Multi-mode face photographing analyzer

Abstract

The utility model discloses a multi-mode face photographing analyzer which comprises a shell, a dodging inner container arranged in the shell, a standard illumination excitation assembly arranged between the bottom of the inner side of the dodging inner container and the shell, a 3D binocular camera, a hyperspectral camera and a TOF module. A jaw support is further arranged at the front end of the shell, and the 3D binocular camera, the hyperspectral camera and the TOF module collect face information through the through holes. The method can meet the requirements of different fields for facial image acquisition, and has important significance in the fields of facial expression and emotion research, human-computer interaction and the like.

Description

Technical Field

[0001] The utility model relates to the technical field of facial imaging devices, and particularly relates to a multi-modal facial photographing and analyzing device. Background Art

[0002] In the fields of medical treatment, health, beauty, and biological analysis, there are strict technical requirements for facial imaging. For example, in the medical field, it is necessary to clearly display the fine structures of the face, such as the details of skin lesions, blood vessel distribution, nerve pathways, etc. For example, when diagnosing facial nerve diseases, it is possible to accurately capture the minute changes of nerves. High precision and high resolution are required, so high precision and high resolution are needed; at the same time, it is necessary to obtain different types of image information simultaneously, such as visible light, infrared, fluorescence, etc., in order to comprehensively judge the condition. For example, when detecting skin cancer, multi-modal imaging is used to distinguish between benign and malignant lesions. When performing quantitative analysis capabilities, it is necessary to accurately measure and quantify the features in the image, such as the size, depth, color intensity, etc. of the lesion area. For example, when evaluating the burn healing process, quantitatively measure the area and quality of the newly formed skin; during real-time imaging, for example, during surgery, it can provide real-time images of the face to assist doctors in performing precise operations and reducing surgical risks.

[0003] In the health field, it is not allowed to cause any harm or discomfort to the human body, and the safety of the detection process should be ensured. For example, when used for sleep monitoring, it should not affect the normal rest of the patient; it also needs to have the function of long-term monitoring, and be able to support long-term continuous monitoring to observe the changes of facial features over time, such as the relationship between facial expressions and psychological stress; there are also certain requirements for portability, and the device should be easy to carry and use, suitable for home health monitoring or mobile medical scenarios. For example, when used for telemedicine, patients can operate by themselves at home to perform facial imaging and upload data.

[0004] In the beauty field, it is necessary to have the function of skin assessment, and be able to accurately assess the texture, moisture content, oil secretion, pigmentation, etc. of the skin, providing a basis for formulating beauty plans. For example, when selecting suitable skin care products, recommendations are made based on the skin assessment results. It also needs to have an effect tracking function and a 3D imaging function. Before and after beauty treatments, imaging is compared to evaluate the treatment effect, such as laser beauty, injection beauty, etc.; provide three-dimensional morphological information of the face for preoperative design and postoperative evaluation of plastic surgery.

[0005] In the field of bioanalysis, molecular-level imaging is required to detect specific biomolecules in facial tissues, such as proteins and gene expression, for early disease diagnosis and biomarker research. Cellular-level imaging and dynamic imaging are also needed to observe the morphology, distribution, and activities of facial cells. For example, studying the metabolism and aging processes of skin cells; real-time monitoring of the dynamic changes in biological processes, such as the metabolism and distribution of drugs in facial tissues.

[0006] In summary, the requirements for facial imaging technology in different fields have different emphases. Existing patents only implement single-functional products for a single application field and are not suitable for cross-field use. Moreover, the control of the product itself in terms of ambient light control, imaging color control, 3D modeling accuracy, etc. only reaches the industry average level. Therefore, in order to pursue higher precision, wider applications, better safety, and convenience, a more comprehensive and higher-precision multimodal facial photography analyzer is needed. Summary of the Invention

[0007] In order to solve certain or some technical problems existing in the prior art, the purpose of this application is to provide a multimodal facial photography analyzer, which can meet the needs of different fields for facial image acquisition and is of great significance for researching fields such as facial expressions and emotions, and human-computer interaction.

[0008] To solve the above-mentioned existing technical problems, the purpose of this application is achieved by adopting the following technical solutions:

[0009] A multimodal facial photography analyzer includes a housing, a light homogenizing inner tank provided in the housing, a standard light excitation component provided between the inner bottom of the light homogenizing inner tank and the housing, a 3D binocular camera, a hyperspectral camera, and a TOF module. The light homogenizing inner tank is provided with a plurality of through holes, and a jaw rest is further provided at the front end of the housing. The 3D binocular camera, hyperspectral camera, and TOF module collect facial information through the through holes.

