Information processing apparatus, information processing method, and program

Abstract

To enable a user to easily confirm at which position on an image face recognition with desired degree of accuracy is possible.SOLUTION: An information processing apparatus detects a predetermined detection target from an image captured by an imaging device, and determines whether the detection target detected from the image satisfies a predetermined condition for recognition processing for the detection target. Then, the information processing apparatus outputs information in which information indicating a determination result of the detection target and a position on the image where the detection target is detected are associated with each other.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an information processing technique for performing image analysis. [Background technology]

[0002] As one of the methods for determining identity based on image analysis, a method using face recognition processing is known. In face recognition processing, it is determined whether or not a captured face image corresponds to a face image of a person registered in advance. In order to improve the accuracy of face recognition, it is important to stably capture a frontal face with high face certainty, but when the image capturing device for capturing the image is a surveillance camera, it is often impossible to capture the frontal face of a person. For this reason, when installing a surveillance camera, it is required to install it in a position and set the camera so that an image that can obtain a face recognition result with a desired degree of accuracy can be obtained.

[0003] However, when installing and configuring cameras, it is not easy to perform installation and configuration that allows acquisition of images that will provide face recognition results with the desired accuracy. In order to confirm whether images that will provide face recognition results with the desired accuracy can be acquired, it is necessary to check, for example, by manual calculation using information on the distance to the person to be recognized and camera information, or by using a dedicated tool, etc.

[0004] Patent Document 1 discloses a method for visualizing past face detection information and enabling the input of parameter settings for image analysis based on the visualized information. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] JP 2023-39504 A Summary of the Invention [Problem to be solved by the invention]

[0006] However, even when the technology disclosed in Patent Document 1 is used, it is still not easy for a user to confirm, when installing or configuring a camera, at what position on an image an image can be obtained that will provide face recognition results with the desired accuracy.

[0007] Therefore, an object of the present invention is to enable a user to easily check at which position on an image face recognition with a desired degree of accuracy is possible. [Means for solving the problem]

[0008] The information processing device of the present invention is characterized by having a detection means for detecting a predetermined detection target from an image captured by an imaging device, a judgment means for judging whether the detection target detected from the image by the detection means satisfies predetermined conditions for recognition processing of the detection target, and an output means for outputting information representing the judgment result of the detection target by the judgment means and information correlating with the position on the image at which the detection target was detected by the detection means. Effect of the Invention

[0009] According to the present invention, a user can easily check at which position on an image face recognition with a desired degree of accuracy is possible. [Brief description of the drawings]

[0010] [Figure 1] FIG. 2 is a diagram illustrating an example of a functional configuration of an information processing device. [Diagram 2] FIG. 2 is a diagram illustrating an example of a hardware configuration of an information processing device. [Diagram 3] 13 is a flowchart showing a flow of information processing. [Figure 4] FIG. 4 is a diagram showing an example of an acquired image. [Diagram 5] FIG. 11 is a diagram illustrating an example of an output according to the first embodiment. [Figure 6] FIG. 11 is a diagram illustrating another output example of the first embodiment. [Figure 7]FIG. 11 is a diagram illustrating an example of a flow line setting according to the second embodiment. [Figure 8] FIG. 13 is a diagram illustrating an example of an output according to the third embodiment. [Figure 9] FIG. 13 is a diagram showing an example of display of installation and setting improvement information in the fourth embodiment. [Figure 10] 13A and 13B are diagrams illustrating examples of displaying face detection results and detail values. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] Hereinafter, embodiments of the present invention will be described with reference to the drawings. The following embodiments do not limit the present invention, and not all of the combinations of features described in the present embodiments are necessarily essential to the solution of the present invention. The configuration of the embodiments may be appropriately modified or changed depending on the specifications of the device to which the present invention is applied and various conditions (conditions of use, environment of use, etc.). In addition, the present invention may be configured by appropriately combining parts of the embodiments described below. In the following embodiments, redundant descriptions of the same or similar configurations and processing steps will be omitted.

[0012] <First embodiment> The information processing device according to this embodiment can be applied to a computer device such as a personal computer, or an image processing circuit incorporated in an imaging device such as a security camera. 1 is a block diagram showing an example of the functional configuration of an information processing system 100 including an information processing device 102 according to this embodiment. The information processing system 100 includes an imaging device 101 and an information processing device 102. The information processing device 102 includes an image acquisition unit 111, a face detection unit 112, a condition determination unit 113, and a result output unit 114. In this embodiment, an example in which the information processing device 102 has each of these functional units will be described, but the functional configuration is not limited to this example.

[0013] The imaging device 101 transmits captured image data corresponding to the imaging angle of view to the information processing device 102 via a network. In the following description, image data captured by the imaging device 101 and transmitted to the information processing device 102 and image data processed in the information processing device 102 will be simply referred to as images unless otherwise required. The imaging device 101 is not limited to an imaging device connected as an external device to the information processing device 102, and may be an imaging device built into the information processing device 102. The imaging device 101 is assumed to be, for example, a surveillance camera.

