Construction site attendance management method and system based on face snapshot

Abstract

The invention provides a construction site attendance management method and system based on face snapshot, and belongs to the technical field of data management, and the method specifically comprises the steps: carrying out the construction of a reference image of a face recognition library according to the number of images, the deviation condition of the image features of different historical face snapshot images, and the snapshot time, acquiring a real-time face image of a person difficult to recognize by using a face snapshot device, and acquiring a face snapshot image of the face snapshot device in a preset time period when it is determined that the recognition accuracy of the real-time face image meets the requirement based on the similar condition of image features of the real-time face image and a reference image of a face recognition library; and the attendance time of the person difficult to identify is determined by utilizing the similar condition of the image features of the face snapshot image, the real-time face image and the reference image, so that the accurate determination of the attendance time is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of data management, and in particular relates to a construction site attendance management method and system based on face capture. Background Art

[0002] The construction site has the characteristics of a large number of construction workers and high mobility, which makes it difficult to meet the requirements for the management of construction site attendance. Therefore, in order to achieve attendance management, the invention patent application CN202410240431.9 "A Face Recognition-based Attendance Management Platform" monitors the on-the-job status of personnel by setting up a portrait monitoring module, which helps to ensure that employees arrive on time. However, there are the following technical problems: Due to the harsh construction environment of the construction site, the technical problem of low accuracy of face recognition will inevitably occur when performing face recognition. As a result, there may be multiple attendance punch-ins when clocking in, making it impossible to accurately obtain the real attendance time.

[0003] In view of the above technical problems, the present invention provides a construction site attendance management method and system based on face capture. Summary of the invention

[0004] To achieve the purpose of the present invention, the present invention adopts the following technical solutions: According to one aspect of the present invention, a construction site attendance management method based on face capture is provided.

[0005] A construction site attendance management method based on face capture, specifically comprising: S1 determines the personnel who are difficult to identify among the attendance personnel based on the historical recognition error data of different attendance personnel during face recognition; S2 determines the deviation of image features between the historical captured face images of the person who is difficult to identify, and uses the deviation to determine the number of images in the face recognition library of the person who is difficult to identify, and constructs a reference image of the face recognition library based on the number of images, the deviation of image features of different historical captured face images, and the capture time; S3 uses a face capture device to obtain a real-time face image of the person who is difficult to identify, and determines that the recognition accuracy of the real-time face image meets the requirements based on the similarity of the image features of the real-time face image and the reference image of the face recognition library, and then proceeds to the next step; S4 obtains the face capture image of the face capture device within a preset time period, and uses the similarity of the image features of the face capture image, the real-time face image, and the reference image to determine the attendance time of the difficult-to-identify person.

[0006] The beneficial effects of the present invention are: 1. Determine whether the recognition accuracy of the real-time face image meets the requirements based on the similarity of the image features between the real-time face image and the reference image in the face recognition library, thereby avoiding the technical problem that the face recognition accuracy does not meet the requirements due to the original simple reliance on specific face images in the image library. By comprehensively evaluating the similarities with the face snapshot images in the historical recognition process, images of the face recognition process within a certain period of time are further introduced into the face recognition process, thereby further improving the face recognition accuracy.

[0007] 2. The attendance time of people who are difficult to identify is determined by using the similarity between the captured face image and the real-time face image and the reference image, which achieves accurate determination of the attendance time of people who are difficult to identify and avoids the technical problem of attendance time identification caused by face recognition failure. By evaluating the similarity with various types of face images, the earliest face verification time is accurately determined from multiple dimensions, which improves employees' satisfaction with attendance.

[0008] A further technical solution is that the historical recognition error data includes the number of face recognition deviations of different historical recognition times of the attendance personnel during face recognition.

[0009] A further technical solution is that the number of face recognition deviations is determined based on the similarity of face images captured by the face capture device within a preset time period.

[0010] A further technical solution is that the image features include color features, texture features, shape features and spatial relationship features.

