CN111210438A - Mirror - Google Patents
Mirror Download PDFInfo
- Publication number
- CN111210438A CN111210438A CN201911369545.9A CN201911369545A CN111210438A CN 111210438 A CN111210438 A CN 111210438A CN 201911369545 A CN201911369545 A CN 201911369545A CN 111210438 A CN111210438 A CN 111210438A
- Authority
- CN
- China
- Prior art keywords
- image
- mirror
- human body
- processing system
- camera device
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- A—HUMAN NECESSITIES
- A47—FURNITURE; DOMESTIC ARTICLES OR APPLIANCES; COFFEE MILLS; SPICE MILLS; SUCTION CLEANERS IN GENERAL
- A47G—HOUSEHOLD OR TABLE EQUIPMENT
- A47G1/00—Mirrors; Picture frames or the like, e.g. provided with heating, lighting or ventilating means
- A47G1/02—Mirrors used as equipment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
Abstract
The invention proposes a mirror comprising: the human body image acquisition system comprises a mirror box, a camera device and a processing system, wherein a mirror surface is arranged on the mirror box, and the camera device faces the outer side of the mirror surface so as to acquire a human body image; the processing system is arranged in the mirror box and connected with the camera device, wherein the processing system is used for carrying out region segmentation on the human body image and selecting a face image from the segmented image; the processing system is also used for outputting human body state parameters according to the comparison result of the facial image and the training image. The invention has the advantages that by arranging the camera device and the processing system, the processing system carries out region segmentation on the collected human body image, selects the face image from the segmented image and outputs the human body state parameters according to the comparison result of the face image and the training image, thereby not only improving the picture quality, but also improving the accuracy and consistency of the face-tongue diagnosis result.
Description
Technical Field
The invention relates to the technical field of medical instruments, in particular to a mirror.
Background
In recent years, with the increasing improvement of living standard, people pay more and more attention to the health condition of the people and the family, the old medical appliances can not meet the needs of some families, and various simple, practical and multifunctional novel household medical appliances are produced at the same time and become necessary articles in the life of the people. Through the equipment, people can better perceive the external information and the self information, and can more efficiently and conveniently know the self health state under the assistance of a computer, a network and even other people. For example, in the case of a facial and tongue diagnosis instrument, usually, the human body is positioned in front of the instrument, and the facial and tongue diagnosis is performed through a series of operations by a head fixing device. However, the equipment has the problems of large volume, certain requirements on installation and use environments, needs to be operated by professional personnel, is only suitable for being used in professional occasions such as hospitals and clubs, is not suitable for popularization, and is not suitable for being applied to mass life. Meanwhile, the existing traditional Chinese medicine facial-lingual diagnosis equipment using the mirror as a carrier has the problems of unstable picture quality depending on facial-lingual diagnosis, inaccurate facial-lingual diagnosis result calculated by facial-lingual diagnosis algorithm, poor consistency and the like.
Disclosure of Invention
In view of this, the invention provides a mirror, and aims to solve the problems of inaccurate facial-lingual diagnosis result and poor consistency of a traditional Chinese medicine facial-lingual diagnosis device using the mirror as a carrier.
In one aspect, the present invention provides a mirror comprising: the human body image acquisition system comprises a mirror box, a camera device and a processing system, wherein a mirror surface is arranged on the mirror box, and the camera device faces the outer side of the mirror surface so as to acquire a human body image; the processing system is arranged in the mirror box and connected with the camera device, wherein the processing system is used for carrying out region segmentation on the human body image and selecting a face image from the segmented image; the processing system is also used for outputting human body state parameters according to the comparison result of the facial image and the training image.
Further, the processing system comprises: and the image segmentation module is used for segmenting the human body image and screening the face image from the segmented image.
Further, the processing system further comprises: the training module is used for training the sample image and matching the trained sample image with the preset human body state parameters to generate training data.
Further, the processing system further comprises: and the comparison module is used for comparing the facial image with the training data and outputting the human body state parameters according to a comparison result.
Further, the processing system further comprises: and the image processing module is used for correcting the colors of the human body image combined with the surrounding environment through a histogram algorithm.
Further, the image processing module is also used for adjusting the white balance parameters of the camera device through white paper correction.
