Visitor attribute analysis device and method based on face recognition

Abstract

The invention discloses a visitor attribute analysis device and method based on face recognition, and relates to the field of visitor attribute analysis method.The visitor attribute analysis device comprises a computer, an integrated controller and a camera fixed to the position close to an image acquisition area, and a human body sensor is fixed to the position close to the image acquisition area; the integrated controller is respectively connected with an image storage input module, an image storage output module, a face recognition mainboard module, a database, a touch screen, a display and a light supplement lamp arranged close to an image acquisition area, and the computer is respectively connected with the display, the database and the face recognition mainboard module. According to the invention, by setting the device, through hardware combination and a software system, the device realizes attributive character recognition of a visitor through a method based on face recognition, so that visitor authentication and visitor access storage and recording are facilitated, visitor recording without voice and paperless recording and data real-time uploading to a platform can be realized; and convenience and rapidness are realized.

Description

Technical Field

[0001] This invention relates to the field of visitor attribute analysis methods, and more specifically, to a visitor attribute analysis device and method based on facial recognition. Background Art

[0002] Facial recognition is a biometric technology that identifies individuals based on their facial features. It involves using cameras or webcams to capture images or video streams containing faces, automatically detecting and tracking faces within the images, and then performing facial recognition. This process is also commonly known as portrait recognition or face recognition. Traditional facial recognition technology primarily relies on visible light images, a familiar method. However, this method has inherent limitations, particularly when ambient lighting changes, causing a sharp decline in recognition accuracy. Furthermore, it sometimes fails to meet the lighting requirements of practical systems. Summary of the Invention

[0003] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a visitor attribute analysis device and method based on face recognition to solve the problems mentioned in the background art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: a visitor attribute analysis device based on face recognition, comprising a computer, an integrated controller, and a camera fixed near the image acquisition area. A human body sensor is fixed near the image acquisition area. The integrated controller is connected to an image storage input / output module, a face recognition motherboard module, a database, a touch screen, a display, and a supplementary light located near the image acquisition area. The computer is connected to the display, the database, and the face recognition motherboard module. The face recognition motherboard module includes a face attribute analysis system, which includes face image acquisition, face image detection, face image preprocessing, face image feature extraction, and face image matching and recognition.

[0005] A method for analyzing visitor attributes based on facial recognition, the steps of which are as follows:

[0006] The first step is facial image acquisition, which uses a camera to capture images of visitors and then sends them to the image storage input and output module.

[0007] The second step is face image detection. The image storage input and output module sends the image to the first stage of the face recognition mainboard module for face image detection.

[0008] The third step is face image preprocessing. The image data that has been detected by face image detection is processed in the second stage of the face recognition mainboard module.

[0009] The fourth step is facial image feature extraction. The preprocessed facial image data is then passed through the third stage of the facial recognition mainboard module to extract facial image features.

[0010] The fifth step, face image matching and recognition, involves using a computer to perform face image matching and recognition by passing the image feature data extracted from the face image through the fourth stage of the face recognition motherboard module.

[0011] Step 6: Output attribute results. Based on the degree of similarity, the identity attribute information of the face is judged, and the result data of computer face image matching and recognition is displayed on the screen.

[0012] Preferably, in the second step, the face image detection includes histogram features, color features, template features, structural features, and Haar features.

[0013] Preferably, in the third step, the face image preprocessing includes light compensation, grayscale transformation, histogram equalization, normalization, geometric correction filtering, and sharpening.

[0014] Preferably, in the fourth step, the facial image feature extraction includes visual features, pixel statistical features, facial image transformation coefficient features, and facial image algebraic features, and the facial image feature extraction adopts a knowledge-based representation method.

[0015] Preferably, in the face image matching and recognition, the feature data produced in the fourth step is searched and matched with the feature templates stored in the database.

[0016] The technical effects and advantages of this invention are as follows:

[0017] 1. Compared with existing technologies, this device, through hardware combination and software system, enables the device to identify the attribute features of visitors based on facial recognition, so as to authenticate visitors and store and record visitor visits. This allows for unmanned and paperless visitor recording, with data uploaded to the platform in real time, which is convenient and fast. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of the face recognition attribute analysis system of the present invention.

[0019] Figure 2 This is a schematic diagram of the overall hardware connection of the present invention.

[0020] Figure 3 This is a schematic diagram of face image detection according to the present invention.