[0011] A further technical solution is that the deviation of the image features between the historical facial capture images includes the deviation of the image features in different dimensions between different historical facial capture images.

[0012] A further technical solution is that the method for determining the attendance time of the personnel who are difficult to identify is: Determine the image feature similarity coefficient between the captured face image and the real-time face image based on the similarity between the captured face image and the real-time face image within a preset time period; Determine the image feature similarity coefficient between the captured face image and the reference image based on the similarity between the captured face image and the reference image within a preset time period; Based on the average of the image feature similarity coefficients of the captured face image and the real-time face image and the image feature similarity coefficients of the captured face image and the reference image, the comprehensive similarity coefficient of the captured face image is determined, and the time corresponding to the captured face image with the longest time interval with the current time that meets the requirements is used as the attendance time of the difficult-to-identify person.

[0013] A further technical solution is that, when the comprehensive similarity coefficient is greater than a preset similarity coefficient threshold, it is determined that the comprehensive similarity coefficient of the captured face image meets the requirement.

[0014] In a second aspect, the present invention provides a computer system comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, it executes the above-mentioned construction site attendance management method based on face capture.

[0015] Other features and advantages will be described in the following description. The objects and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description and drawings.

[0016] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the accompanying drawings; Figure 1 It is a flow chart of a construction site attendance management method based on face capture; Figure 2 is a flow chart of a method for identifying definitive difficult personnel; Figure 3 is a flow chart of a method for determining the number of images in a face recognition library for persons with difficulty in identifying; Figure 4 is a flow chart of a method for determining the attendance time of a person who is difficult to identify; Figure 5 It is a framework diagram of a computer system. DETAILED DESCRIPTION

[0018] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0019] Due to the harsh construction environment of the construction site, the technical problem of low accuracy of face recognition will inevitably occur when performing face recognition. As a result, there may be multiple attendance punch-ins when clocking in, making it impossible to accurately obtain the real attendance time.

[0020] Difficult-to-identify persons: These are determined by the ratio of recognition deviations during face recognition. Specifically, persons with a ratio of recognition deviations greater than 20% are considered difficult-to-identify persons.

[0021] Reference image: The reference image is determined by using the similarity between the face recognition library and the collected image, and the historical face capture images in the face recognition library with a similarity greater than 80% are used as reference images.

[0022] The recognition accuracy of real-time facial images is determined by the average value of the similarity coefficients between the real-time facial images and different reference images. For example, if the similarity coefficients are 0.9, 0.8, and 0.7 respectively, the recognition accuracy is 0.8. When it is greater than 0.7, it is determined that the recognition accuracy of the real-time facial images meets the requirements.

[0023] Attendance time of personnel who are difficult to identify: The earliest time corresponding to the similarity between the captured face image and the real-time face image is used as the attendance time.

[0024] To solve the above problems, according to one aspect of the present invention, Figure 1 As shown, a construction site attendance management method based on face capture is provided, which specifically includes: S1 determines the personnel who are difficult to identify among the attendance personnel based on the historical recognition error data of different attendance personnel during face recognition; Furthermore, the historical recognition error data includes the number of face recognition deviations of the attendance personnel at different historical recognition times during face recognition.

[0025] Specifically, the number of face recognition deviations is determined according to the similarity of face images captured by the face capturing device within a preset time period.

[0026] It should be noted that if Figure 2 As shown, the method for determining the difficult-to-identify personnel is: Determine the deviation recognition times in the historical recognition times based on the face recognition deviation times of the attendance personnel at different historical recognition times during face recognition, and determine the basic recognition difficulty coefficient of the attendance personnel based on the proportion of the deviation recognition times in the historical recognition times; Determine the average recognition deviation number of deviation recognition times by taking the average value of face recognition deviation times of different deviation recognition times, and perform the recognition deviation coefficient of the attendance personnel based on the average recognition deviation number; The identification difficulty coefficient of the attendance person is determined by multiplying the identification deviation coefficient by the basic identification difficulty coefficient, and the identification difficulty coefficient is used to determine whether the attendance person is an identification-difficult person.