[0014] The image acquisition unit 111 of the information processing device 102 acquires a plurality of captured images with different capture times from the imaging device 101, and sends the plurality of captured images to the face detection unit 112. The images acquired from the imaging device 101 may be either moving images or still images, and in either case, the image acquisition unit 111 sends the images to the face detection unit 112 one by one. That is, when acquiring a moving image from the imaging device 101, the image acquisition unit 111 sequentially sends each image of each frame with different capture times that constitutes the moving image to the face detection unit 112. Also, when acquiring a still image from the imaging device 101, the image acquisition unit 111 sends each still image captured by the imaging device 101, that is, each still image with different capture times, to the face detection unit 112. In the following embodiment, an example is given in which the imaging device 101 captures a moving image, and the images acquired by the image acquisition unit 111 from the imaging device 101 are captured images with different capture times for each frame.

[0015] The face detection unit 112 detects a human face as a predetermined detection target from the image received from the image acquisition unit 111. The specific face detection process in the face detection unit 112 may be any of various known face detection processes, and may be any type of process as long as it is possible to detect a face and its position in an image, for example, every time a predetermined time has elapsed. The face detection unit 112 sends the detection result of the face detection process to the condition determination unit 113. In the case of this embodiment, the face detection unit 112 outputs a rectangular area that includes the area of ​​the detected face as the face detection result. That is, the face detection unit 112 outputs a rectangular area according to the position and size of the face from the image received from the image acquisition unit 111 as the face detection result.

[0016] Here, when the imaging device 101 is used as a surveillance camera or the like, the face area detected from the captured image by the face detection process can be used for, for example, face recognition process. For this reason, when installing a surveillance camera, it is necessary to install it in a position where an image that allows face recognition with a desired degree of accuracy can be acquired and to set the camera. That is, an image that allows face recognition with a desired degree of accuracy is, for example, an image that satisfies a condition that the orientation of the face in the image is within a predetermined angle range in the up, down, left, and right directions with respect to the front of the face, and a condition that the size of the face in the image is within a predetermined size range. The predetermined angle range and the predetermined size range as these conditions can be defined as thresholds for the orientation of the face and the size of the face. In other words, these conditions correspond to thresholds for determining whether an image that is captured by a camera and is to be subjected to face recognition process is an image that can improve the accuracy of face recognition. For example, the threshold for the orientation of the face (predetermined angle range) can be a value within 45° in the left and right directions and within 30° in the up and down directions with respect to the front face. Also, for example, the threshold for the size of the face (predetermined size range) can be a value such as a face width of 100 pixels or more. Hereinafter, in this embodiment, the conditions (thresholds) for the target image of the face recognition process captured by the camera to become an image that can improve the face recognition accuracy will be referred to as recommended conditions. The recommended conditions can be defined not only in terms of the face direction and face size, but also in terms of image quality and lighting conditions, and may also be defined as recommended conditions according to the analysis engine that performs the face recognition process.

[0017] As described above, when the imaging device 101 is used as a surveillance camera, when the imaging device 101 is installed, it is necessary to install the imaging device 101 at a position where an image satisfying the recommended conditions can be acquired and set the camera. For this reason, a user who installs and sets the imaging device 101 needs to check whether the imaging device 101 is installed and set so that an image satisfying the recommended conditions can be acquired, and if the recommended conditions are not satisfied, to install and set the camera so that the recommended conditions are satisfied. However, as described in the background art section, it is not easy to check whether the recommended conditions are satisfied when installing and setting the camera. Therefore, the information processing device 102 of this embodiment is provided with a condition determination unit 113 and a result output unit 114 in addition to the image acquisition unit 111 and face detection unit 112 so that the user can easily check at which position on the image the desired accuracy of face recognition is possible.

[0018] The condition determination unit 113 compares the face detection result by the face detection process of the face detection unit 112 with a threshold value predefined as a predetermined recommended condition, and sends the comparison result to the result output unit 114. In other words, the condition determination unit 113 sends the determination result of whether or not the face detection result by the face detection unit 112 satisfies the predetermined recommended condition for face recognition process with a desired high degree of accuracy to the result output unit 114. In this embodiment, the condition determination unit 113 determines whether or not the face orientation and face size of the face image detected by the face detection process each satisfy the predefined recommended condition (within the range of the recommended condition), and sends the determination result to the result output unit 114.

[0019] The result output unit 114 superimposes information indicating whether the face detection result by the face detection unit 112 satisfies the recommended conditions for each face detection position on the image based on the determination result by the condition determination unit 113, and outputs the information to a predetermined output destination. In the case of this embodiment, the result output unit 114 superimposes information that visualizes in a manner that enables identification of whether the face detection result by the face detection process satisfies the recommended conditions or not, corresponding to each position in the captured image where the face detection unit 112 detected a face, and outputs the information to a predetermined output destination.

