting the authentication code C is selected as a coordinate comparison cell, and the center position of each coordinate comparison cell in the captured images is calculated as pixel coordinates (image coordinates) m 2i Processing for two-dimensionally calculating (u,v) is performed on each captured image.
[0032] Next, a three-dimensional position coordinate acquisition process is performed in step S117. In this process, for each captured image of the authentication code C, the center position of an actual cell corresponding to the above-mentioned coordinate comparison cell of the authentication code C is calculated as three-dimensional position coordinates x i The three-dimensional position coordinates x, y, z are calculated by using the cell size obtained as described above, assuming that one of the four corners of the authentication code C is the origin. i (x, y, z) can be calculated accurately.
[0033] As mentioned above, pixel coordinate m 2i (u,v) and three-dimensional position coordinate x i When (x, y, z) is calculated and acquired, a distortion coefficient calculation process is performed in step S119. In this process, as shown in FIG. 7, the three-dimensional position coordinate x i (x, y, z) and the pixel coordinate m when the authentication code C is captured 2i Collect the pairs of (u,v) for each cell for coordinate comparison and use them as the three-dimensional position coordinate x i Pixel coordinate m calculated from (x, y, z) 3i (u,v) and the above pixel coordinate m 2i The distortion coefficient (camera parameter p) is calculated so that the error with (u,v) is small. 3iWhen the function for calculating (u,v) is F and the camera parameters are collectively represented as p, it can be expressed as the following equation (1).
number
[0034] Regarding the above function F, x from the camera coordinate system i The coordinate comparison cell at (x, y, z) is calculated by the following formulas (2) to (8) to find the pixel coordinate m 3i is converted to (u,v). x' = x / z (2) y'=y / z (3)
number
number
[0035] By solving the optimization problem of the above formula (1) using the above formulas (2) to (8), the distortion coefficients k1 to k6, p1 to p2, and s1 to s4 can be calculated. In addition, in the optimization problem, various methods can be used, for example, the LM (Levenberg-Marquardt) method or the least squares method. In addition, the control unit 21 that performs the distortion coefficient calculation process can correspond to an example of a "distortion coefficient calculation unit."
[0036] 6 is performed, and a process for capturing a face image of the user through the reading window is performed by the imaging unit 23. Then, an image correction process is performed in step S123, and the captured image captured in step S121 is corrected so that distortion is suppressed according to the distortion coefficient calculated in step S119. The control unit 21 that performs the image correction process may correspond to an example of a "distortion correction unit."
[0037] Next, a facial feature point extraction process shown in step S125 is performed to extract facial feature points from the captured image (corrected image) corrected as described above. If facial feature points are not extracted from this corrected image (No in S127), the process from step S121 is performed and the process of extracting facial feature points from the corrected image that has been captured again and corrected for distortion is repeated. The control unit 21 that performs the facial feature point extraction process can be an example of a "processing unit" that performs processing using the corrected image.
[0038] Then, when the facial feature points are successfully extracted from the corrected image (Yes in S127), a matching process shown in step S129 is performed, and the facial feature points extracted from the corrected image are compared with the facial feature point information obtained as a result of the decoding process of the authentication code C (S105) to determine whether or not all items in the facial feature points match.
[0039] Then, in the determination process shown in step S131, when it is determined that the authentication is successful because all items in the facial feature points match (Yes in S131), authentication success information is transmitted to the locking / unlocking control device (S133), and the authentication process ends. Note that in the determination process, it may be determined that the authentication is successful when a predetermined number of items in the facial feature points are deemed to match.
[0040] As described above, the image processing device 20 transmits authentication success information, and the locking / unlocking control device receives the authentication success information and unlocks the electric lock, allowing the user to enter the specific room.
[0041] As described above, in the image processing device 20 according to this embodiment, the distortion of the captured image of the imaging unit 23 is corrected by the image correction process (S123) based on the distortion coefficient calculated by the distortion coefficient calculation process (S119), and the facial feature point extraction process (S125) is performed using this corrected image. In the distortion coefficient calculation process, pixel coordinates m 2i (u,v) and the three-dimensional position coordinates x of the cell of authentication code C corresponding to the coordinate comparison cell i Based on (x, y, z), the distortion coefficients are calculated.