[0021] Figure 4 This is a schematic diagram of the face image feature extraction structure of the present invention. Detailed Implementation

[0022] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0023] As attached Figure 1-4 The device shown is a visitor attribute analysis device based on facial recognition, including a computer, an integrated controller, and a camera fixed near the image acquisition area. A human body sensor is fixed near the image acquisition area. The integrated controller is connected to an image storage input / output module, a facial recognition motherboard module, a database, a touch screen, a display, and a supplementary light located near the image acquisition area. The computer is connected to the display, the database, and the facial recognition motherboard module. The facial recognition motherboard module includes a facial attribute analysis system, which includes facial image acquisition, facial image detection, facial image preprocessing, facial image feature extraction, and facial image matching and recognition.

[0024] Based on the above, a method for analyzing visitor attributes using facial recognition is proposed, and its steps are as follows:

[0025] The first step is facial image acquisition. A camera is used to capture images of visitors, which are then sent to the image storage input and output module. Different facial images can be captured through the camera lens, such as static images, dynamic images, and different expressions. When the user is within the shooting range of the acquisition device, that is, the image acquisition area, the acquisition device will automatically search for and capture the user's facial image.

[0026] The second step is face image detection. The image storage input and output module sends the image to the first stage of the face recognition mainboard module for face image detection.

[0027] The third step is face image preprocessing. The image data that has been detected by face image detection is processed in the second stage of the face recognition mainboard module.

[0028] The fourth step is facial image feature extraction. The preprocessed facial image data is then passed through the third stage of the facial recognition mainboard module to extract facial image features.

[0029] The fifth step, face image matching and recognition, involves using a computer to perform face image matching and recognition by passing the image feature data extracted from the face image through the fourth stage of the face recognition motherboard module.

[0030] Step 6: Output attribute results. Based on the degree of similarity, the identity attribute information of the face is judged, and the result data of computer face image matching and recognition is displayed on the screen.

[0031] In a preferred embodiment, as shown in the appendix Figure 1 As shown, in the second step, face image detection includes histogram features, color features, template features, structural features, and Haar features. In practice, face detection is mainly used for the preprocessing of face recognition, that is, to accurately mark the position and size of the face in the image. Face images contain a wealth of pattern features, such as histogram features, color features, template features, structural features, and Haar features. Face detection is to extract the useful information from these features and use them to achieve face detection. The overall face image detection often uses the Adaboost algorithm. In the face detection process, the Adaboost algorithm is used to select some rectangular features (weak classifiers) that best represent the face. The weak classifiers are constructed into a strong classifier by weighted voting. Then, several strong classifiers trained are connected in series to form a cascaded classifier, which effectively improves the detection speed of the classifier.

[0032] Based on the above, Haar features can be understood as convolution templates. Haar features are divided into three categories: edge features, linear features, and center features, and diagonal features, which are combined to form a feature template. The feature template contains two types of rectangles: white and black. The feature value of this template is defined as the sum of the white rectangle pixels minus the sum of the black rectangle pixels. Haar feature values ​​reflect the grayscale variations of an image; for example, some facial features can be simply described by rectangular features, such as the eyes being darker than the cheeks, the sides of the nose being darker than the bridge of the nose, and the mouth being darker than the surrounding area. However, rectangular features are only sensitive to some simple graphic structures, such as edges and line segments, so they can only describe structures with specific horizontal, vertical, or diagonal orientations. Haar features are often used for face detection and pedestrian detection.

[0033] In a preferred embodiment, as shown in the appendix Figure 1 As shown, in the third step, the face image preprocessing includes light compensation, grayscale transformation, histogram equalization, normalization, geometric correction filtering, and sharpening.

[0034] Image preprocessing for faces is a process of processing images based on face detection results and ultimately serving feature extraction. The original images acquired by the system are often unusable directly due to various limitations and random interference. They must undergo image preprocessing such as grayscale correction and noise filtering in the early stages of image processing. For face images, the preprocessing process mainly includes lighting compensation, grayscale transformation, histogram equalization, normalization, geometric correction, filtering, and sharpening.

[0035] In a preferred embodiment, as shown in the appendix Figure 1 As shown, in the fourth step, face image feature extraction includes visual features, pixel statistical features, face image transformation coefficient features, and face image algebraic features. The face image feature extraction adopts a knowledge-based representation method. Face feature extraction is performed on certain features of the face. Face feature extraction, also known as face representation, is the process of feature modeling of the face.