[0020] In this embodiment, a display device such as a display is assumed as the predetermined output destination. By viewing the display on the display, the user can check whether the face detection result by the face detection process satisfies the recommended conditions for each face detection position on the image. The predetermined output destination may be in any form as long as the user can check whether the face detection result satisfies the recommended conditions for each face detection position on the image. The predetermined output destination is not limited to a specific output destination, and may be an external device via a wireless or wired connection. The result output unit 114 may output the information on the determination result of the condition determination unit 113 as it is, or may output it as a visible graphics image.

[0021] FIG. 2 is a diagram showing an example of a hardware configuration of the information processing device 102. As shown in FIG. The information processing device 102 includes a CPU 201, a ROM 202, a RAM 203, a large-capacity memory 204, a disk drive 205, a network IF (interface) 206, an input device 207, a display device 208, etc. The network IF 206 is connected to a network 211, and the imaging device 101 described above is connected to the information processing device 102 via the network 211.

[0022] The CPU 201 is a control device that controls the information processing device 102. The ROM 202 stores a control program by which the CPU 201 controls the information processing device 102, an information processing program for performing information processing related to each functional unit of the information processing device 102 shown in FIG. 1, and the like. A secondary storage device may be provided instead of the ROM 202. The RAM 203 is a memory for the CPU 201 to expand the program read from the ROM 202 and execute the processing. The RAM 203 is also used as a temporary storage area for temporarily storing data to be subjected to various processes.

[0023] The network IF 206 is a circuit that performs communication via the network 211. In this embodiment, the network IF 206 receives an image from the imaging device 101 connected via the network 211. The CPU 201 performs image analysis processing, such as the face detection processing described above, on the image received by the network IF 206. Note that the CPU 201 can also perform face recognition processing using a face detection result from the face detection processing, as necessary. The large-capacity memory 204 is an HDD, an SSD, or the like, and can store images and the like received by the network IF 206 from the imaging device 101. Therefore, the CPU 201 can read out images stored in the large-capacity memory 204 and perform face detection processing, face recognition processing, and the like.

[0024] The display device 208 is a display device that displays images, text, and the like, and is an example of a predetermined output destination in the result output unit 114 in FIG. The input device 207 is a device equipped with at least one of a keyboard for input, a pointing device for a screen display on the display device 208, a mouse, a touch panel, etc. A user of the information processing device 102 can input instructions and operations via the input device 207, and the CPU 201 performs processing according to the instructions and operations from the user.

[0025] As described above, the hardware configuration of the information processing device 102 has components similar to those of hardware components mounted on a general PC (personal computer) or the like. Therefore, various functions realized by the information processing device 102 can be implemented as software (information processing program) that runs on the PC. The CPU 201 executes the information processing program according to this embodiment to realize processing related to each functional unit of the information processing device 102 shown in FIG. 1. Of course, each functional unit of the information processing device 102 shown in FIG. 1 may be realized as a circuit configuration.

[0026] Hereinafter, information processing according to this embodiment, in which information indicating whether or not the face detection result satisfies a predetermined recommended condition is visualized and displayed on the screen while being superimposed on each face detection position on the image, will be described with reference to the flowchart in Fig. 3. Note that in the flowchart in Fig. 3, the symbol S indicates a processing step (process).

[0027] In this embodiment, a case will be described in which a recommended condition for face orientation and a recommended condition for face size are predefined as the predetermined recommended condition. The recommended condition for face orientation is defined as an angle value in the up-down direction and the left-right direction based on a face facing forward, and the recommended condition for face size is defined as a pixel value in the width direction of the face. As specific numerical values ​​of the recommended conditions, the recommended condition for face orientation is defined as a condition of within 45° left and right and within 30° up and down, and the recommended condition for face size is defined as a condition of face width of 100 pixels or more.

[0028] First, in S301, when a command to start a test analysis is input from the user via the input device 207, the information processing device 102 starts processing from S302 onwards. The test analysis is performed to determine whether or not a predetermined recommended condition is satisfied based on an image captured by the imaging device 101, and to visualize the determination result, so that the user can check whether the imaging device 101 is installed and configured to be able to acquire an image that satisfies the predetermined recommended condition. The user can start the test analysis at any timing by issuing an instruction via the input device 207. When an instruction to start the test analysis is issued by the user, the information processing device 102 advances the processing to S302.

[0029] In S302, the image acquisition unit 111 acquires an image for test analysis from the image capture device 101, and the face detection unit 112 executes face detection processing on the image for test analysis. Thereafter, in S303, when an instruction to end the test analysis is input from the user via the input device 207, the information processing device 102 ends the test analysis and stops the face detection process by the face detection unit 112. That is, the user can stop the test analysis at any timing by inputting an instruction via the input device 207.

[0030] Thereafter, in S304, the condition determination unit 113 determines whether or not the recommended conditions are satisfied based on the face detection result detected by the face detection unit 112 in S302. Then, the result output unit 114 outputs (i.e., displays) a UI (user interface) that visualizes the determination result to the display device 208.