Furthermore, the mirror also comprises strip-shaped light sources for providing stable light for the camera device, and the strip-shaped light sources are symmetrically arranged on the mirror surface.
Further, an offline algorithm is built in the processing system.
Further, the mirror further comprises: the system comprises a control system, a distance sensor and a motion sensor, wherein the camera device, the distance sensor and the motion sensor are respectively connected with the control system, and the distance sensor is used for sensing the distance between a human body and a mirror surface and outputting distance data; the motion sensor is used for sensing the motion characteristics of a human body in front of the mirror and outputting motion characteristic data; and the control system controls the camera device to shoot the human body image according to the distance data and the action characteristic data.
Further, the camera device is used for dynamically capturing the human body image of the human body closest to the camera device, and automatically analyzing the size and quality of the human face image in the captured human body image.
Compared with the prior art, the method has the advantages that the processing system performs region segmentation on the collected human body image, selects the face image from the segmented image and outputs the human body state parameters according to the comparison result of the face image and the training image by arranging the camera device and the processing system, so that the picture quality is improved, and the accuracy and consistency of the facial-lingual diagnosis result are improved.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
FIG. 1 is a schematic structural diagram of a mirror provided in an embodiment of the present invention;
FIG. 2 is a functional block diagram of a processing system provided by an embodiment of the invention;
FIG. 3 is a schematic structural view of a mirror in a closed state according to an embodiment of the present invention;
FIG. 4 is a schematic view of a mirror according to an embodiment of the present invention in an open position;
fig. 5 is a schematic structural connection diagram of a mirror according to an embodiment of the present invention.
As shown in the figure, the mirror box 1, the upper cover 11, the sensing area 12; a mirror surface 2; a control system 3; the sensor 4, the distance sensor 41, the motion sensor 42; an image pickup device 5; a light source 6; an indicator light 7; a display screen 8; the system comprises a processing system 9, an image segmentation module 91, a training module 92, a comparison module 93 and an image processing module 94.
Detailed Description
Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. It should be noted that the embodiments and features of the embodiments may be combined with each other without conflict. The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
Referring to fig. 1 and 2, the present embodiment provides a mirror including: the human body image acquisition system comprises a mirror box 1, a camera device 5 and a processing system 9, wherein a mirror surface 2 is arranged on the mirror box 1, and the camera device 5 faces the outer side of the mirror surface 2 so as to acquire a human body image; the processing system 9 is arranged in the mirror box 1, the processing system 9 is connected with the camera device 5, wherein the processing system 9 is used for carrying out region segmentation on the human body image and selecting a face image from the segmented image; the processing system 9 is further configured to output a human body state parameter according to a comparison result between the facial image and the training image.
It can be seen that, by arranging the camera device 5 and the processing system 9, the processing system 9 performs region segmentation on the acquired human body image, selects a face image from the segmented image, and outputs human body state parameters according to the comparison result of the face image and the training image, thereby not only improving the image quality, but also improving the accuracy and consistency of the diagnosis result of the face and tongue.
As shown in connection with fig. 3-5, in particular, the mirror further comprises: the system comprises a control system 3 and a sensor 4, wherein the sensor 4 comprises a distance sensor 41 and a motion sensor 42, the camera device 5, the distance sensor 41 and the motion sensor 42 are respectively connected with the control system 3, and the distance sensor 41 is used for sensing the distance between a human body and the mirror surface 2 and outputting distance data; the motion sensor 42 is used for sensing the motion characteristics of the human body in front of the mirror and outputting motion characteristic data; the control system 3 controls the camera device 5 to shoot the human body image according to the distance data and the action characteristic data.
Specifically, the camera device 5 is configured to dynamically capture a human body image of a human body located closest to the camera device, and automatically analyze the size and quality of a face image in the captured human body image.
Particularly, the mirror automatically collects, processes and analyzes the facial-lingual image in the human body image; after the camera device 5 is started by the mirror, the face and tongue images of the human body closest to the front of the current camera are dynamically captured through face recognition and automatic focusing, the size and the quality of the captured face images are automatically analyzed, when the face size in the images is not proper, voice prompt is given, after proper images are captured, photographing, image processing and analysis are automatically completed, and the face diagnosis efficiency can be greatly improved.
