Image quality detection method for airport passenger face acquisition camera, and storage medium

Abstract

The invention discloses an image quality detection method of an airport passenger face acquisition camera and a storage medium. The method comprises the following steps: acquiring image data in an airport passenger face acquisition camera; image detection is carried out on the image data based on the image detection mode, a detection result data set is obtained, and the detection result data set comprises at least one detection result; a detection condition corresponding to the at least one detection result is compared with the at least one detection result, a comparison result is obtained, and the comparison result is used for verifying whether the at least one detection result meets the detection condition or not; and determining an early warning mode based on a comparison result. According to the invention, the technical problem of low face recognition accuracy of airport passengers in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of image detection, and in particular to an image quality detection method and storage medium of an airport passenger face acquisition camera. Background Art

[0002] Facial recognition technology has become an indispensable part of airport services because it can provide passengers with a more convenient and comfortable travel experience. However, facial recognition applications in airport scenarios have the following problems:

[0003] (1) Unstable image acquisition quality: Factors such as camera placement, distance, angle, and hardware failure will affect the quality of the collected facial images, making subsequent facial feature extraction and recognition difficult;

[0004] (2) Lack of real-time monitoring and feedback mechanism: Existing facial recognition systems often lack real-time monitoring and feedback mechanisms for the quality of images captured by the camera. Once a camera fails or the image quality deteriorates, it cannot be discovered and handled in a timely manner, affecting the passenger experience and the accuracy of the facial recognition system.

[0005] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0006] The embodiments of the present invention provide an image quality detection method and a storage medium for an airport passenger face collection camera, so as to at least solve the technical problem of low accuracy of airport passenger face recognition in the related art.

[0007] According to an aspect of one of the embodiments of the present invention, there is provided an image quality detection method for an airport passenger face collection camera, comprising: acquiring image data from the airport passenger face collection camera; performing image detection on the image data based on an image detection mode to obtain a detection result data set, wherein the detection result data set includes: at least one detection result; comparing the detection condition corresponding to the at least one detection result with the at least one detection result to obtain a comparison result, wherein the comparison result is used to verify whether the at least one detection result meets the detection condition; and determining an early warning mode based on the comparison result.

[0008] Optionally, performing image detection on the image data based on the image detection mode to obtain a detection result data set includes: in response to the image detection mode being a first detection mode, using a preset character recognition model to recognize the image data to obtain an image recognition result, wherein the first detection mode is used to detect whether the image acquisition device is in an abnormal state, and the image recognition result is used to determine the target object in the image data; and determining the image recognition result as the detection result data set.

[0009] Optionally, performing image detection on the image data based on the image detection mode to obtain a detection result data set includes: in response to the image detection mode being the second detection mode, using a preset image detection model to detect the image data to obtain a detection result data set, wherein the second detection mode is used to detect whether the image data is in an abnormal state, and the detection result data set includes image quality scores, gradient data, mean, variance, color distribution data, the number of target objects in the image data, the proportion of target objects, and the deflection angle of the target objects.

[0010] Optionally, the detection condition corresponding to at least one detection result is compared with at least one detection result to obtain the comparison result, including: in response to the image detection mode being the second detection mode, obtaining a detection parameter threshold data set in the detection condition, wherein the detection parameter threshold in the detection parameter threshold data set corresponds one-to-one to the detection result in the detection result data set; and comparing the detection parameter threshold with the detection result to obtain a comparison result.

[0011] Optionally, comparing the detection condition corresponding to at least one detection result with at least one detection result to obtain the comparison result includes: in response to the image detection mode being the first detection mode, acquiring the detection condition corresponding to the image recognition result; comparing the image recognition result with the detection condition to obtain the comparison result.

[0012] Optionally, determining the warning mode based on the comparison result includes: in response to a comparison result corresponding to the image recognition result in the comparison result, determining that the detection result does not meet the detection condition, and triggering a warning message.

[0013] Optionally, determining the warning mode based on the comparison results includes: responding to the comparison results corresponding to the number of target objects in the image data in the comparison results, or the proportion of target objects, or the deflection angle of the target objects, determining that the detection results do not meet the detection conditions, and triggering a warning message.

[0014] Optionally, determining the warning mode based on the comparison results includes: obtaining the number of times that the comparison results corresponding to the image quality score, or gradient data, or mean, or variance, or color distribution data in the comparison results within a preset time period do not meet the detection conditions; in response to the number of times being greater than a preset quantity threshold, triggering a warning message.

[0015] According to one embodiment of the present invention, there is also provided an image detection device, comprising: an acquisition module, used to acquire image data from an airport passenger face collection camera; a detection module, used to perform image detection on the image data based on an image detection mode, and obtain a detection result data set, wherein the detection result data set includes: at least one detection result; a comparison module, used to compare the detection condition corresponding to at least one detection result with at least one detection result, and obtain a comparison result, wherein the comparison result is used to verify whether at least one detection result meets the detection condition; and a determination module, used to determine a warning mode based on the comparison result.

[0016] Optionally, the determination module is also used to: in response to the image detection mode being the first detection mode, use a preset character recognition model to identify the image data to obtain an image recognition result, wherein the first detection mode is used to detect whether the image acquisition device is in an abnormal state, and the image recognition result is used to determine the target object in the image data; and determine the image recognition result as a detection result data set.

[0017] Optionally, the determination module is also used to: in response to the image detection mode being the second detection mode, use a preset image detection model to detect the image data to obtain a detection result data set, wherein the second detection mode is used to detect whether the image data is in an abnormal state, and the detection result data set includes image quality scores, gradient data, mean, variance, color distribution data, the number of target objects in the image data, the proportion of target objects, and the deflection angle of the target objects.

[0018] Optionally, the acquisition module is also used to: in response to the image detection mode being the second detection mode, acquire a detection parameter threshold data set in the detection conditions, wherein the detection parameter thresholds in the detection parameter threshold data set correspond one-to-one to the detection results in the detection result data set; the comparison module is also used to: compare the detection parameter thresholds with the detection results to obtain a comparison result.