[0031] In the case of the example of this embodiment, it is assumed that a subject person walks and moves within the imaging angle of the imaging device 101 that is installed during the test analysis. The imaging device 101 captures a moving image of the person moving within the imaging angle of view, the image acquisition unit 111 acquires an image for each frame of the moving image, and the face detection unit 112 performs face detection processing on the image for each frame. FIG. 4 is a diagram showing an example of an image 400 acquired by the image acquisition unit 111 during the test analysis. The subject person 401 walks and moves within the imaging angle of view of the imaging device 101, and the dotted arrows in the figure represent the movement lines 402 and 403 of the subject person 401 when he moves. Note that the subject person during the test analysis is not limited to one person, but may be multiple people taking into consideration individual differences and differences in behavior, and the movement lines of the person are not limited to the movement lines 402 and 403 in FIG. 4, but may be multiple different movement lines. The test analysis itself may also be repeated multiple times. While the test analysis is continuing, the face detection unit 112 detects faces and their positions from the image at predetermined time intervals, and continues to send the face detection results at each predetermined time interval to the condition determination unit 113 .

[0032] FIG. 5(a) is a diagram in which the face detection results for each predetermined time when a person moves within the imaging angle of view of the imaging device 101 in the test analysis are visualized to see whether they satisfy the recommended conditions, and are superimposed on each face detection position on the captured image 500. In this embodiment, when the face detection unit 112 detects a face from the captured image, it outputs a rectangular area that contains the area of ​​the face as the face detection result. That is, the rectangular area is an area according to the position and size of the face. FIG. 5(a) shows an example in which face detection results 501 and 502 are displayed by visualizing rectangular areas according to the position and size of the face detected from the captured image for each predetermined time. In this embodiment, face detection processing is performed for each predetermined time while the subject person is walking and moving, so the visualized face detection results 501 and 502 are arranged and superimposed according to the position on the image of the face detected for each predetermined time.

[0033] In this embodiment, as described above, a case where the face direction and the face size are defined as the predetermined recommended conditions is taken as an example. Therefore, the condition determination unit 113 determines whether the face detection result for each position on the captured image satisfies at least one of the face direction and the face size defined as the predetermined recommended conditions. In the example of this embodiment, the condition determination unit 113 determines whether the face detection result for each position on the captured image satisfies both the face direction and the face size. Then, the result output unit 114 determines the color of the rectangle based on the determination result, and displays the visualized face detection result superimposed on the captured image. The face detection result 501 illustrated in FIG. 5(a) is superimposed as a rectangle of a color representing that the predetermined recommended conditions are satisfied (within the range of the recommended conditions). On the other hand, the face detection result 502 is superimposed as a rectangle of a color representing that the predetermined recommended conditions are not satisfied (outside the range of the recommended conditions). In this embodiment, an example is given in which whether or not a specified recommended condition is satisfied is expressed by varying the color, but this is not limited to color, and whether or not a specified recommended condition is satisfied may also be expressed by varying the pattern, or both the color and the pattern.

[0034] The visualized face detection result in FIG. 5(a) is a rectangle, and whether or not the recommended conditions are satisfied is indicated by the color of the rectangle. However, the result output unit 114 may visualize and superimpose the detailed values ​​of the detected face. For example, the result output unit 114 may superimpose and display the angle values ​​of the vertical direction (pitch direction) and horizontal direction (yaw direction) of the detected face as detailed values ​​of the face orientation. In addition, for example, the result output unit 114 may superimpose and display the pixel value corresponding to the detected face width (width of the rectangular area) or the pixel value corresponding to the width between the left and right eyes (eye width) as the width of a predetermined area in the face area as detailed values ​​of the face size. FIG. 5(b) is a diagram showing an example in which detailed values ​​(numerical values) indicating the face orientation and face size are also superimposed and displayed in addition to the display form of the face detection result exemplified in FIG. 5(a). Note that the display of the detailed values ​​as exemplified in Fig. 5(b) may be performed when the user selects one or more desired face detection results from among the face detection results visualized as in Fig. 5(a) via the input device 207. That is, in this case, the result output unit 114 visualizes and displays the detailed values ​​of the face orientation and face size of the face detection result selected by the user.

[0035] Further, for example, the result output unit 114 may generate pseudo face figures representing the detected face direction and face size as well as the rectangular face detection result as shown in Fig. 5 as a visualization example of the face detection result, and superimpose and display them on the captured image. Fig. 6 is a diagram showing an example in which pseudo face figures 601, 602 representing the detected face direction and face size are superimposed and displayed on a captured image 600 as a visualized face detection result. In the example of Fig. 6 as well, whether or not the recommended conditions are satisfied is expressed by differences in color and pattern.

[0036] Alternatively, for example, when test analyses are performed by multiple people or multiple test analyses are performed in consideration of individual differences and differences due to behavior as described above, the result output unit 114 may display multiple face detection results detected in the multiple test analysis results in an overlapping manner. In this case, too, the user can check whether or not each position on the image satisfies a predetermined recommended condition by viewing the image on which the multiple face detection results are displayed in an overlapping manner.