Specifically, the mirror surface 2 is provided on the mirror box 1, and the imaging device 5 faces the outside of the mirror surface 2, so that the mirror can be used as a normal mirror, and the imaging device 5 can clearly see a diagnostician in front of the mirror and acquire an image for the diagnostician.
Specifically, the mirror box 1 includes six surfaces, and the mirror surfaces 2 may be disposed on the six surfaces, or an appropriate number of mirror surfaces 2 may be disposed as needed.
Specifically, as shown in fig. 3 to 5, a control system 3 and a sensor 4 are provided in the mirror box 1, and the imaging device 5 and the sensor 4 are connected to the control system 3. The sensor 4 senses the human body state parameters of the diagnostician in front of the mirror, and the control system 3 is used for receiving the human body state parameters sensed by the sensor 4 to start the camera device 5 to collect the human body image. The sensor 4 can be preset with certain state parameters of a human body, when a diagnostician is positioned in front of the mirror and in a preset sensing state of the sensor 4, the sensor 4 senses the state parameters of the human body of the diagnostician and sends a signal to the control system 3, and the control system 3 controls the camera device 5 to be started according to the received signal to collect human body images.
Specifically, the imaging device 5 may be disposed inside the mirror box 1, and the imaging device 5 is disposed inside the mirror surface 2 accordingly. In this case, the mirror surface 2 can be set as a single-face mirror, and the single-face mirror has the function that people cannot see objects in the mirror box 1 in front of the mirror; when the mirror box 1 is seen from the inside to the outside, the mirror box is completely transparent glass, and things outside the mirror box 1 can be clearly seen. The diagnostician is positioned in front of the mirror, not only can be used as a common mirror, but also can acquire images for the diagnostician through the camera device 5 on the inner side of the mirror surface 2.
As shown in fig. 3 and 4, the mirror box 1 includes an upper cover 11, a lower cover, and a box body. The imaging device 5 may be provided on the inner surface of the upper cover 11, or may be provided on a lower cover in the mirror box 1. But preferably, camera device 5 sets up on the internal surface of upper cover 11, and the distance between camera device 5 and the human body is nearer like this, and what can shoot is clearer, and the shooting effect is better, and the image of gathering is clearer, and subsequent image processing and analysis and diagnosis are convenient for diagnostic result is more accurate, reliable. Preferably, the image pickup device 5 is a high-definition camera.
Specifically, in order to enable the camera device 5 to better collect human body images, the upper cover 11 can be provided with an opening, and images of a diagnostician in front of the mirror surface 2 are transmitted to the camera device 5 through the opening, so that the collected images are clearer, the image processing is facilitated, and the accuracy of a diagnosis result is improved. The openings may be provided in one, two or more. Preferably, the opening is provided in a plurality of which are evenly distributed on the upper cover 11.
Specifically, the imaging device 5 may be provided on the mirror box 1, and the imaging device 5 may be directed to the outside of the mirror surface 2 to directly capture an image of a human body to a diagnostician without using a hole or a single-plane mirror to capture the image. In this case, the mirror surface 2 can be set as a common mirror, which saves cost.
As shown in fig. 4, a sensing area 12 is provided on the upper cover 11 of the mirror box 1, and the sensor 4 is provided in the sensing area 12. In addition, a prompt mark is provided in the sensing region 12 to prompt the diagnostician that the region is the sensing region 12. The prompt mark can be set into various shapes, such as a circle, an ellipse, a face shape, a rectangle, a square, a heart shape and the like.
Specifically, the sensing area 12 may be the entire area of the upper cover 11, and the diagnostician is located in front of the upper cover 11, the sensor 4 may sense the human body status parameter of the diagnostician and send a signal to the control system 3, and the control system 3 performs a series of operations.
Specifically, the sensing region 12 may be a partial region of the upper cover 11. Different induction areas 12 are arranged according to different requirements, so that different requirements of people are met.
Specifically, when the sensing region 12 is a partial region of the upper cover 11, the sensor 4 may sense only the human body state parameter in the sensing region 12, or may sense the human body state parameter in the entire region of the upper cover 11.