[0019] Optionally, the acquisition module is further used to acquire the detection conditions corresponding to the image recognition results in response to the image detection mode being the first detection mode; the comparison module is further used to compare the image recognition results with the detection conditions to obtain a comparison result.

[0020] Optionally, the determination module is further configured to, in response to a comparison result corresponding to the image recognition result in the comparison result, determine that the detection result does not meet the detection condition, and trigger an early warning message.

[0021] Optionally, the determination module is also used to determine that the detection result does not meet the detection condition and trigger a warning message in response to the comparison result corresponding to the number of target objects in the image data in the comparison result, or the proportion of the target objects, or the deflection angle of the target objects.

[0022] Optionally, the acquisition module is also used to: obtain the number of times that the comparison results corresponding to the image quality score, or gradient data, or mean, or variance, or color distribution data in the comparison results within a preset time length do not meet the detection conditions; in response to the number of times being greater than a preset quantity threshold, trigger an early warning message.

[0023] According to one embodiment of the present invention, there is also provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the above-mentioned image quality detection method of the airport passenger face collection camera is executed when the program is running.

[0024] According to one embodiment of the present invention, a computer-readable storage medium is also provided, including: the computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the storage medium is located is controlled to execute the above-mentioned image quality detection method of the airport passenger face collection camera.

[0025] According to one embodiment of the present invention, a computer program product is also provided, including: a computer program, which implements the above-mentioned image quality detection method of the airport passenger face collection camera when executed by a processor.

[0026] In an embodiment of the present invention, a method of acquiring image data from an airport passenger face collection camera is adopted, image detection is performed on the image data based on an image detection mode to obtain a detection result data set, and a detection condition corresponding to at least one detection result is compared with at least one detection result to obtain a comparison result. Finally, an early warning mode is determined based on the comparison result, thereby achieving the purpose of quickly and comprehensively evaluating the quality of image data collected by the airport passenger face collection device, thereby realizing the technical effect of improving the accuracy of airport passenger face recognition, and further solving the technical problem of low accuracy of airport passenger face recognition in related technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0028] Figure 1 This is a hardware structure block diagram of an image quality detection method for an airport passenger face acquisition camera according to one embodiment of the present invention;

[0029] Figure 2 is a flow chart of an image quality detection method for an airport passenger face collection camera according to one embodiment of the present invention;

[0030] Figure 3is a schematic diagram of an image quality detection method for an airport passenger face acquisition camera according to one embodiment of the present invention;

[0031] Figure 4 is a schematic diagram of another method for detecting image quality of an airport passenger face acquisition camera according to one embodiment of the present invention;

[0032] Figure 5 is a flow chart of another method for detecting image quality of an airport passenger face collection camera according to one embodiment of the present invention;

[0033] Figure 6 It is a structural block diagram of an image quality detection device for an airport passenger face collection camera according to one embodiment of the present invention. DETAILED DESCRIPTION

[0034] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0035] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0036] The image quality detection method embodiment of the airport passenger face collection camera provided in the embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 is a hardware structure diagram of an image quality detection method for an airport passenger face acquisition camera according to one embodiment of the present invention. Figure 1As shown, the computer terminal 10 (or electronic device 10) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission module 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0037] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or electronic device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0038] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the image quality detection method of the airport passenger face collection camera in the embodiment of the present application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the image quality detection method of the airport passenger face collection camera described above is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0039] The transmission module 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission module 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission module 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0040] The display may be, for example, a touch screen type liquid crystal display (LCD), which may enable a user to interact with a user interface of the computer terminal 10 (or electronic device).

[0041] It should be noted that, in some optional embodiments, the above Figure 1 The computer device (or electronic device) shown may include hardware elements (including circuits), software elements (including computer code stored on a computer-readable medium), or a combination of hardware elements and software elements. It should be noted that Figure 1 This is merely one example of a particular embodiment and is intended to illustrate the types of components that may be present in the above-described computer device (or electronic device).

[0042] According to an embodiment of the present invention, a method embodiment of an image quality detection method for an airport passenger face collection camera is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in an order different from that shown here.

[0043] Figure 2 FIG. 1 is a flow chart of an image quality detection method for an airport passenger face acquisition camera according to one embodiment of the present invention. Figure 2 As shown, the method comprises the following steps:

[0044] Step S20, obtaining image data from the airport passenger face collection camera;

[0045] In step S20, the above image data is used to represent the image captured by the image acquisition device in the airport.

[0046] Step S22, performing image detection on the image data based on the image detection mode to obtain a detection result data set, wherein the detection result data set includes: at least one detection result;

[0047] In step S22, the above-mentioned image detection mode includes a first detection mode and a second detection mode, wherein the first detection mode represents post-flight semi-automatic detection, and the second detection mode represents a daily automatic detection mode.

[0048] The above detection result data set is used to store the detection result, wherein the detection result is used to characterize the result obtained after the image data is detected. For example, if the image data is subjected to image quality detection, the detection result is the image quality score.

[0049] Step S24, comparing the detection condition corresponding to the at least one detection result with the at least one detection result to obtain a comparison result, wherein the comparison result is used to verify whether the at least one detection result satisfies the detection condition;

[0050] In step S24, the detection conditions are used to represent a series of rules or standards for evaluating whether the image data meets specific standards or requirements when performing image detection. The detection conditions include but are not limited to: preset thresholds, standard parameters, or best practice parameters derived from experience.

[0051] Step S26, determining the early warning mode based on the comparison result.

[0052] In step S26, the above-mentioned warning mode includes an immediate warning mode and a cumulative warning mode. Immediate warning mode: When a certain test result is determined based on the comparison result to not meet the test condition, the warning mechanism is directly triggered. Cumulative warning mode: When a certain test result is determined based on the comparison result to not meet the test condition for a number of times within a preset time that exceeds a set threshold, the warning mechanism is triggered.