[0010] Preferably, the light homogenizing inner tank includes a horn-shaped light homogenizing cover with a rectangular rounded corner, and a light homogenizing plate provided at the inner bottom of the horn-shaped light homogenizing cover. The light homogenizing plate is vertically arranged at the light inlet of the horn-shaped light homogenizing cover to form a horn-shaped reflection cavity. The opening of the horn-shaped light homogenizing cover faces the side of the housing.

[0011] Preferably, the horn-shaped light homogenizing cover is fitted in the housing, and a circle of protective silica gel is provided at the opening end between the horn-shaped light homogenizing cover and the housing.

[0012] Preferably, the standard light excitation component includes a mounting plate and light sources evenly distributed on the mounting plate.

[0013] Preferably, the horn-shaped light homogenizing cover and the inner layer of the light homogenizing plate are coated with a scratch-resistant total reflection environmental protection coating.

[0014] Preferably, a U-shaped support frame is provided at the bottom of the housing, a storage cavity penetrating through both sides is formed between the housing and the support frame, and the housing is horizontally placed through the support frame.

[0015] Preferably, a main camera is provided in the middle of the 3D binocular camera, and the 3D binocular camera and the main camera are horizontally arranged.

[0016] Preferably, 4 rubber anti-slip blocks are provided at the bottom of the support frame.

[0017] Compared with the prior art, the beneficial effects of the present utility model are as follows:

[0018] 1. It can provide clear and realistic images for the analysis of facial fine features, and can distinguish skin texture and pore details;

[0019] 2. It can collect information on different levels and tissues of the face, such as deep blood vessel distribution, melanin deposition, etc.;

[0020] 3. It can obtain 3D information of the face, perform 3D modeling and precise measurement on the face, and obtain the three-dimensional shape, contour curve and size ratio of each part of the face;

[0021] 4. It can capture the dynamic expressions and movements of the face in real time, which is of great significance for the research of fields such as facial expressions and emotions, and human-computer interaction. Description of the Drawings

[0022] Figure 1 It is a schematic diagram of the overall structure of the present utility model;

[0023] Figure 2 It is a schematic diagram of the structure of the present utility model when the rear cover of the housing is not installed, showing the relative position relationship of the standard light excitation component, the 3D binocular camera, the hyperspectral camera and the TOF module;

[0024] In the figure: 1. Support frame; 2. Protective silica gel; 3. Light homogenizing inner tank; 31. Horn-shaped light homogenizing cover; 32. Light homogenizing plate; 4. 3D binocular camera; 5. Main camera; 6. Hyperspectral camera; 7. Housing; 8. TOF module; 9. Through hole; 11. Jaw support; 10. Storage cavity; 12. Rubber anti-slip block; 13. Standard light excitation component; 14. Mounting plate; 15. Light source. Detailed Embodiments

[0025] Next, in combination with the accompanying drawings and specific embodiments, the present application will be further described. It should be noted that, on the premise of non-conflict, the following-described embodiments or technical features can be arbitrarily combined with each other to form new embodiments.

[0026] In the description of the present application, it should be understood that the orientation or positional relationship indicated by terms such as "upper", "lower", "left", "right", etc. is based on the orientation or positional relationship shown in the accompanying drawings. It is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present application.

[0027] The terms "first", "second", etc. in the present application are used to distinguish similar objects, rather than to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described herein. And the objects distinguished by "first", "second", etc. are usually of the same type, and do not limit the number of objects. For example, the first object can be one or multiple. In addition, "and / or" in the specification and claims means at least one of the connected objects. The character " / ", generally represents an "or" relationship between the associated objects before and after.

[0028] As Figure 1 and Figure 2 shown, a multi-modal facial photographing analyzer includes a housing 7, a light homogenizing inner liner 3 provided in the housing 7, a standard light illumination excitation component 13 provided between the inner bottom of the light homogenizing inner liner 3 and the housing 7, a 3D binocular camera 4, a hyperspectral camera 6, and a TOF module 8. A plurality of through holes 9 are provided on the light homogenizing inner liner 3, and a jaw rest 11 is further provided at the front end of the housing 7. The 3D binocular camera 4, the hyperspectral camera 6, and the TOF module 8 collect facial information through the through holes 9, wherein the TOF module 8 and the hyperspectral camera 6 are respectively located on the upper and lower sides of the 3D binocular camera 4, and the 3D binocular camera 4 is located at the middle position of the bottom of the light homogenizing inner liner 3.