[0027] Furthermore, the recognition deviation coefficient of the attendance personnel is determined based on the ratio of the average recognition deviation number to the preset deviation number.

[0028] It should also be noted that the value range of the recognition difficulty coefficient of the attendance personnel is between 0 and 1. When the recognition difficulty coefficient of the attendance personnel is greater than a preset coefficient threshold, the attendance personnel is determined to be a difficult-to-recognize person.

[0029] It should be further explained that the method for determining the persons with difficulty in identification is: Determine the deviation recognition times in the historical recognition times based on the face recognition deviation times of the attendance personnel in different historical recognition times during face recognition; Determine the deviation recognition times whose face recognition deviation times are greater than the deviation times limit value with face recognition deviation times of different deviation recognition times, and use it as the screening deviation times; Whether the attendance person is a difficult-to-identify person is determined by the number of screening deviations.

[0030] It should be further explained that the method for determining the difficult-to-identify personnel is: S11 determines the deviation recognition times in the historical recognition times based on the face recognition deviation times of the attendance personnel with different historical recognition times during face recognition, and judges whether the deviation recognition times meet the requirements. If so, proceed to the next step, if not, proceed to step S14; S12 determines whether there is a deviation recognition number of face recognition deviation times greater than the deviation recognition number limit value based on the face recognition deviation times of different deviation recognition times. If so, proceed to the next step. If not, determine that the attendance personnel does not belong to the difficult-to-recognize personnel; S13 determines the total number of face recognition deviations of the attendance personnel through face recognition deviations of different deviation recognition times, and judges whether the total number of face recognition deviations of the attendance personnel is within a preset interval. If not, proceed to the next step. If so, determine that the attendance personnel does not belong to the difficult-to-identify personnel; S14 determines the average recognition deviation number of deviation recognition times by taking the average value of the face recognition deviation times of different deviation recognition times, and performs the recognition deviation coefficient of the attendance personnel based on the average recognition deviation number; S15 determines the basic recognition difficulty coefficient of the attendance personnel by using the proportion of the deviation recognition times in the historical recognition times, determines the recognition difficulty coefficient of the attendance personnel by multiplying the recognition deviation coefficient by the basic recognition difficulty coefficient, and determines whether the attendance personnel is a difficult-to-recognize person by using the recognition difficulty coefficient.

[0031] S2 determines the deviation of image features between the historical captured face images of the person who is difficult to identify, and uses the deviation to determine the number of images in the face recognition library of the person who is difficult to identify, and constructs a reference image of the face recognition library based on the number of images, the deviation of image features of different historical captured face images, and the capture time; Furthermore, the image features include color features, texture features, shape features and spatial relationship features.

[0032] Specifically, the deviation of image features between the historical captured facial images includes the deviation of image features in different dimensions between different historical captured facial images.

[0033] It is understandable that if Figure 3 As shown, the method for determining the number of images in the face recognition library of persons with difficulty in identifying is: Determine the deviation of image features in different dimensions between different historical face capture images based on the deviation of image features between different historical face capture images, and determine the image feature deviation value between different historical face capture images based on the deviation of image features in different dimensions; Determine the image feature deviation values ​​between different historical face snapshot images and other historical face snapshot images based on the image feature deviation values ​​between different historical face snapshot images, and determine the image deviation coefficients of different historical face snapshot images by the average value of the image feature deviation values ​​between the different historical face snapshot images and other historical face snapshot images; The image deviation coefficients of different historical facial capture images are used to determine the image of the deviation image in the historical facial capture images, and the number of images in the facial recognition library of the person with difficulty in identification is determined based on the image proportion of the deviation image.

[0034] Further, the number of images in the face recognition library of the person with difficulty in identifying is determined based on the image proportion of the deviation images, specifically including: Based on the image proportion of the deviation images, the number of images in the face recognition library of the person with difficulty in identifying is determined according to a preset ratio.