[0053] Based on the above steps S20 to S26, the method of acquiring image data from the airport passenger face collection camera is adopted, image detection is performed on the image data based on the image detection mode to obtain a detection result data set, and the detection condition corresponding to at least one detection result is compared with at least one detection result to obtain a comparison result, and finally the early warning mode is determined based on the comparison result, thereby achieving the purpose of quickly and comprehensively evaluating the quality of the image data collected by the airport passenger face collection device, thereby realizing the technical effect of improving the accuracy of airport passenger face recognition, and further solving the technical problem of low accuracy of airport passenger face recognition in related technologies.

[0054] Optionally, in step S22, image detection is performed on the image data based on the image detection mode, and the detection result data set obtained includes:

[0055] Step S221, in response to the image detection mode being the first detection mode, using a preset character recognition model to recognize the image data to obtain an image recognition result, wherein the first detection mode is used to detect whether the image acquisition device is in an abnormal state, and the image recognition result is used to determine the target object in the image data;

[0056] In step S221, the first detection mode is used to characterize the post-flight semi-automatic detection. The first detection mode is used to detect whether the face collection device has a reversal effect before the face collection device is put into use at the airport or regularly after the flight ends, and the operation and maintenance personnel are required to cooperate with the detection operation. When the face collection device has a reversal effect, it means that the face collection device is in an abnormal state.

[0057] The above-mentioned preset character recognition model is used to represent an optical character recognition (OCR) model. The preset character recognition model can recognize and extract text information from various types of documents.

[0058] The above target object is used to represent characters in image data.

[0059] The above-mentioned image recognition result is used to characterize the target object in the image data after the image data is recognized using a preset character recognition model.

[0060] Step S222: determine the image recognition result as a detection result data set.

[0061] Specifically, the first detection mode is turned on at a preset time every day. For example, the start time of the first detection mode is set after the airport flight ends. After the first detection mode is turned on, the operation and maintenance personnel hold the picture and stand in front of the image acquisition device to be detected to show it. At this time, the OCR model is used to recognize the characters in the picture to obtain the image recognition result. Based on this, the detection result data set corresponding to the first detection mode is obtained. In addition, the IP address and detection time of the image acquisition device are recorded in the detection result data set.

[0062] Based on the above steps S221 to S222, in response to the image detection mode being the first detection mode, the image data is recognized using a preset character recognition model to obtain an image recognition result; the image recognition result is determined as a detection result data set, which can accurately determine the target object and provide timely feedback to operation and maintenance personnel, so that they can quickly locate the problem and take corresponding maintenance measures.

[0063] Optionally, in step S22, image detection is performed on the image data based on the image detection mode, and the detection result data set obtained includes:

[0064] Step S223, in response to the image detection mode being the second detection mode, the image data is detected using a preset image detection model to obtain a detection result data set, wherein the second detection mode is used to detect whether the image data is in an abnormal state, and the detection result data set includes image quality scores, gradient data, mean, variance, color distribution data, the number of target objects in the image data, the proportion of target objects, and the deflection angle of the target objects.

[0065] In step S223, the second detection mode is used to represent the daily automatic detection mode. The second detection mode is used to perform real-time detection of the collection quality of the airport face collection equipment when the face recognition service is running in the daily airport. For example, face recognition used for entering the station by face scanning and security check channels.

[0066] The above target object is used to represent the face detected in the image.

[0067] The above-mentioned preset image detection model is used to detect the image quality score, gradient data, mean, variance, color distribution data, the number of target objects in the image data, the proportion of target objects, and the deflection angle of the target objects. The preset image detection module includes the following modules: an image quality assessment module for determining the image quality score; an image defocus detection module for determining the gradient value of the image; a brightness anomaly detection module for determining the mean and variance of the image; an image color cast detection module for determining the color distribution data of the image, that is, the color histogram of the image; a face frame detection module for determining the number of target objects in the image, that is, the number of faces; the face frame detection module is also used to determine the proportion of target objects in the image, that is, the ratio of the face area to the image area; a face key point detection module for determining the deflection angle of the target object in the image, that is, the deflection angle of the face.

[0068] Specifically, when the image detection mode is the second detection mode, the scanning time interval of the image acquisition device is set. Based on the scanning time interval, the image data is detected using a preset image detection model to obtain a detection result data set, wherein the detection result data set includes image quality score, gradient data, mean, variance, color distribution data, the number of target objects in the image data, the proportion of target objects, and the deflection angle of the target objects. In addition, the IP address and detection time of the image acquisition device are recorded in the detection result data set.

[0069] Exemplarily, a scanning time interval is set for a face security inspection image acquisition camera, a face self-service check-in machine image acquisition camera, etc. When the time interval countdown is 0, the face image transmitted from the camera is detected using a preset image detection model to obtain a detection result data set, wherein the detection items include: image quality score detection, gradient data detection, mean detection, variance detection, color distribution data detection, the number of target objects in the image data, the proportion of target objects, and the deflection angle detection of the target object. The detection result data set includes the detection result corresponding to each detection item, that is, the detection result data set includes image quality score, gradient data, mean, variance, color distribution data, the number of target objects in the image data, the proportion of target objects, and the deflection angle of the target object. In addition, the IP address and detection time of the camera are recorded in the detection result data set.

[0070] Based on the above step S223, in response to the image detection mode being the second detection mode, the image data is detected using a preset image detection model to obtain a detection result data set. The second detection mode can quickly identify abnormal conditions such as defocus, abnormal brightness, and color cast of the image data, which helps to take timely measures to ensure the normal operation of the image acquisition equipment, and by real-time detection of the quality of the face acquisition equipment, ensure the quality of the collected face images, improve the user experience of the face recognition service, and reduce recognition failures or delays caused by image quality problems.