Specifically, when the sensor 4 only senses the human body state parameters in the sensing area 12, the diagnostician is located in the sensing area 12, the sensor 4 can sense the human body state parameters of the diagnostician, and the control system 3 receives the human body state parameters sensed by the sensor 4 to start the camera device 5 to collect the human body image; if the diagnostician is located in the non-sensing area 12, the sensor 4 cannot sense the human body state parameters of the diagnostician, and the control system 3 cannot control the camera device 5 to be turned on.
Specifically, when the sensor 4 senses the human body state parameters in the whole area of the upper cover 11, the diagnostician is positioned in front of the upper cover 11, and even if the diagnostician is not positioned in the sensing area 12, the sensor 4 senses the human body state parameters of the diagnostician, and the control system 3 controls the camera device 5 to be turned on to acquire the human body image. Under the condition, when a diagnostician is located in the induction area 12, the image acquired by the camera device 5 is clearer and more complete, the result of analyzing and processing the image is more accurate and more reliable, and the accuracy of the diagnosis result is improved.
According to the above described embodiments, the mirror may be provided with a switch. When the switch is turned on, the sensor 4 of the mirror senses the human body state parameters of a diagnostician, and the control system 3 controls the camera device 5 to be turned on, collect human body images and other operations; when the switch is closed, the mirror is used as a normal mirror.
In particular, the mirror may also be provided without a switch. If the sensor 4 only senses the human body state parameters in the sensing area 12, when the diagnostician is located in the sensing area 12, the sensor 4 senses the human body state parameters of the diagnostician, and the control system 3 controls the camera device 5 to be started to collect the human body image. When the diagnostician is located in the non-sensing area 12, the sensor 4 cannot sense the human body state parameters of the diagnostician, the control system 3 cannot control the camera device 5 to be turned on, and then the mirror is only used as a common mirror.
Specifically, if the sensor 4 senses the human body state parameters in the whole area of the upper cover 11, the purpose of collecting images according to the intention of a diagnostician can be achieved by correspondingly setting the mirror, that is, related program options such as a "diagnosis mirror" and a "normal mirror" are set on the mirror, when the diagnostician needs to perform diagnosis, the "diagnosis mirror" option is selected, the sensor 4 senses the human body state parameters of the diagnostician, and the control system 3 controls the camera device 5 to be started to collect the human body images; when the diagnostician does not need to diagnose, the ordinary mirror is selected, and the mirror is only used as the ordinary mirror and does not collect images for the diagnostician.
As shown in fig. 3 and 4, the mirror 2 may be provided on the surface of the upper cover 11. Specifically, the mirror surface 2 may be provided on the outer surface of the upper cover 11, or may be provided on the inner surface of the upper cover 11, and the mirror surface may be opened by opening the upper cover 11.
Specifically, the mirror surface 2 may be movably coupled to the housing of the mirror housing 1 to form the upper cover 11. Therefore, the mirror surface 2 can be directly covered on the box body, can also be hinged on the box body through a hinge, can also be movably connected on the box body in a drawing-in and drawing-out mode, can also be connected on the box body through a rotating shaft, and can also be connected on the box body through a hinge.
Specifically, the mirror box 1 is further provided with an indicator light 7, the indicator light 7 is used for prompting a diagnostician that the mirror can start to collect a human body image, and the diagnostician places a part needing diagnosis in front of the mirror according to the prompt of the indicator light 7. The indicator light 7 is connected to the control system 3 and is turned on in response to a command from the control system 3.
Specifically, the indicator light 7 is disposed at a position where the indication of the indicator light 7 can be seen by a diagnostician through the opening in the mirror box 1. Or on the outside of the mirror box 1, such as on the side of the mirror box 1, on the mirror surface 2, etc.
Specifically, the human body state parameters include the distance between the human body and the mirror surface 2 and the motion characteristics of the human body in front of the mirror.