[0035] It should also be noted that the method for determining the number of images in the face recognition library for persons with difficulty in identifying is as follows: Determine the deviation of image features in different dimensions between different historical face capture images based on the deviation of image features between different historical face capture images, and determine the image feature deviation value between different historical face capture images based on the deviation of image features in different dimensions; Determine the feature deviation amount based on the average value of the image feature deviation values ​​between different historical face capture images; The feature deviation amount is used to determine the number of images in the face recognition library of the person who is difficult to identify.

[0036] Further, the number of images in the face recognition library of the person with difficulty in identifying is determined by using the feature deviation, specifically including: The minimum number of images under the feature deviation amount is determined by the feature deviation amount, and the minimum number of images is used as the number of images in the face recognition library of the person with difficulty in identifying.

[0037] It should also be noted that the method for determining the number of images in the face recognition library for persons with difficulty in identifying is as follows: S21 determines the deviation of image features in different dimensions between different historical face capture images based on the deviation of image features between different historical face capture images, and determines the image feature deviation value between different historical face capture images based on the deviation of image features in different dimensions, and determines whether there is a historical face capture image whose image feature deviation value is not within a preset deviation interval, if so, proceeds to the next step, if not, proceeds to step S24; S22 determines whether the number of historical face capture images whose image feature deviation values ​​are not within the preset deviation interval meets the requirement, if so, proceeds to the next step, if not, determines the number of images in the face recognition library of the person with difficulty in identifying based on the preset number; S23 determines the feature deviation amount based on the average value of the image feature deviation values ​​between different historical face capture images, and judges whether the feature deviation amount is greater than a preset deviation threshold. If so, determines the number of images in the face recognition library of the person with difficulty in identification based on a preset number. If not, proceeds to the next step. S24 determines the image feature deviation values ​​between different historical face snapshot images and other historical face snapshot images based on the image feature deviation values ​​between different historical face snapshot images, and determines the image deviation coefficients of different historical face snapshot images by the average value of the image feature deviation values ​​between the different historical face snapshot images and other historical face snapshot images, and judges whether the number of historical face snapshot images whose image deviation coefficients do not meet the requirements meets the requirements, if so, proceeds to the next step, if not, determines the number of images in the face recognition library of the person with difficulty in identifying based on a preset number; S25 determines the image of the deviation image in the historical face capture image through the image deviation coefficient of different historical face capture images, and determines the number of images in the face recognition library of the person with difficulty in identification based on the image proportion of the deviation image.

[0038] Specifically, constructing the reference image of the face recognition library includes: Determine the deviation of image features in different dimensions between different historical face capture images based on the deviation of image features of different historical face capture images; Determine the image feature deviation values ​​between different historical face snapshot images and other historical face snapshot images based on the image feature deviation values ​​between different historical face snapshot images, and determine the image deviation coefficients of different historical face snapshot images by the average value of the image feature deviation values ​​between the different historical face snapshot images and other historical face snapshot images; The image reference values ​​of different historical face snapshot images are determined by weighting the image deviation coefficients of different historical face snapshot images and the length of time from the snapshot moment to the current moment, and the reference images of the face recognition library are constructed based on the image reference values ​​and the number of images.

[0039] Further, constructing the reference image of the face recognition library based on the image reference value and the number of images specifically includes: Taking the number of images as a constraint, the reference images of the face recognition library are constructed according to the image reference values ​​from large to small.

[0040] S3 uses a face capture device to obtain a real-time face image of the person who is difficult to identify, and determines that the recognition accuracy of the real-time face image meets the requirements based on the similarity of the image features of the real-time face image and the reference image of the face recognition library, and then proceeds to the next step; It should be noted that determining that the recognition accuracy of the real-time face image meets the requirements specifically includes: Determine the deviation of image features in different dimensions from different reference images based on the similarity of image features between the real-time face image and the reference images in the face recognition library, and determine the image feature similarity coefficients with different reference images through the deviation of image features in different dimensions; Determine the reference value weight coefficients of different reference images according to the time between the capture time of different reference images and the current time; The recognition accuracy of the real-time face image is determined by multiplying the reference value weight coefficients of different reference images by the image feature similarity coefficients, and whether the recognition accuracy of the real-time face image meets the requirements is determined based on a preset accuracy threshold.