[0071] Optionally, in step S24, the detection condition corresponding to the at least one detection result is compared with the at least one detection result, and the comparison result obtained includes:

[0072] Step S241, in response to the image detection mode being the second detection mode, obtaining a detection parameter threshold data set in the detection condition, wherein the detection parameter thresholds in the detection parameter threshold data set correspond one-to-one to the detection results in the detection result data set;

[0073] In step S241, the detection parameter thresholds in the detection parameter threshold data set correspond to the detection results in the detection result data set. The detection result data set includes image quality score, gradient data, mean, variance, color distribution data, the number of target objects in the image data, the proportion of target objects, and the deflection angle of the target object. The detection parameter threshold data set includes: image quality score threshold, gradient threshold, mean interval, variance interval, color distribution data threshold, the number of target objects in the image data, the proportion of target objects, and the deflection angle threshold of the target object.

[0074] Step S242, comparing the detection parameter threshold with the detection result to obtain a comparison result.

[0075] Specifically, when the image detection mode is the second detection mode, a detection parameter threshold data set in the detection condition is obtained, and the detection result in the detection result data set is compared with the detection parameter threshold in the detection parameter threshold data set to obtain a comparison result.

[0076] Specifically, the image data is input into the image quality assessment module in the preset image detection model to obtain an image quality score, where the image quality score is a floating point number between 0 and 1. The image quality score is compared with a preset image quality score threshold. If the image quality score is lower than the image quality score threshold, the comparison result corresponding to the image quality score indicates that the image quality score does not meet the detection condition.

[0077] Specifically, the performance of image defocus is blurred, and the gradient value is used to measure the degree of image blur, wherein the higher the gradient value of the image, the richer the edge information of the image, and the clearer the image. The image data is input into the image defocus detection module in the preset image detection model to obtain the gradient value of the image. The gradient value is compared with the set gradient threshold. If the image gradient value is lower than the gradient threshold, the comparison result corresponding to the image gradient value indicates that the image gradient value does not meet the detection condition.

[0078] Specifically, image brightness detection needs to calculate the mean and variance of the face image on the grayscale image. By calculating the mean and variance of the grayscale image, it is evaluated whether the image has overexposure or underexposure problems. When there is a brightness anomaly, the mean will deviate from the mean point and the variance will be smaller. The image data is input into the brightness anomaly detection module in the preset image detection model to obtain the mean and variance of the image. The mean is compared with the set mean interval, and the variance is compared with the set variance interval. If the image mean is not in the mean interval, the comparison result corresponding to the image mean indicates that the image mean does not meet the detection conditions, and / or if the image variance is not in the variance interval, the comparison result corresponding to the image variance indicates that the image mean does not meet the detection conditions.

[0079] Specifically, image color cast refers to the color deviation or color distortion in the image. The image color cast detection module first converts the color space of the image from RGB to HSV or Lab space to better analyze the hue and color distribution. Then the statistical characteristics of the color distribution are calculated by analyzing the color histogram of the image. The image data is input into the image color cast detection module in the preset image detection model to obtain the color distribution data of the image, that is, the color histogram of the image. The color distribution data is compared with the set color distribution data threshold. If the color distribution data deviates from the set color distribution data threshold, the comparison result corresponding to the image color distribution data indicates that the image color distribution data does not meet the detection conditions.

[0080] Specifically, the image data is input into the face frame detection module in the preset image detection model to obtain the number of faces in the image. The number of faces in the image is compared with a preset face number threshold. If the number of faces in the image is higher than the preset face number threshold, the comparison result corresponding to the number of faces in the image indicates that the number of faces in the image does not meet the detection condition, and at the same time, it is determined that the image acquisition device is currently in panoramic mode.

[0081] Specifically, the image data is input into the face frame detection module in the preset image detection model to obtain the ratio of the face area to the image area in the image. The ratio of the face area to the image area in the image is compared with a preset ratio threshold. If the ratio of the face area to the image area in the image is lower than the preset ratio threshold, the comparison result corresponding to the ratio of the face area to the image area in the image indicates that the ratio of the face area to the image area in the image does not meet the detection condition.

[0082] Specifically, the facial key point detection module calculates the positions of the facial features in the image, and then calculates the deflection angle of the face in the image. The image data is input into the facial key point detection module in the preset image detection model to obtain the deflection angle of the face. The deflection angle of the face in the image is compared with a pre-set deflection angle threshold. If the deflection angle of the face in the image is higher than the set face deflection angle threshold, the comparison result corresponding to the deflection angle of the face in the image indicates that the deflection angle of the face in the image does not meet the detection condition.

[0083] Based on the above steps S241 to S242, in response to the image detection mode being the second detection mode, a detection parameter threshold data set in the detection conditions is obtained; the detection parameter threshold is compared with the detection result to obtain a comparison result, which not only improves the efficiency and accuracy of the detection, but also reduces costs and improves the response speed of equipment maintenance, while ensuring the normal operation of security monitoring systems in key places such as airports.

[0084] Optionally, in step S24, the detection condition corresponding to the at least one detection result is compared with the at least one detection result, and the comparison result obtained includes:

[0085] Step S243, in response to the image detection mode being the first detection mode, obtaining a detection condition corresponding to the image recognition result;

[0086] Step S244, comparing the image recognition result with the detection condition to obtain a comparison result.

[0087] Specifically, when the image detection mode is the first detection mode, the detection condition corresponding to the image recognition result is the actual characters in the image data. The image recognition result is compared with the actual characters in the image data to determine whether the image recognition result is consistent with the actual characters in the image data, and a comparison result is obtained. If the image recognition result is consistent with the actual characters in the image data, the comparison result indicates that the image recognition result meets the detection condition; if the image recognition result is inconsistent with the actual characters in the image data, the comparison result indicates that the image recognition result does not meet the detection condition.