[0042] In this way, since the distortion coefficient is calculated using the captured authentication code C, it is possible to easily calculate the distortion coefficient without preparing a dedicated calibration chart, etc. Therefore, since the authentication code C can be captured and the distortion coefficient calculated every time processing using the captured image is performed, it is possible to correct the distortion of the captured image based on the calculated distortion coefficient without performing camera calibration for each camera in advance.
[0043] Even if the imaging unit 23 is configured to function as a fisheye camera by using a fisheye lens as an imaging lens, the distortion coefficient is calculated using the authentication code C captured each time a facial feature point extraction process using a fisheye image is performed, and the distortion of the fisheye image can be corrected based on the calculated distortion coefficient. Note that the imaging unit 23 is not limited to being configured as a fisheye camera using a fisheye lens, but may be configured as a wide-angle camera using a wide-angle lens with a narrower angle of view than a fisheye camera, or may be configured as a camera using a general imaging lens. Even when configured in this way, distortion of a wide-angle image, etc. can be corrected.
[0044] In particular, a decoding process is performed on the captured image of the authentication code C captured by the imaging unit 23 to decode the authentication code C, and the decoded result is used to perform a facial feature extraction process using the corrected image, etc. This allows the distortion coefficient to be calculated from the captured image of the authentication code C in order to obtain the decoding result, and there is no need to capture a two-dimensional code that does not need to be decoded just to calculate the distortion coefficient, thereby improving the efficiency of the process.
[0045] Furthermore, facial feature point information relating to facial feature points extracted from the user's face image is recorded in the authentication code C, and user authentication processing is performed using the facial feature point information obtained as a decoded result and the facial feature points extracted from the user's face image captured by the imaging unit 23 and whose distortion has been corrected by image correction processing. This not only makes it possible to calculate a distortion coefficient from the captured image of the authentication code C captured to obtain the facial feature point information, but also makes it possible to correct the distortion of the user's face image from which the facial feature points are extracted based on the distortion coefficient, thereby improving the authentication accuracy of the authentication processing.
[0046] Furthermore, since information regarding the size of the cells of the authentication code C is recorded in the authentication code C, the actual shape of the captured authentication code C can be accurately grasped. This makes it easier to accurately calculate the three-dimensional position coordinates of each cell of the authentication code C corresponding to the coordinate comparison cells, thereby improving the calculation accuracy of the distortion coefficient, i.e., the distortion correction accuracy of the captured image. Note that the authentication code C may be generated using a predetermined cell size, making it unnecessary to record the cell size.
[0047] In the distortion coefficient calculation process, the pixel coordinate m of the authentication code C captured multiple times according to the specified number is used. 2i (u,v) and 3D position coordinate x i The distortion coefficient is calculated based on (x, y, z). This makes it easier to suppress the influence of camera shake during imaging compared to a case where the distortion coefficient is calculated based on the pixel coordinates and three-dimensional position coordinates of the authentication code C from one captured image, and therefore the calculation accuracy of the distortion coefficient, i.e., the distortion correction accuracy of the captured image, can be improved.
[0048] Furthermore, since the authentication code C is displayed on the screen of the mobile terminal 30, the authentication code C itself is not distorted when captured because it is printed on paper or the like, and this improves the calculation accuracy of the distortion coefficient, i.e., the distortion correction accuracy of the captured image. Note that the authentication code C is not limited to being displayed on the screen and used, and may be printed on a print medium that is less likely to be distorted, such as an employee ID card or membership card, and used.
[0049] [Other embodiments] The present invention is not limited to the above-described embodiments and modifications, and may be embodied as follows, for example. (1) In the authentication process performed by the control unit 21 of the image processing device 20, it is not necessary to calculate the distortion coefficient each time an image of the authentication code C held by the user is captured. The processes from step S101 to step S119 may be eliminated on the assumption that the distortion coefficient already calculated within a specified period of time is reused.