[0041] Further, when the recognition accuracy of the real-time facial image is less than the preset accuracy threshold, it is determined that the recognition accuracy of the real-time facial image does not meet the requirement.

[0042] It is understandable that when the recognition accuracy of the real-time facial image does not meet the requirement, the facial capture device continues to acquire the facial image.

[0043] It should also be noted that determining whether the recognition accuracy of the real-time face image meets the requirements specifically includes: S31 determines the deviation of image features in different dimensions from different reference images based on the similarity of image features between the real-time face image and the reference image in the face recognition library, and determines the image feature similarity coefficient with different reference images through the deviation of image features in different dimensions, and judges whether there is a reference image whose image feature similarity coefficient meets the requirements, if so, proceeds to the next step, if not, determines that the recognition accuracy of the real-time face image does not meet the requirements; S32: taking the reference image whose image feature similarity coefficient meets the requirement as the similar reference image, and judging whether the proportion of the similar reference image in the reference image is greater than the preset proportion, if yes, proceeding to the next step, if no, proceeding to step S35; S33 determines whether the image feature similarity coefficients of the real-time face image and different reference images are all greater than the preset similarity coefficients. If so, it is determined that the recognition accuracy of the real-time face image meets the requirements. If not, proceed to the next step. S34 determines the reference value weight coefficients of different reference images based on the time from the capture moment of different reference images to the current moment, and judges whether the ratio of the sum of the reference value weight coefficients of the similar reference images to the sum of the reference value weight coefficients of the reference images meets the requirement, and if so, determines that the recognition accuracy of the real-time face image meets the requirement, and if not, proceeds to the next step; S35 determines the recognition accuracy of the real-time face image by multiplying the reference value weight coefficient of different reference images by the image feature similarity coefficient, and determines whether the recognition accuracy of the real-time face image meets the requirements based on a preset accuracy threshold.

[0044] S4 obtains the face capture image of the face capture device within a preset time period, and uses the similarity of the image features of the face capture image, the real-time face image, and the reference image to determine the attendance time of the difficult-to-identify person.

[0045] Specifically, Figure 4 As shown, the method for determining the attendance time of the personnel who are difficult to identify is: Determine the image feature similarity coefficient between the captured face image and the real-time face image based on the similarity between the captured face image and the real-time face image within a preset time period; Determine the image feature similarity coefficient between the captured face image and the reference image based on the similarity between the captured face image and the reference image within a preset time period; Based on the average of the image feature similarity coefficients of the captured face image and the real-time face image and the image feature similarity coefficients of the captured face image and the reference image, the comprehensive similarity coefficient of the captured face image is determined, and the time corresponding to the captured face image with the longest time interval with the current time that meets the requirements is used as the attendance time of the difficult-to-identify person.

[0046] Further, when the comprehensive similarity coefficient is greater than a preset similarity coefficient threshold, it is determined that the comprehensive similarity coefficient of the captured face image meets the requirement.

[0047] Second, as Figure 5 As shown, the present invention provides a computer system, comprising: a memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that: when the processor runs the computer program, it executes the above-mentioned construction site attendance management method based on face capture.

[0048] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0049] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0050] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. A construction site attendance management method based on face capture, characterized in that: Specifically include: Determine the personnel who are difficult to identify among the attendance personnel based on historical recognition error data of different attendance personnel during face recognition; Determine the deviation of image features between the historical captured face images of the person who is difficult to identify, and use the deviation to determine the number of images in the face recognition library of the person who is difficult to identify, and construct a reference image of the face recognition library based on the number of images, the deviation of image features of different historical captured face images, and the capture time; A real-time face image of the person who is difficult to identify is obtained by using a face capture device, and when it is determined that the recognition accuracy of the real-time face image meets the requirements based on the similarity of the image features of the real-time face image and the reference image of the face recognition library, the next step is entered; The face capture image of the face capture device within a preset time period is obtained, and the attendance time of the difficult-to-identify personnel is determined by using the similarity of the image features of the face capture image, the real-time face image and the reference image.