[0088] For instance, Figure 3 Schematic diagram of an image quality detection method for an airport passenger face acquisition camera according to one embodiment of the present invention. After the first detection mode is turned on, the operation and maintenance personnel hold the picture and stand in front of the image acquisition device to be detected to display it. The displayed picture is as follows Figure 3 As shown. Next, the OCR model is used to identify the image captured by the image acquisition device, and the image is reversed to obtain the image recognition result. The numbers at the key positions are used to determine whether the image is mirrored or reversed. "0" and "8" are key numbers, and the following judgments can be made based on the relative positions of the two numbers:

[0089] (1) If the image recognition result shows that "0" is above and to the right of "8", the image acquisition device is normal;

[0090] (2) If the image recognition result shows that "0" is above and to the left of "8", the image acquisition device is horizontally inverted;

[0091] (3) If the image recognition result shows that "0" is below and to the right of "8", the image acquisition device is vertically reversed;

[0092] Based on the above steps S243 to S244, in response to the image detection mode being the first detection mode, detection conditions corresponding to the image recognition results are obtained; the image recognition results are compared with the detection conditions to obtain comparison results, and the user experience of the face recognition service is improved by ensuring the quality of the collected image data, and recognition failures or delays caused by image quality issues are reduced.

[0093] Optionally, in step S26, determining the early warning mode based on the comparison result includes:

[0094] Step S261, in response to the comparison result corresponding to the image recognition result in the comparison result, it is determined that the detection result does not meet the detection condition, and a warning message is triggered.

[0095] Specifically, in an airport environment, when it is determined that the detection result does not meet the detection condition based on the comparison result corresponding to the image recognition result in the comparison result, it means that the image is reversed. Image reversal is usually caused by incorrect settings of the image acquisition device. This will cause the collected facial features to be inaccurate, resulting in failure of subsequent face comparison. When the image acquisition device is detected to be reversed, an early warning message should be sent immediately to alert the image acquisition device maintainer. For example, the alarm information is sent to the backend system and the operation and maintenance personnel of the application to which the image acquisition device belongs via email or text message.

[0096] Based on the above step S261, in response to the comparison result corresponding to the image recognition result in the comparison result, it is determined that the detection result does not meet the detection condition, and a warning message is triggered. By promptly discovering and correcting the setting errors of the image acquisition equipment, the misrecognition of face recognition due to image inversion is reduced, and the recognition accuracy is improved. By automatically triggering the warning message, the operation and maintenance personnel can quickly locate the problem and perform maintenance, thereby improving the operation and maintenance efficiency and reducing the workload of manual inspections.

[0097] Optionally, in step S26, determining the early warning mode based on the comparison result includes:

[0098] Step S262, in response to the comparison result corresponding to the number of target objects in the image data, or the proportion of the target objects, or the deflection angle of the target objects in the comparison result, it is determined that the detection result does not meet the detection condition, and a warning message is triggered.

[0099] Specifically, when it is determined that the detection result does not meet the detection conditions based on the number of target objects in the image data in the comparison result, or the proportion of target objects, or the comparison result corresponding to the deflection angle of the target object, an early warning information is immediately triggered, wherein the early warning information includes but is not limited to: the detection result, the detection time, and the IP address of the image acquisition device, etc.

[0100] Specifically, in an airport environment, the panoramic mode of an image acquisition device is usually turned on because the image acquisition device is far away from the passenger, or the image acquisition device has selected an incorrect acquisition mode. If the image acquisition device captures too many faces during imaging, it will result in the capture of facial information of other passengers, causing subsequent facial matching services to fail. When the number of faces in images continuously appearing in the image acquisition device exceeds the set face number threshold, an early warning message is directly triggered to notify the image acquisition device maintenance personnel to adjust the angle of the image acquisition device or the acquisition range of the image acquisition device to ensure the normal use of the image acquisition device.

[0101] Specifically, in an airport environment, if the image acquisition device is far away from the passenger, the captured face will be too small. The captured face will be too small, which will cause the face algorithm to be unable to extract features from the passenger's face information, making it impossible for the passenger to perform subsequent comparison services. When the image acquisition device continuously shows that the ratio of the face area to the image area in the image is lower than the set ratio threshold, an early warning message will be directly triggered.

[0102] Specifically, in an airport environment, if the face deflection captured by the image acquisition device is too large, the face algorithm will not be able to accurately extract the facial features of the passenger, which will lead to comparison failure or misidentification in subsequent face recognition. When the deflection angle of the face in the image is higher than the set face deflection angle threshold, an early warning message is directly triggered to notify the image acquisition device operation and maintenance personnel to adjust the angle of the image acquisition device.

[0103] Based on the above step S262, in response to the comparison result corresponding to the number of target objects in the image data, or the proportion of target objects, or the deflection angle of the target objects in the comparison result, it is determined that the detection result does not meet the detection condition, and a warning message is triggered. By monitoring the number, proportion and deflection angle of faces, recognition errors caused by incomplete or distorted face information can be reduced, the accuracy of face recognition can be improved, and after the warning message is triggered, the operation and maintenance personnel can quickly adjust the angle or acquisition range of the image acquisition device to ensure that the equipment is in the best working condition.

[0104] Optionally, in step S26, determining the early warning mode based on the comparison result includes:

[0105] Step S263, obtaining the number of times that the comparison results corresponding to the image quality score, gradient data, mean value, variance, or color distribution data in the comparison results within a preset time period do not meet the detection conditions;

[0106] Step S264, in response to the number of times being greater than a preset threshold, triggering a warning message.

[0107] Specifically, the number of times that the comparison results corresponding to the image quality score, or gradient data, or mean, or variance, or color distribution data in the comparison results within a preset time period do not meet the detection conditions is obtained; when the number is greater than a preset threshold, an early warning information is triggered, wherein the early warning information includes but is not limited to: the detection result, the detection time, and the IP address of the image acquisition device, etc.

[0108] Specifically, in an airport environment, failure to meet the quality score of an image is usually related to image out-of-focus, color cast, etc., which will affect the accuracy of face recognition. If the quality score of an image captured by an image acquisition device is lower than the image quality score threshold for more times than the preset number threshold within a preset time period, an early warning message is triggered.

[0109] Specifically, in an airport environment, the main reason why the image acquisition device captures a face and causes the image to be blurred and out of focus is that the passenger moves during image acquisition, which causes problems with the face acquisition algorithm of the image acquisition device. Blurred and out of focus facial images will result in the inability to accurately capture facial features. If the number of times the gradient value of the image captured by an image acquisition device within a period of time is lower than the gradient threshold is greater than the preset number threshold, an early warning message is triggered.