[0029] During actual use, the person whose facial features are to be collected places their chin on the jaw rest 11, and then turns their face towards the inside of the light homogenizing inner liner 3. One or more of the 3D binocular camera 4, hyperspectral camera 6, and TOF module 8 are activated to collect the person's facial information. Among them, the 3D binocular camera 4 and the hyperspectral camera 6 use high-resolution image sensors and are equipped with high-quality optical lenses to obtain clear facial details. Through the hyperspectral imaging of the hyperspectral camera 6, parameters such as skin moisture content, sebum secretion, and pigment distribution can be analyzed. By introducing the 3D scanning technology in the 3D binocular camera 4, the facial contour and wrinkle depth can be accurately measured to evaluate the beauty effect; through the TOF module 8, the facial features of a person can also be recognized, and functions such as judging a person's age, skin type, facial bone changes, and pathological analysis can be achieved through big data. In combination with the hyperspectral and high-precision color restoration cameras, more recognition and detection can be realized. By combining the visible light imaging and infrared thermal imaging emitted by the standard light excitation component 13, the temperature distribution of the face can be detected to assist in the diagnosis of diseases such as inflammation; by integrating fluorescence imaging, specific fluorescent agents are injected to label diseased tissues, improving the diagnostic accuracy. By developing an image fusion algorithm, images of different modalities can be accurately superimposed and registered, providing comprehensive information for doctors. Through precise acquisition of face images through different combinations, the facial photo analyzer can be applied to different fields.

[0030] Among them, the TOF module 8 mainly includes a light emitting unit, optical lenses, an image sensor, and possibly an infrared filter, etc. Among them, the light emitting unit is used to emit near-infrared light waves, the optical lenses are used to focus and transmit the light waves, the image sensor receives the reflected light waves, and the depth information is obtained by calculating the flight time of the light, thereby realizing 3D imaging. The infrared filter only allows infrared light of the corresponding wavelength at the emission end to pass through, filtering out optical interference of other wavelengths. The specific composition of the TOF module 8 may vary depending on different products and applications. For example, in some TOF modules 8, components such as a control chip and a lens may also be included, which have the characteristics of simple structure, small module size, long detection distance, and low material cost, and can be widely used in multiple fields such as surveying and mapping, logistics, driverless, mobile phones, tablets, and various intelligent hardware. It has advantages such as richer depth of field information, safer 3D face recognition, smaller volume, lower environmental requirements, and lower cost.

[0031] Further improvement is made such that the light homogenizing inner liner 3 includes a horn-shaped light homogenizing cover 31 with rounded corners at the rectangle, and a light homogenizing plate 32 provided at the inner bottom of the horn-shaped light homogenizing cover 31. The light homogenizing plate 32 is vertically arranged at the light entrance of the horn-shaped light homogenizing cover 31 to form a horn-shaped reflection cavity, and the opening of the horn-shaped light homogenizing cover 31 faces the side of the outer shell 7.

[0032] After the standard light excitation component 13 is started, light can pass through the light homogenizing plate 32 and irradiate the face of the image to be collected. At the same time, the light in the light homogenizing inner tank 3 can also be homogenized by the horn-shaped light homogenizing cover 31, making the brightness of the face to be detected more uniform, making the collected image more accurate, and the collection result stable and reliable.

[0033] Further improvement is that the horn-shaped light homogenizing cover 31 is fitted and arranged in the housing 7, and a ring of protective silica gel 2 is provided at the open end of the horn-shaped light homogenizing cover 31 and the housing 7.

[0034] The horn-shaped light homogenizing cover 31 is fitted and arranged in the housing 7. Through the protective silica gel 2, the open end of the horn-shaped light homogenizing cover 31 and the housing 7 can be shielded and protected, and it can also play a protective role for the face, so that when the face approaches the jaw rest 11, even if it collides with the photo analyzer, it contacts the protective silica gel 2.

[0035] Further improvement is that the standard light excitation component 13 includes a mounting plate 14 and light sources 15 evenly distributed on the mounting plate 14.