[0037] As described above, in the information processing device 102 of the first embodiment, whether or not predetermined recommended conditions are satisfied is visualized for each position on an image using face detection results obtained by performing a test analysis. This allows the user to easily check whether an image captured by the imaging device 101 that has been temporarily installed and set satisfies the predetermined recommended conditions. Therefore, if an image captured by the imaging device 101 does not satisfy the predetermined recommended conditions, the user can change the installation position of the imaging device 101 or change the camera settings so that the predetermined recommended conditions are satisfied.

[0038] In the above-described embodiment, an example has been described in which information on the face detection result is superimposed on the face detection position in the captured image, but the present invention is not limited to this. For example, a configuration may be used in which information in which the face detection result and the face detection position in the captured image are associated with each other is output to the user. In this case, the information output to the user may be, for example, information in which the face detection result and the face detection position are associated in a list format, or information in which a line such as an arrow is extended from the face detection position in the captured image and the corresponding face detection result is described. In other words, the information to be output may be information that allows the user to confirm the association between the face detection result and the face detection position.

[0039] <Second embodiment> Next, a second embodiment will be described. In the following, only the differences from the first embodiment will be described, and the configurations of the information processing system 100 and the information processing device 102 and the information processing flowcharts are assumed to be the same as those of the first embodiment unless otherwise stated.

[0040] In the first embodiment, a case has been described in which the test analysis ends when an end instruction is given in S303 from the user via the input device 207. In the second embodiment, a case will be described in which the test analysis ends automatically by setting a flow line area in advance.

[0041] In the case of the second embodiment, the user can set a flow line along which a person passes on the image via the input device 207 before performing a test analysis. For example, the user can specify a line 701 on a UI screen for setting a flow line as shown in FIG. 7(a) through an input operation via the input device 207. For example, when the user sets, for example, a line end 702 and a line end 703 on the image, the condition determination unit 113 sets a line 701 connecting the line end 702 and the line end 703. Furthermore, the user can specify a minimum face size 704 and a maximum face size 705 at each line end through an input operation via the input device 207. It is assumed that the line 711, the line end 712, the line end 713, the minimum face size 714, and the maximum face size 714 shown in FIG. 7(a) are also specified by the user in the same manner.

[0042] When a user designation as described in FIG. 7(a) is performed, the condition determination unit 113 automatically sets a target area 706 as shown in FIG. 7(b) based on the information of the user designation. The target area 706 is a movement line area automatically set corresponding to the line 701, line end 702, line end 703, minimum face size 704, and maximum face size 704 shown in FIG. 7(a). Similarly, the condition determination unit 113 automatically sets a target area 716 as shown in FIG. 7(b) based on the line 711, line end 712, line end 713, minimum face size 714, and maximum face size 714 shown in FIG. 7(a). In addition, when a user instruction operation is performed via the input device 207 to move each vertex 707 of the target area 706, the condition determination unit 113 also changes the target area 706 in accordance with the movement of each vertex 707 by the user instruction operation.

[0043] In addition to setting the lines, line ends, minimum face size, and maximum face size as shown in Fig. 7(a), the user can also directly set polygons such as target areas 706 and 716 shown in Fig. 7(b). That is, in direct setting of the polygon of the target area, when the user specifies each vertex 707 in Fig. 7(b) via the input device 207, the condition determination unit 113 automatically sets the target area 706 and target area 716 that connect each vertex 707.

[0044] In the second embodiment, the face detection unit 112 stops the face detection process in S302 when the total area of ​​the face size (area of ​​the face frame) detected in the target area automatically set as described above reaches a certain percentage or more. This ends the test analysis in S303.

[0045] As described above, in the second embodiment, a target area based on a movement line is automatically set in advance, and when the total area of ​​the face size detected in the target area (area of ​​the face frame) reaches a certain percentage or more, the test analysis can be automatically terminated. As a result, according to the second embodiment, the user can check without fail whether the detection position on the image satisfies the predetermined recommended conditions.

[0046] <Third embodiment> Next, a third embodiment will be described. In the above-mentioned first embodiment, a case where the condition determination unit 113 performs a determination based on one recommended condition will be described. In the third embodiment, a case where the condition determination unit 113 performs a determination based on a plurality of recommended conditions will be described. In the third embodiment, only the points different from the first and second embodiments will be described, and the configurations of the information processing system 100 and the information processing device 102 and the information processing flow chart will be the same as those of the above-mentioned embodiments unless otherwise stated.

[0047] In the third embodiment, a plurality of predetermined recommended conditions may be set according to the face recognition accuracy required for each use case. In the third embodiment, a plurality of patterns of recommended conditions are prepared, and two or more recommended conditions are selected and used from the plurality of patterns of recommended conditions according to the face recognition use case. The plurality of patterns of recommended conditions may include, for example, strict recommended conditions (hereinafter referred to as first recommended conditions) when a relatively high recognition accuracy is required, and loose recommended conditions (hereinafter referred to as second recommended conditions) when it is desired to enable face recognition even if the recognition accuracy is somewhat lowered. Examples of the first recommended conditions include, for example, a face orientation within 15° in each of the up, down, left, and right directions relative to the front, and a face size of 120 pixels or more. Examples of the second recommended conditions may include, for example, a face orientation within 30° in each of the up, down, left, and right directions relative to the front, and a face size of 70 pixels or more.