[0110] Specifically, in an airport environment, since the airport uses transparent glass as the outer wall, when the light is strong during the day, the face image captured by the image acquisition device will appear too bright; or the image captured will be too dark due to backlighting. An image that is too bright or too dark will cause abnormal facial feature extraction, resulting in failure of passenger identity verification. If the number of times that the image mean of the face image captured by an image acquisition device within a period of time is not within the mean interval exceeds the preset number threshold, an early warning message is triggered.

[0111] Specifically, in an airport environment, inaccurate color calibration of image acquisition equipment or abnormalities in the image acquisition or transmission process may cause image color cast, resulting in abnormal facial feature extraction. If the number of times that the color distribution data of facial images collected by an image acquisition device deviates from the set color distribution data threshold within a period of time exceeds the preset number threshold, an early warning message is triggered.

[0112] Furthermore, after the daily airport flights are completed, an operation report for the day is generated for each image acquisition device, and the report content includes but is not limited to:

[0113] (1) Calculate the average image quality detection score for the day.

[0114] (2) Analyze the overall abnormality of each image acquisition device and record the number of occurrences of each abnormality category.

[0115] (2) Make a histogram of the image quality acquisition score and the frequency of abnormal types in each time period to confirm whether there is a period in which the score is too low or a certain type of abnormality occurs with high frequency. For example, if the boarding gate of an airport is bright at 3 pm, the camera quality score and brightness abnormality frequency during this period will be high. If the camera operation and maintenance personnel obtain this information, they can adjust the acquisition angle or camera parameters accordingly at a specific time to improve the success rate of face recognition.

[0116] Based on the above steps S263 to S264, the number of times that the comparison results corresponding to the image quality score, or gradient data, or mean, or variance, or color distribution data in the comparison results within the preset time length do not meet the detection conditions is obtained; in response to the number of times being greater than the preset quantity threshold, a warning message is triggered. By promptly discovering and solving image quality problems, such as defocusing and color cast, etc., face recognition errors caused by image quality problems can be reduced, and the recognition accuracy can be improved. The automated warning system reduces the workload of manual inspections and improves operation and maintenance efficiency and response speed.

[0117] According to one embodiment of the present invention, there is also provided an image quality detection system for an airport passenger face collection camera, comprising: a computer program, which implements the above-mentioned image quality detection method for an airport passenger face collection camera when executed by a processor. Figure 4 FIG. 1 is a schematic diagram of another method for detecting image quality of an airport passenger face acquisition camera according to one embodiment of the present invention. Figure 4 As shown in the figure, the image acquisition device is a camera as an example. Figure 4 In the figure, the dotted arrows indicate the data flow direction, and the solid arrows indicate the call flow direction. In the airport environment, the face collection system includes an external system and the image detection system, wherein the external system includes the application to which the face camera collection belongs, the operation and maintenance personnel of the application to which the camera collection belongs, and the operation and maintenance personnel of the airport face algorithm application.

[0118] The image detection system includes an automatic detection module, a semi-automatic detection module, an algorithm model, an analysis module, an alarm module and a display module, wherein the automatic detection module corresponds to the second detection mode, the semi-automatic detection module corresponds to the first detection mode, the algorithm model includes the detection modules applied in the first detection mode and the second detection mode, and the analysis module is used to analyze the detection results, analyze the historical detection results and generate a detection report.

[0119] Specifically, image data is obtained from the application to which the face camera in the external system belongs. When the detection mode is the first detection mode, the semi-automatic detection module calls the OCR module in the algorithm model to perform image inversion detection to obtain the image recognition result. When the detection mode is the second detection mode, the automatic detection module calls the image quality assessment module in the algorithm model to calculate the image quality score and obtain the image quality score; the automatic detection module calls the defocus detection module in the algorithm model to perform image blur detection to obtain the gradient value of the image; the automatic detection module calls the brightness anomaly detection module in the algorithm model to perform image brightness detection to obtain the mean and variance of the image; the automatic detection module calls the image color cast detection module in the algorithm model to perform image color cast detection to obtain the color distribution data of the image; the automatic detection module calls the face frame detection module in the algorithm model to detect the number of faces in the image to obtain face data; the automatic detection module calls the face frame detection module in the algorithm model to calculate the ratio of the face area in the image to the image area to obtain the face ratio; the automatic detection module calls the face key point detection module in the algorithm model to calculate the face deflection angle of the face in the image to obtain the deflection angle of the face in the image.

[0120] Specifically, in the analysis module, analyzing the detection results includes: when the image detection mode is the first detection mode, the detection condition corresponding to the image recognition result is the actual character in the image data. The image recognition result is compared with the actual character in the image data to determine whether the image recognition result is consistent with the actual character in the image data, and obtain the comparison result. When the image detection mode is the second detection mode, the detection parameter threshold data set in the detection condition is obtained, and the detection result in the detection result data set is compared with the detection parameter threshold in the detection parameter threshold data set to obtain the comparison result.

[0121] Specifically, based on the detection result analysis and alarm module in the analysis module, the early warning mode is determined. When the camera is detected to be reversed, an early warning message should be triggered immediately, wherein the early warning information includes but is not limited to: the detection result, the detection time, and the IP address of the camera. When it is determined that the detection result does not meet the detection condition based on the number of target objects in the image data in the comparison result, or the proportion of the target objects, or the comparison result corresponding to the deflection angle of the target object, the early warning message is triggered immediately. Obtain the number of times that the comparison result corresponding to the image quality score, gradient data, mean, variance, or color distribution data in the comparison result within the preset time length does not meet the detection condition; when the number is greater than the preset number threshold, the early warning message is triggered.

[0122] Specifically, in the analysis module, generating a test report includes: generating a daily operation report for each camera after the airport flight ends each day, and displaying the operation report using the display module. In the analysis module, analyzing historical test results includes: adjusting the threshold in the verification condition according to the historical test results, and updating the camera parameter settings to improve the image quality collected by the camera.