[0036] The distribution of the light sources 15 is in a ring shape or a neatly arranged shape to reduce shadows and reflections. In addition, the light sources 15 can also use, for example, LED light sources 15 or xenon lamps, etc. In this solution, the mounting plate 14 is used to fix the light sources 15, so as to ensure the consistency of the irradiation light angle and the uniformity.

[0037] Further improvement is that the inner layers of the horn-shaped light homogenizing cover 31 and the light homogenizing plate 32 are coated with scratch-resistant total reflection environmental protection coatings.

[0038] The scratch-resistant total reflection environmental protection coating can effectively protect the outer surfaces of the horn-shaped light homogenizing cover 31 and the light homogenizing plate 32, avoid scratching and abrasion, make their service life longer, and the light homogenizing effect more stable.

[0039] Further improvement is that a U-shaped support frame 1 is provided at the bottom of the housing 7, and a storage cavity 10 penetrating through both sides is formed between the housing 7 and the support frame 1, and the housing 7 is horizontally placed through the support frame 1.

[0040] When people perform face recognition, it can be placed on the operating table through the support frame 1, which is convenient for the face to approach the detection. And through the storage cavity 10, the overall weight can be reduced, and temporary items such as mobile phones can be placed.

[0041] Further improvement is that a main camera 5 is provided in the middle of the 3D binocular camera 4, and the 3D binocular camera 4 and the main camera 5 are horizontally arranged.

[0042] The main camera 5 enables high color reproduction performance during face image acquisition.

[0043] Furthermore, it is improved that four rubber anti-slip blocks 12 are provided at the bottom of the support frame 1.

[0044] When the facial photograph analyzer is placed on the operating table, it is contacted and supported by the rubber anti-slip blocks 12, which can make its placement more stable and less likely to fall on a smooth surface.

[0045] The above embodiments are only the preferred embodiments of the present application, and the scope of protection of the present application cannot be limited thereby. Any non-substantive changes and substitutions made by those skilled in the art based on the present application all belong to the scope of protection required by the present application.

Claims

1. A multimodal facial photography analyzer, characterized in that: The invention comprises a shell (7), a light homogenizing liner (3) arranged in the shell (7), a standard light excitation component (13) arranged between the inner bottom of the light homogenizing liner (3) and the shell (7), a 3D binocular camera (4), a hyperspectral camera (6) and a TOF module (8), wherein the light homogenizing liner (3) is provided with a plurality of through holes (9), and the front end of the shell (7) is also provided with a jaw rest (11), and the 3D binocular camera (4), the hyperspectral camera (6) and the TOF module (8) collect facial information through the through holes (9).

2. A multimodal facial photography analyzer according to claim 1, characterized in that: The light homogenizing liner (3) comprises a horn-shaped light homogenizing cover (31) with a rectangular rounded transition, and a light homogenizing plate (32) arranged at the inner bottom of the horn-shaped light homogenizing cover (31). The light homogenizing plate (32) is vertically arranged at the light entrance of the horn-shaped light homogenizing cover (31) to form a horn-shaped reflection cavity. The opening of the horn-shaped light homogenizing cover (31) faces the side of the outer shell (7).

3. A multimodal facial photography analyzer according to claim 2, characterized in that: The inner layers of the horn-shaped light homogenizing cover (31) and the light homogenizing plate (32) are coated with scratch-resistant, fully reflective, environmentally friendly paint.

4. A multimodal facial photography analyzer according to claim 2, characterized in that: The trumpet-shaped light homogenizing cover (31) is arranged in a close fit within the outer shell (7), and a circle of protective silica gel (2) is provided between the open ends of the trumpet-shaped light homogenizing cover (31) and the outer shell (7).

5. The multimodal facial photography analyzer according to claim 1, characterized in that: The standard light excitation component (13) comprises a mounting plate (14) and light sources (15) evenly distributed on the mounting plate (14).

6. A multimodal facial photography analyzer according to claim 1, characterized in that: A U-shaped support frame (1) is provided at the bottom of the outer shell (7), and a storage cavity (10) penetrating on both sides is formed between the outer shell (7) and the support frame (1), and the outer shell (7) is placed horizontally via the support frame (1).

7. A multimodal facial photography analyzer according to claim 1, characterized in that: A main camera (5) is arranged in the middle of the 3D binocular camera (4), and the 3D binocular camera (4) and the main camera (5) are arranged horizontally.

8. A multimodal facial photography analyzer according to claim 6, characterized in that: Four rubber anti-sliding blocks (12) are provided at the bottom of the support frame (1).

Images