[0048] The condition determination unit 113 in the third embodiment performs the same determination as described above for each of the two or more patterns of recommended conditions. Then, the result output unit 114 superimposes the face detection result visualized based on the determination result for each of the recommended conditions on the image. FIG. 8 is a diagram showing an example of superimposing face detection results visualized in a plurality of stages based on the respective determination results according to the first recommended conditions and the second recommended conditions. In the example of FIG. 8, a face detection result 801 represents a face detection result determined to be within the range of the first recommended conditions and the range of the second recommended conditions. Meanwhile, a face detection result 802 represents a face detection result determined to be outside the range of the first recommended conditions and the range of the second recommended conditions. Also, a face detection result 803 represents a face detection result determined to be outside the range of the first recommended conditions and the range of the second recommended conditions.

[0049] In the third embodiment, the first and second recommended conditions are given as examples, but of course, three or more recommended conditions may be used to obtain the respective judgment results. In the third embodiment, the detailed values ​​of the recommended conditions (numerical values ​​such as face direction and face size) explained in the first embodiment may be switched and displayed after the test analysis is completed, and the output of the judgment result may be dynamically switched accordingly.

[0050] In the third embodiment, as described above, face detection results divided into multiple stages according to a combination of judgment results based on multiple recommended conditions are visualized and displayed. This allows the user to check in more detail whether the face detection result at the detection position on the image satisfies the recommended conditions. In addition, in the third embodiment, judgment processing is performed using two or more recommended conditions selected from multiple recommended conditions according to the face recognition accuracy required for each use case. This allows the user to check whether the face detection result satisfies the recommended conditions according to the use case for the face recognition processing.

[0051] <Fourth embodiment> Next, a fourth embodiment will be described. In the fourth embodiment, an example will be described in which a user instructs to change the installation position and camera settings of the imaging device 101 so as to expand the range of the area satisfying the recommended conditions based on the judgment result visualized as in the above-mentioned embodiment, that is, an example will be described in which an instruction is given to improve the installation and settings. In the fourth embodiment, only the points different from the first to third embodiments will be described, and the configurations of the information processing system 100 and the information processing device 102 and the information processing flow chart will be the same as those of the above-mentioned embodiments unless otherwise mentioned.

[0052] The user can recognize which positions in the image are outside the range of the recommended conditions by viewing the image output from the result output unit 114 in S304, that is, the face detection results in which whether or not the recommended conditions are satisfied is visualized. In the case of the fourth embodiment, each face detection result displayed on the UI screen is selectable in response to an instruction from the user via the input device 207. Here, when one or more face detection results outside the range of the recommended conditions are selected by the user on the UI screen, the condition determination unit 113 generates camera installation and setting improvement information for bringing the face detection results within the range of the recommended conditions at the positions in the image of the selected face detection results. Then, the result output unit 114 displays the installation and setting improvement information on the UI screen.

[0053] FIG. 9 shows a UI screen 900, and illustrates an example in which a face detection result 902 outside the range of the recommended conditions is selected by the user. FIG. 9 illustrates an example in which a face detection result 902 located very close to the image capture device 101 is selected by the user from among face detection results visualized as being outside the range of the recommended conditions. The face detection result 902 is a face detection result in which the camera depression angle of the image capture device 101 is large with respect to a person as a subject, and the person's face is captured from above, so that the orientation of the face does not satisfy the recommended conditions. In this case, in order for the face detection result to be within the range of the recommended conditions at the position on the image of the face detection result 902, it is necessary to lower the position of the image capture device 101 or install the image capture device 101 in a direction away from the person. For this reason, the condition determination unit 113 generates installation and setting improvement information such as "Lower the height of the camera, or increase the distance between the camera and the subject." Then, the result output unit 114 displays the installation and setting improvement information in the improvement proposal area 901 of the UI screen 900. By looking at the installation / setting improvement information in the improvement proposal area 901, the user realizes that if the height of the imaging device 101 is lowered or the imaging device 101 is placed further away, the face detection result will be within the range of the recommended conditions at the position on the image of the face detection result 902.

[0054] Furthermore, when the user changes the installation and settings of the imaging device 101 based on the installation and setting improvement information, for example, face detection results 1001 such as face direction and face size and detailed values ​​1002 as shown in Fig. 10 may be analyzed in real time and displayed on the UI screen 1000. That is, in this case, the condition determination unit 113 analyzes the face detection results such as face direction and face size and detailed values ​​in real time, and the result output unit 114 displays the face detection results and detailed values. This allows the user to check in real time whether the face detection results satisfy the recommended conditions, and makes it possible to appropriately improve the installation and settings of the imaging device 101 based on the results.

[0055] As described above, in the fourth embodiment, when a user selects a face detection result that does not satisfy the recommended conditions, information for improving the installation and settings of the image capture device 101 is presented to the user based on the position on the image of the face detection result. This allows the user to improve the installation and settings of the image capture device 101, and as a result, the range of the area that satisfies the recommended conditions can be expanded.