Specifically, the sensor 4 includes a distance sensor 41 for sensing a distance between the human body and the mirror surface 2, and a motion sensor 422 for sensing a motion characteristic of the human body in front of the mirror. The distance sensor 41 and the motion sensor 422 are connected to the control system 3, respectively. Therefore, the mirror can automatically sense the state parameters of the human body through the sensor 4, the posture of a diagnostician is not required to be adjusted, the image of the human body can be acquired, and the mirror is convenient and quick to use and is convenient for the diagnostician to use. Even in an unstable environment, such as a vehicle or in the process of walking, the mirror can acquire images of a human body, so that the mirror is suitable for various environments.
When the distance between the human body and the mirror surface 2 is within a certain range, the distance sensor 41 senses a signal of related information, the information signal is transmitted to the control system 3, and the control system 3 controls other devices to be in a state of waiting to be started. When a human body acts in front of the mirror, the action sensor 422 senses action characteristics and transmits the action characteristic signal to the control system 3, and the control system 3 controls the camera device 5 to be started to collect human body images. The distance between the human body and the mirror surface 2 can be set in advance. The movement of the human body in front of the mirror may be any movement, such as smiling, frowning, blinking, etc., or may be by a gesture, such as a hand swiping or swinging in front of the mirror, etc., which may be sensed by the movement sensor 42.
Specifically, the mirror can diagnose not only the face and tongue, but also other parts of the human body, such as neck, arms, ears, waist, legs and the like, has a wide diagnosis range, enables a diagnostician to diagnose at home or in other various places and under various environments, and has no region limitation.
Specifically, a processing system 9 is arranged in the mirror box 1, the processing system 9 is respectively connected with the control system 3 and the camera device 5, and is used for analyzing and processing human body images acquired by the camera device 5 and transmitting diagnosis results obtained after analysis and processing to the control system 3, and the control system 3 stores and displays the diagnosis results, so that a diagnostician can clearly see the diagnosis results, and trend analysis and remote diagnosis of health conditions are realized.
Specifically, various data such as a standard image of the health condition of each part of the human body, a judgment standard defining a disease or a health condition, a standard analysis of a relevant diagnosis, and the like are preset or stored in the processing system 9, the human body image acquired by the imaging device 5 is transmitted to the processing system 9, the acquired real-time human body image is compared with the standard image, the judgment standard, the standard analysis, and the like preset or stored in the processing system 9, the comparison and analysis comparison results of the image are digitally processed, and a diagnosis result easy to understand by a diagnostician is finally obtained, so that the diagnostician can conveniently know the diagnosis result and know the health state of the diagnostician.
Specifically, the analysis processing of the human body image is not limited to the above structure, and a data input/output interface may be provided on the mirror, and the data input/output interface is used to transmit the human body image acquired by the image pickup device 5 to an external device, such as a computer, a smart phone, or the like, and receive a diagnosis result returned by the external device. The control system 3 transmits the human body image collected by the camera device 5 to the external equipment through the data input and output interface, the external equipment analyzes and processes the collected human body image to obtain a diagnosis result, and the external equipment transmits the diagnosis result to the control system 3 through the data input and output interface.
Specifically, the external device may further store the acquired human body image and the diagnosis result, and may serve as a backup for subsequent query. Meanwhile, the diagnosis result can be displayed through external equipment, so that the diagnostician can conveniently look up the diagnosis result.
In the present embodiment, the processing system 9 is provided in the mirror box 1 as an example.
Specifically, the mirror further comprises a light source 6, the light source 6 is connected with the control system 3 and is turned on or off according to a command of the control system 3, stable light is provided for the camera device 5, and image collection by the camera device 5 is facilitated. When external light is dark, the light source 6 can provide light required by image acquisition for the camera device 5, so that the camera device 5 is not influenced by the external light, and the image acquisition effect is ensured. The light source 6 can be arranged in the mirror box 1, and the light source 6 can penetrate through the opening arranged on the upper cover 11 to provide stable light. The light source 6 may also be arranged on the surface of the mirror surface 2. Preferably, the light source 6 is arranged inside the mirror box 1. More preferably, the light source 6 is disposed on the inner surface of the upper cover 11 of the mirror box 1, and the light source 6 provides stable light through the opening of the upper cover 11. Alternatively, the light source 6 is disposed on a lower cover in the mirror box 1 and corresponds to an opening of the upper cover 11, and the light source 6 provides stable light through the opening of the upper cover 11.