[0123] Furthermore, the information obtained by the alarm module and the display module is sent to the operation and maintenance personnel of the camera acquisition application and the airport face algorithm application in the external system to provide data for improving the camera acquisition application and the airport face algorithm, thereby improving the image quality captured by the camera.

[0124] Figure 5 FIG. 1 is a flow chart of another method for detecting image quality of an airport passenger face acquisition camera according to one embodiment of the present invention. Figure 5 As shown, the method comprises the following steps:

[0125] Step S501, acquiring image data;

[0126] Step S502, in response to the image detection mode being the first detection mode, using a preset character recognition model to recognize the image data to obtain an image recognition result;

[0127] Step S503, determining the image recognition result as a detection result data set;

[0128] Step S504, in response to the image detection mode being the second detection mode, detecting the image data using a preset image detection model to obtain a detection result data set;

[0129] Step S505, in response to the image detection mode being the second detection mode, obtaining a detection parameter threshold data set in the detection condition;

[0130] Step S506, comparing the detection parameter threshold with the detection result to obtain a comparison result;

[0131] Step S507, in response to the image detection mode being the first detection mode, obtaining a detection condition corresponding to the image recognition result;

[0132] Step S508, comparing the image recognition result with the detection condition to obtain a comparison result;

[0133] Step S509, in response to the comparison result corresponding to the image recognition result in the comparison result, it is determined that the detection result does not meet the detection condition, and a warning message is triggered;

[0134] Step S510, in response to the comparison result corresponding to the number of target objects in the image data, or the proportion of the target objects, or the deflection angle of the target objects in the comparison result, it is determined that the detection result does not meet the detection condition, and a warning message is triggered;

[0135] Step S511, obtaining the number of times that the comparison results corresponding to the image quality score, gradient data, mean value, variance, or color distribution data in the comparison results within a preset time period do not meet the detection conditions;

[0136] Step S512, in response to the number of times being greater than a preset threshold, triggering a warning message.

[0137] Based on the above steps S501 to S511, the method of acquiring image data from the airport passenger face collection camera is adopted, image detection is performed on the image data based on the image detection mode to obtain a detection result data set, and the detection condition corresponding to at least one detection result is compared with at least one detection result to obtain a comparison result, and finally an early warning mode is determined based on the comparison result, thereby achieving the purpose of quickly and comprehensively evaluating the quality of the image data collected by the airport passenger face collection device, thereby realizing the technical effect of improving the accuracy of airport passenger face recognition, and further solving the technical problem of low accuracy of airport passenger face recognition in related technologies.

[0138] Through the description of the above implementation methods, those skilled in the art can clearly understand that the method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods of various embodiments of the present invention.

[0139] In the embodiments of the present invention, an image detection device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. As used below, the term "module" can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware is also possible and conceived.

[0140] Figure 6 is a structural block diagram of an image quality detection method and device of an airport passenger face acquisition camera according to one embodiment of the present invention, such as Figure 6 As shown, the device comprises:

[0141] An acquisition module 601 is used to acquire image data from a camera that collects faces of passengers at an airport;

[0142] The detection module 602 is used to perform image detection on the image data based on the image detection mode to obtain a detection result data set, wherein the detection result data set includes: at least one detection result;

[0143] A comparison module 603 is used to compare the detection condition corresponding to the at least one detection result with the at least one detection result to obtain a comparison result, wherein the comparison result is used to verify whether the at least one detection result satisfies the detection condition;

[0144] The determination module 604 is used to determine the early warning mode based on the comparison result.

[0145] Optionally, the determination module 604 is also used to: in response to the image detection mode being the first detection mode, use a preset character recognition model to identify the image data to obtain an image recognition result, wherein the first detection mode is used to detect whether the image acquisition device is in an abnormal state, and the image recognition result is used to determine the target object in the image data; and determine the image recognition result as a detection result data set.

[0146] Optionally, the determination module 604 is also used to: in response to the image detection mode being the second detection mode, use a preset image detection model to detect the image data to obtain a detection result data set, wherein the second detection mode is used to detect whether the image data is in an abnormal state, and the detection result data set includes image quality scores, gradient data, mean, variance, color distribution data, the number of target objects in the image data, the proportion of target objects, and the deflection angle of the target objects.

[0147] Optionally, the acquisition module 601 is also used to: in response to the image detection mode being the second detection mode, acquire a detection parameter threshold data set in the detection conditions, wherein the detection parameter thresholds in the detection parameter threshold data set correspond one-to-one to the detection results in the detection result data set; the comparison module 603 is also used to: compare the detection parameter thresholds with the detection results to obtain a comparison result.

[0148] Optionally, the acquisition module 601 is further used to acquire the detection conditions corresponding to the image recognition results in response to the image detection mode being the first detection mode; the comparison module 603 is further used to compare the image recognition results with the detection conditions to obtain a comparison result.

[0149] Optionally, the determination module 604 is further configured to, in response to a comparison result corresponding to the image recognition result in the comparison result, determine that the detection result does not meet the detection condition, and trigger an early warning message.

[0150] Optionally, the determination module 604 is also used to determine that the detection result does not meet the detection conditions and trigger a warning message in response to the comparison result corresponding to the number of target objects in the image data, or the proportion of target objects, or the deflection angle of the target objects in the comparison result.

[0151] Optionally, the acquisition module 601 is also used to: obtain the number of times that the comparison results corresponding to the image quality score, or gradient data, or mean, or variance, or color distribution data in the comparison results within a preset time length do not meet the detection conditions; in response to the number of times being greater than a preset quantity threshold, trigger a warning message.

[0152] It should be noted that the above modules can be implemented by software or hardware. For the latter, it can be implemented in the following ways, but not limited to: the above modules are all located in the same processor; or the above modules are located in different processors in any combination.