[0036] Among them, knowledge-based representation methods mainly obtain feature data that helps face classification based on the shape description of facial organs and the distance characteristics between them. Its feature components usually include Euclidean distance, curvature and angle between feature points. The face is composed of local parts such as eyes, nose, mouth and chin. The geometric description of these local parts and the structural relationship between them can serve as important features for recognizing faces. These features are called geometric features. Knowledge-based face representation mainly includes geometric feature-based methods and template matching methods.

[0037] Among them, facial attribute analysis is mainly based on the basic attributes of facial recognition from facial images. The training data is based on the comparison of multiple facial data from different scenes. The more facial data from different scenes collected, the higher the accuracy of facial attribute analysis tends to be.

[0038] In a preferred embodiment, as shown in the appendix Figure 1 As shown, in the fifth step, the feature data produced in the fourth step is searched and matched with the feature templates stored in the database. The feature data of the extracted face image is searched and matched with the feature templates stored in the database. By setting a threshold, when the similarity exceeds this threshold, the matching result is output. Face recognition is to compare the face features to be identified with the obtained face feature templates and judge the identity information of the face based on the degree of similarity. This process is divided into two categories: one is confirmation, which is a one-to-one image comparison process, and the other is identification, which is a one-to-many image matching and comparison process.

[0039] In this device, the face recognition motherboard module is the most critical, and it needs to have the following functions: support for single / dual cameras, support for relays, support for human body sensing modules, support for Ethernet / WIFI, support for RS485, support for audio and microphone interfaces, and support for LVDS / MIPI display screens, etc.

[0040] Furthermore, the computer should have compatible software devices installed, including a PyQt5-based client for user login, real-time detection, offline detection, data upload to the cloud, and data analysis, as well as a Django-based web server cloud platform using an SQLite database or other relevant databases.

[0041] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0042] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A visitor attribute analysis device based on facial recognition, comprising a computer, an integrated controller, and a camera fixed near the image acquisition area, characterized in that: A human body sensor is fixed near the image acquisition area. The integrated controller is connected to an image storage input / output module, a face recognition motherboard module, a database, a touch screen, a display, and a fill light located near the image acquisition area. The computer is connected to the display, the database, and the face recognition motherboard module. The face recognition motherboard module includes a face attribute analysis system, which includes face image acquisition, face image detection, face image preprocessing, face image feature extraction, and face image matching and recognition.

2. A method for analyzing visitor attributes based on facial recognition, employing the visitor attribute analysis device based on facial recognition as described in claim 3, characterized in that: The steps are as follows: The first step is facial image acquisition, which uses a camera to capture images of visitors and then sends them to the image storage input and output module. The second step is face image detection. The image storage input and output module sends the image to the first stage of the face recognition mainboard module for face image detection. The third step is face image preprocessing. The image data that has been detected by face image detection is processed in the second stage of the face recognition mainboard module. The fourth step is facial image feature extraction. The preprocessed facial image data is then passed through the third stage of the facial recognition mainboard module to extract facial image features. The fifth step, face image matching and recognition, involves using a computer to perform face image matching and recognition by passing the image feature data extracted from the face image through the fourth stage of the face recognition motherboard module. Step 6: Output attribute results. Based on the degree of similarity, the identity attribute information of the face is judged, and the result data of computer face image matching and recognition is displayed on the screen.

3. The method for analyzing visitor attributes based on face recognition according to claim 2, characterized in that: In the second step, face image detection includes histogram features, color features, template features, structural features, and Haar features.

4. The method for analyzing visitor attributes based on face recognition according to claim 2, characterized in that: In the third step, the face image preprocessing includes light compensation, grayscale transformation, histogram equalization, normalization, geometric correction filtering, and sharpening.

5. The method for analyzing visitor attributes based on face recognition according to claim 2, characterized in that: In the fourth step, the facial image feature extraction includes visual features, pixel statistical features, facial image transformation coefficient features, and facial image algebraic features. The facial image feature extraction adopts a knowledge-based representation method.

6. The method for analyzing visitor attributes based on face recognition according to claim 2, characterized in that: In the fifth step, the feature data produced in the fourth step is searched and matched with the feature templates stored in the database.

Images