2. The construction site attendance management method based on face capture as claimed in claim 1, characterized in that: The historical recognition error data includes the number of face recognition deviations of the attendance personnel at different historical recognition times during face recognition.

3. The construction site attendance management method based on face capture as claimed in claim 1, characterized in that: The number of face recognition deviations is determined based on the similarity of face images captured by the face capture device within a preset time period.

4. The construction site attendance management method based on face capture as claimed in claim 1, characterized in that: The method for determining the person with difficulty in identifying is: Determine the deviation recognition times in the historical recognition times based on the face recognition deviation times of the attendance personnel at different historical recognition times during face recognition, and determine the basic recognition difficulty coefficient of the attendance personnel based on the proportion of the deviation recognition times in the historical recognition times; Determine the average recognition deviation number of deviation recognition times by taking the average value of face recognition deviation times of different deviation recognition times, and perform the recognition deviation coefficient of the attendance personnel based on the average recognition deviation number; The identification difficulty coefficient of the attendance person is determined by multiplying the identification deviation coefficient by the basic identification difficulty coefficient, and the identification difficulty coefficient is used to determine whether the attendance person is an identification-difficult person.

5. The construction site attendance management method based on face capture as claimed in claim 4, characterized in that: The recognition deviation coefficient of the attendance personnel is determined based on the ratio of the average recognition deviation number to the preset deviation number.

6. The construction site attendance management method based on face capture as claimed in claim 1, characterized in that: The image features include color features, texture features, shape features and spatial relationship features.

7. The construction site attendance management method based on face capture as claimed in claim 1, characterized in that: The deviation of the image features between the historical captured face images includes the deviation of the image features in different dimensions between different historical captured face images.

8. The construction site attendance management method based on face capture as claimed in claim 1, characterized in that: The method for determining the number of images in the face recognition library of the person who is difficult to identify is: Determine the deviation of image features in different dimensions between different historical face capture images based on the deviation of image features between different historical face capture images, and determine the image feature deviation value between different historical face capture images based on the deviation of image features in different dimensions; Determine the image feature deviation values ​​between different historical face snapshot images and other historical face snapshot images based on the image feature deviation values ​​between different historical face snapshot images, and determine the image deviation coefficients of different historical face snapshot images by the average value of the image feature deviation values ​​between the different historical face snapshot images and other historical face snapshot images; The image deviation coefficients of different historical facial capture images are used to determine the image of the deviation image in the historical facial capture images, and the number of images in the facial recognition library of the person with difficulty in identification is determined based on the image proportion of the deviation image.

9. The construction site attendance management method based on face capture as claimed in claim 1, characterized in that: The method for determining the attendance time of the personnel who are difficult to identify is: Determine the image feature similarity coefficient between the captured face image and the real-time face image based on the similarity between the captured face image and the real-time face image within a preset time period; Determine the image feature similarity coefficient between the captured face image and the reference image based on the similarity between the captured face image and the reference image within a preset time period; Based on the average of the image feature similarity coefficients of the captured face image and the real-time face image and the image feature similarity coefficients of the captured face image and the reference image, the comprehensive similarity coefficient of the captured face image is determined, and the time corresponding to the captured face image with the longest time interval with the current time that meets the requirements is used as the attendance time of the difficult-to-identify person.

10. A computer system comprising: A memory and a processor connected in communication, and a computer program stored in the memory and capable of running on the processor, characterized in that the processor executes a construction site attendance management method based on face capture as described in any one of claims 1-9 when running the computer program.

Images