[0056] In the above-described embodiments, examples of detecting a human face from an image have been given, but the detection target is not limited to a human face. The detection target may be, for example, an animal, a vehicle such as an automobile or a freight truck, and the present embodiment is also applicable to a case where it is confirmed at which position on the image the detection result of such a detection target satisfies a predetermined recommended condition.

[0057] The present invention can also be realized by a process in which a program for implementing one or more of the functions of the above-described embodiments is supplied to a system or device via a network or a storage medium, and one or more processors in a computer of the system or device read and execute the program. The present invention can also be realized by a circuit (e.g., ASIC) for implementing one or more of the functions. The above-mentioned embodiments are merely examples of the implementation of the present invention, and the technical scope of the present invention should not be interpreted as being limited by these. In other words, the present invention can be implemented in various forms without departing from its technical concept or main features.

[0058] The disclosure of this embodiment includes the following configuration, method, and program. (Configuration 1) A detection means for detecting a predetermined detection target from an image captured by the imaging device; a determination means for determining whether the detection object detected from the image by the detection means satisfies a predetermined condition for a recognition process for the detection object; an output means for outputting information representing a result of the determination of the detection object by the determination means, superimposing the information on a position on the image where the detection means detected the detection object; 13. An information processing device comprising: (Configuration 2) The information processing device according to configuration 1, wherein the output means outputs information representing a result of the determination of the detection object by the determination means, superimposed on a position on the image where the detection object is detected by the detection means. (Configuration 3) The information processing device according to configuration 1 or 2, wherein the output means outputs, as information representing the judgment result of the detection target by the judgment means, at least information that is visualized so as to distinguish between cases where the detection target satisfies the predetermined condition and cases where it does not. (Configuration 4) The detection means detects the detection target from a plurality of images captured at different times, The determination means determines whether the detection target detected by the detection means for each of the images satisfies the predetermined condition, The information processing device according to any one of configurations 1 to 3, wherein the output means outputs information representing the determination result of the detection object for each of the images by the determination means, superimposed on each position on the image where the detection means detected the detection object. (Configuration 5) The detection means has a setting means for setting a target area in which the detection object is to be detected, The information processing device according to configuration 4, wherein the detection means terminates the process of detecting the detection target when a cumulative total area of ​​the detection target detected from the plurality of images by the detection means in the target region reaches or exceeds a certain percentage. (Configuration 6) The information processing device according to configuration 5, wherein the setting means sets the target area based on a line in accordance with a user's instruction and a size of a detection target specified by the user with respect to an end of the line. (Configuration 7) 7. The information processing apparatus according to configuration 5 or 6, wherein the setting means sets the target area based on a plurality of vertices designated by a user. (Configuration 8) 8. The information processing apparatus according to any one of configurations 5 to 7, wherein the setting means changes the target area in response to an instruction from a user. (Configuration 9) The information processing device according to any one of configurations 1 to 8, characterized in that the output means outputs information representing a plurality of judgment results obtained by repeating the processing by the detection means and the judgment means a plurality of times, superimposed on the captured image. (Configuration 10) the determination means has a plurality of the predetermined conditions, and determines whether the detection object detected from the image satisfies each of the plurality of predetermined conditions; 10. The information processing device according to any one of configurations 1 to 9, wherein the output means generates the information to be output based on a plurality of the judgment results by the judgment means using the plurality of predetermined conditions. (Configuration 11) The information processing device according to configuration 10, characterized in that the output means generates, as the information to be output, information represented in a plurality of stages according to a combination of a plurality of judgment results using the plurality of predetermined conditions by the judgment means. (Configuration 12) The information processing device according to configuration 10 or 11, characterized in that the determination means performs the determination using two or more of the predetermined conditions selected from the plurality of predetermined conditions depending on a use case of the recognition processing performed using the detection result by the detection means. (Configuration 13) 13. The information processing device according to any one of configurations 1 to 12, wherein the detection target is a human face. (Configuration 14) The information processing device according to configuration 13, wherein the determination means determines whether the detected face orientation and face size satisfy the range of face orientation and face size defined as the predetermined condition. (Configuration 15) 15. The information processing device according to configuration 14, wherein the size of the face is the width of a rectangle that contains the face, or the width between the left and right eyes of the face. (Configuration 16) The information processing device according to configuration 14 or 15, wherein the output means outputs information on the angle value inclined in at least one of the up / down and left / right directions with respect to a face facing forward as information representing the judgment result of the detection target by the judgment means. (Configuration 17) The information processing device according to any one of configurations 14 to 16, wherein the output means outputs a face image indicating whether the face orientation and face size satisfy the predetermined conditions as information indicating the judgment result of the detection target by the judgment means. (Configuration 18) The information processing device described in any one of configurations 1 to 17, characterized in that the output means displays on a display means information representing a result of the detection object judged by the judgment means and information in which the position on the image at which the detection object was detected by the detection means is associated with each other. (Method 1) A detection step of detecting a predetermined detection target from an image captured by the imaging device; a determination step of determining whether the detection target detected from the image by the detection step satisfies a predetermined condition for a recognition process for the detection target; an output step of outputting information representing a result of the determination of the detection object in the determination step and information in which the information is associated with a position on the image at which the detection object is detected in the detection step; 13. An information processing method comprising: (Program 1) A program for causing a computer to function as the information processing device according to any one of configurations 1 to 18. [Explanation of symbols]