[0050] (2) Pixel coordinate m 2i (u,v) and three-dimensional position coordinate x i The coordinate comparison cells to be used for calculating (x, y, z) are not limited to being set to each of the dark color cells constituting the authentication code C, but may be set to, for example, some of the dark color cells or each of the light color cells. 2i (u,v) and three-dimensional position coordinate x i (x, y, z) is not limited to being set at the center position of the coordinate comparison cell, and may be set at, for example, one of the four corners.
[0051] (3) The present invention is not limited to being adopted in an image processing device 20 that performs authentication processing using a face image, but may be adopted, for example, in an image processing device that performs a predetermined process using a decoded result of a two-dimensional code and a corrected image obtained by correcting a captured image. Also, the present invention may be adopted, for example, in an image processing device that uses a corrected image corrected based on a distortion coefficient calculated from a captured image of a two-dimensional code without using a decoded result.
[0052] (4) The authentication code C is not limited to being configured as a QR code, and may be configured as another type of two-dimensional code in which a plurality of dark color cells and light color cells are arranged, such as a data matrix code or maxicode, or may be configured as a two-dimensional code in which a plurality of color cells are arranged in a two-dimensional shape. [Explanation of symbols]
[0053] 10. Authentication system 20...Image processing device 21...Control unit (distortion coefficient calculation unit, distortion correction unit, processing unit, decoding unit) 23...Imaging unit 30. Mobile terminal C…Authentication code (2D code)
Claims
1. an imaging unit having an imaging lens and an imaging element that captures an image through the imaging lens; a distortion coefficient calculation unit that calculates a distortion coefficient for correcting distortion of an image captured by the imaging unit; a distortion correction unit that corrects distortion of the captured image of the imaging unit based on the distortion coefficient calculated by the distortion coefficient calculation unit; a processing unit that performs processing using a corrected image whose distortion has been corrected by the distortion correction unit; Equipped with the distortion coefficient calculation unit calculates the distortion coefficient based on pixel coordinates of each of coordinate comparison cells that are at least a part of the plurality of cells in an image of a two-dimensional code in which a plurality of cells are arranged, the image being captured by the imaging unit, and based on three-dimensional position coordinates of each of the cells of the two-dimensional code that correspond to the coordinate comparison cells; a decoding unit that performs a decoding process for decoding the two-dimensional code on an image of the two-dimensional code captured by the imaging unit, In the two-dimensional code, facial feature point information regarding facial feature points extracted from a facial image of a user is recorded, The processing unit performs authentication processing of the user by utilizing the facial feature point information obtained as a result of decoding by the decoding unit and facial feature points extracted from a facial image of the user captured by the imaging unit and whose distortion has been corrected by the distortion correction unit.
2. 2. The image processing apparatus according to claim 1, wherein information regarding a size of a cell of the two-dimensional code is recorded in the two-dimensional code.
3. an imaging unit having an imaging lens and an imaging element that captures an image through the imaging lens; a distortion coefficient calculation unit that calculates a distortion coefficient for correcting distortion of an image captured by the imaging unit; a distortion correction unit that corrects distortion of the captured image of the imaging unit based on the distortion coefficient calculated by the distortion coefficient calculation unit; a processing unit that performs processing using a corrected image whose distortion has been corrected by the distortion correction unit; Equipped with The image processing device is characterized in that the distortion coefficient calculation unit calculates the distortion coefficient so as to reduce an error between pixel coordinates of each of coordinate comparison cells that are at least a part of a two-dimensional code consisting of an array of a plurality of cells in an image captured by the imaging unit, and pixel coordinates calculated from the three-dimensional position coordinates of each of the cells of the two-dimensional code that correspond to the coordinate comparison cells.
4. 4. The image processing device according to claim 1, wherein the imaging unit functions as a fisheye camera by employing a fisheye lens as the imaging lens.
5. The image processing device according to any one of claims 1 to 4, characterized in that the distortion coefficient calculation unit calculates the distortion coefficient based on the pixel coordinates and the three-dimensional position coordinates of the two-dimensional code imaged multiple times.
6. 6. The image processing device according to claim 1, wherein the two-dimensional code is displayed on a screen.
Citation Information
Patent Citations
Image processing apparatus, image processing method, program, server, client terminal, image processing system, and method for image processing system
JP2013162280A
Calibration device, calibration chart, chart pattern generating device, and calibration method
JP6764533B2