[0153] According to one embodiment of the present invention, there is also provided an electronic device, comprising: a memory storing an executable program; and a processor for running the program, wherein the above-mentioned image quality detection method of the airport passenger face collection camera is executed when the program is running.

[0154] Optionally, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0155] Step S1, obtaining image data from an airport passenger face collection camera;

[0156] Step S2, performing image detection on the image data based on the image detection mode to obtain a detection result data set, wherein the detection result data set includes: at least one detection result;

[0157] Step S3, comparing the detection condition corresponding to the at least one detection result with the at least one detection result to obtain a comparison result, wherein the comparison result is used to verify whether the at least one detection result satisfies the detection condition;

[0158] Step S4, determining the early warning mode based on the comparison result.

[0159] According to one embodiment of the present invention, a computer-readable storage medium is also provided, including: the computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the storage medium is located is controlled to execute the above-mentioned image quality detection method of the airport passenger face collection camera.

[0160] Optionally, in this embodiment, the storage medium may be configured to store a computer program for performing the following steps:

[0161] Step S1, obtaining image data from an airport passenger face collection camera;

[0162] Step S2, performing image detection on the image data based on the image detection mode to obtain a detection result data set, wherein the detection result data set includes: at least one detection result;

[0163] Step S3, comparing the detection condition corresponding to the at least one detection result with the at least one detection result to obtain a comparison result, wherein the comparison result is used to verify whether the at least one detection result satisfies the detection condition;

[0164] Step S4, determining the early warning mode based on the comparison result.

[0165] Optionally, in this embodiment, the above-mentioned storage medium may include but is not limited to: a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and other media that can store computer programs.

[0166] According to one embodiment of the present invention, a computer program product is also provided, including: a computer program, which implements the above-mentioned image quality detection method of the airport passenger face collection camera when executed by a processor.

[0167] Optionally, in this embodiment, the computer program product may be configured to store computer program instructions for performing the following steps:

[0168] Step S1, obtaining image data from an airport passenger face collection camera;

[0169] Step S2, performing image detection on the image data based on the image detection mode to obtain a detection result data set, wherein the detection result data set includes: at least one detection result;

[0170] Step S3, comparing the detection condition corresponding to the at least one detection result with the at least one detection result to obtain a comparison result, wherein the comparison result is used to verify whether the at least one detection result satisfies the detection condition;

[0171] Step S4, determining the early warning mode based on the comparison result.

[0172] Optionally, the specific examples in this embodiment may refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.

[0173] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0174] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0175] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0176] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0177] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0178] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0179] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for detecting the image quality of an airport passenger face collection camera, characterized in that: include: Obtain image data from airport passenger face collection cameras; Performing image detection on the image data based on an image detection mode to obtain a detection result data set, wherein the detection result data set includes: at least one detection result; Comparing the detection condition corresponding to the at least one detection result with the at least one detection result to obtain a comparison result, wherein the comparison result is used to verify whether the at least one detection result satisfies the detection condition; An early warning mode is determined based on the comparison result.

2. The image quality detection method of the airport passenger face collection camera according to claim 1 is characterized in that: Performing image detection on the image data based on the image detection mode to obtain a detection result data set includes: In response to the image detection mode being the first detection mode, the image data is recognized using a preset character recognition model to obtain an image recognition result, wherein the first detection mode is used to detect whether the image acquisition device is in an abnormal state, and the image recognition result is used to determine a target object in the image data; The image recognition result is determined as the detection result data set.

3. The image quality detection method of the airport passenger face collection camera according to claim 1 is characterized in that: Performing image detection on the image data based on the image detection mode to obtain a detection result data set includes: In response to the image detection mode being the second detection mode, the image data is detected using a preset image detection model to obtain the detection result data set, wherein the second detection mode is used to detect whether the image data is in an abnormal state, and the detection result data set includes image quality scores, gradient data, mean, variance, color distribution data, the number of target objects in the image data, the proportion of the target objects, and the deflection angle of the target objects.

4. The image quality detection method of the airport passenger face collection camera according to claim 1 is characterized in that: Comparing the detection condition corresponding to the at least one detection result with the at least one detection result to obtain a comparison result includes: In response to the image detection mode being the second detection mode, acquiring a detection parameter threshold data set in the detection condition, wherein the detection parameter thresholds in the detection parameter threshold data set correspond one-to-one to the detection results in the detection result data set; The detection parameter threshold is compared with the detection result to obtain a comparison result.

5. The image quality detection method of the airport passenger face collection camera according to claim 2 is characterized in that: Comparing the detection condition corresponding to the at least one detection result with the at least one detection result to obtain a comparison result includes: In response to the image detection mode being the first detection mode, acquiring a detection condition corresponding to the image recognition result; The image recognition result is compared with the detection condition to obtain a comparison result.

6. The image quality detection method of the airport passenger face collection camera according to claim 2 is characterized in that: Determining the early warning mode based on the comparison result includes: In response to a comparison result corresponding to the image recognition result in the comparison result, it is determined that the detection result does not meet the detection condition, and a warning message is triggered.

7. The image quality detection method of the airport passenger face collection camera according to claim 3 is characterized in that: Determining the early warning mode based on the comparison result includes: In response to a comparison result corresponding to the number of target objects in the image data, the proportion of the target objects, or the deflection angle of the target objects in the comparison result, it is determined that the detection result does not meet the detection condition, and a warning message is triggered.

8. The image quality detection method of the airport passenger face collection camera according to claim 3 is characterized in that: Determining the early warning mode based on the comparison result includes: Obtaining the number of times that the image quality score, the gradient data, the mean, the variance, or the color distribution data in the comparison result fails to meet the detection condition within a preset time period; In response to the number of times being greater than a preset threshold, an early warning message is triggered.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the storage medium is located is controlled to execute the image quality detection method for an airport passenger face collection camera as described in any one of claims 1 to 7.

10. An electronic device, characterized in that: include: A memory storing an executable program; A processor is used to run the program, wherein the program, when running, executes the image quality detection method for an airport passenger face collection camera as described in any one of claims 1 to 7.

Images