[0059] 100: information processing system, 101: imaging device, 102: information processing device, 111: image acquisition unit, 112: face detection unit, 113: condition determination unit, 114: result output unit

Claims

1. A detection means for detecting a predetermined detection target from an image captured by the imaging device; a determination means for determining whether the detection object detected from the image by the detection means satisfies a predetermined condition for a recognition process for the detection object; an output means for outputting information indicating a result of the determination of the detection object by the determination means and information in which the information is associated with a position on the image where the detection object is detected by the detection means; 13. An information processing device comprising:

2. The information processing device according to claim 1 , wherein the output means outputs information in which information representing a result of the determination of the detection target by the determination means is superimposed on a position on the image where the detection target is detected by the detection means.

3. The information processing device according to claim 1, characterized in that the output means outputs, as information representing the judgment result of the detection object by the judgment means, at least information that is visualized in a manner that makes it possible to distinguish between cases where the detection object satisfies the specified condition and cases where it does not.

4. The detection means detects the detection target from a plurality of images captured at different times, The determination means determines whether the detection object detected for each of the images by the detection means satisfies the predetermined condition, 2 . The information processing apparatus according to claim 1 , wherein the output means outputs information representing a result of the determination of the detection target for each image by the determination means by superimposing the information on each position on the image where the detection means detected the detection target.

5. the detection means has a setting means for setting a target area in which the detection object is to be detected, The information processing device according to claim 4 , characterized in that the detection means terminates the process of detecting the detection object when a cumulative total area of ​​the detection object detected from the plurality of images by the detection means in the target region reaches or exceeds a certain percentage.

6. 6. The information processing apparatus according to claim 5, wherein the setting means sets the target area based on a line in accordance with a user's instruction and a size of a detection target designated by the user with respect to an end of the line.

7. 6. The information processing apparatus according to claim 5, wherein said setting means sets said target area based on a plurality of vertices designated by a user.

8. 6. The information processing apparatus according to claim 5, wherein the setting means changes the target area in response to an instruction from a user.

9. 2 . The information processing apparatus according to claim 1 , wherein the output means outputs information representing a plurality of determination results obtained by repeating the processes performed by the detection means and the determination means a plurality of times, superimposed on the captured image.

10. the determination means has a plurality of the predetermined conditions, and determines whether the detection object detected from the image satisfies each of the plurality of predetermined conditions; 2 . The information processing apparatus according to claim 1 , wherein the output unit generates the information to be output based on a plurality of the determination results obtained by the determination unit using the plurality of predetermined conditions.

11. 11. The information processing apparatus according to claim 10, wherein the output means generates, as the information to be output, information expressed in a plurality of stages according to a combination of a plurality of the judgment results obtained by the judgment means using the plurality of predetermined conditions.

12. The information processing device according to claim 10, characterized in that the determination means makes the determination using two or more of the predetermined conditions selected from the plurality of predetermined conditions depending on a use case of the recognition processing performed using the detection result by the detection means.

13. 13. The information processing apparatus according to claim 1, wherein the detection target is a human face.

14. 14. The information processing apparatus according to claim 13, wherein the determining means determines whether the detected face direction and face size satisfy a range of face direction and a range of face size defined as the predetermined condition.

15. 15. The information processing apparatus according to claim 14, wherein the size of the face is a width of a rectangle that contains the face, or a width between the left and right eyes of the face.

16. The information processing device according to claim 14, characterized in that the output means outputs information on an angle value inclined in at least one of an up-down direction and a left-right direction with respect to a face facing forward as information representing a result of the determination of the detection target by the determination means.

17. The information processing device according to claim 14 , wherein the output means outputs a face image indicating whether the face orientation and face size satisfy the predetermined condition as information indicating the result of the determination made by the determination means for the detection target.

18. The information processing device according to claim 1, characterized in that the output means causes a display means to display information in which information representing a result of the detection object judged by the judgment means is associated with a position on the image at which the detection object was detected by the detection means.

19. A detection step of detecting a predetermined detection target from an image captured by the imaging device; a determination step of determining whether the detection target detected from the image by the detection step satisfies a predetermined condition for a recognition process for the detection target; an output step of outputting information representing a result of the determination of the detection object in the determination step and information in which the information is associated with a position on the image at which the detection object is detected in the detection step; 13. An information processing method comprising:

20. Computer, A detection means for detecting a predetermined detection target from an image captured by the imaging device; a determination means for determining whether the detection object detected from the image by the detection means satisfies a predetermined condition for a recognition process for the detection object; an output means for outputting information indicating a result of the determination of the detection object by the determination means and information in which the information is associated with a position on the image where the detection object is detected by the detection means; A program that causes the device to function as an information processing device having the above-mentioned configuration.

Images