Specifically, the light source 6 is a strip light source 6, and the strip light source 6 is symmetrically arranged on the mirror surface 2 or in the mirror box 1. By arranging the strip-shaped light source 6, the image quality acquired by the camera device 5 is greatly improved.
Preferably, the light sources 6 are LED lamps, and one or more light sources may be provided, and the number of the light sources 6 is set according to specific needs.
The image capturing device 5 is spaced from the light source 6 by a distance that does not affect the image capturing effect. If the distance between the light source 6 and the camera device 5 is too short, the light provided by the light source 6 is strong, the camera device 5 is exposed, the image is not clear, the analysis and the processing of the image by the processing system 9 are affected, and the diagnosis result is affected.
Specifically, the mirror further comprises a display screen 8 used for displaying a diagnosis result, the display screen 8 is connected with the control system 3, the processing system 9 transmits the diagnosis result obtained after the human body image is analyzed and processed to the control system 3, and the control system 3 controls the display screen 8 to display the diagnosis result, so that a diagnostician can conveniently check the diagnosis result. The display screen 8 may be disposed on the outer surface of the side of the mirror box 1, may be disposed on a certain region of the surface of the upper cover 11, or may be disposed outside the mirror box 1, separately from the mirror box 1, and connected by a connection line.
Particularly, the processing system 9 can also be connected with a mobile phone through Bluetooth, and the diagnosis result can be displayed on the mobile phone conveniently and quickly.
Specifically, the control system 3 may further include a storage unit configured to store the human body image acquired by the camera device 5 and a diagnosis result obtained by analyzing and processing the human body image, so as to facilitate subsequent query operations. If the diagnosis result is doubtful, the stored human body image and the diagnosis result can be copied, so that a doctor in a hospital can conveniently analyze the human body image and the diagnosis result, the program of the hospital is saved, and the time is saved.
Specifically, the mirror can be provided with a USB interface and can be connected with a computer, and the acquired human body image, the diagnosis result and the like are displayed on the computer, so that the inquiry and the storage are facilitated.
Specifically, the power required by each device in the mirror can be supplied by a power supply or a battery, and a power supply interface can be arranged on the mirror box 1 and connected with the power supply through a power line, so that stable power is supplied for the normal operation of the mirror. A battery can also be arranged in the mirror box 1, and when the power supply is cut off or the mirror is carried out, the battery can support the normal work of the mirror.
Particularly, the mirror can set up to various patterns, like dressing mirror, wash the mirror, toilet glass, the little mirror of being convenient for carry in the pocket etc. satisfies people's different demands, and is small simultaneously, portable, simple structure moreover, simple to operate.
As shown in fig. 3-5, the specific working process of the mirror is as follows: the following description will take an example in which the sensor 4 senses only the state of the human body in the sensing region 12. When a diagnostician is in front of the mirror, the distance sensor 41 senses the distance between the diagnostician and the mirror surface 2, if the distance between the diagnostician and the mirror surface 2 is within the sensing range of the distance sensor 41, the distance sensor 41 transmits a signal to the control system 3, the control system 3 receives the signal, controls each device to be in a state to be started, controls the indicator light 7 to be turned on, prompts the diagnostician that the mirror is in a starting state, and can start to collect human body images. According to the prompt of the indicator light 7, a diagnostician places a part to be diagnosed in the sensing area 12 in front of the mirror, and has corresponding actions such as smiling, blinking, gesture actions and the like, the action sensor 422 senses the action characteristics of the diagnostician and transmits the action characteristic signals to the control system 3, the control system 3 controls the camera device 5 and the light source 6 to be turned on according to the action characteristic signals, the light source 6 provides stable light for the diagnostician through the opening hole in the upper cover 11, and the camera device 5 collects images for the diagnostician. The human body image collected by the camera device 5 is transmitted to the control system 3 for storage and backup on one hand, and is transmitted to the processing system 9 on the other hand, the processing system 9 analyzes and processes the human body image to obtain a diagnosis result, and transmits the diagnosis result to the control system 3, and the control system 3 stores and backups the diagnosis result and displays the diagnosis result to a diagnostician through the display screen 8 for the diagnostician to check.
It can be seen that the mirror can be used as a common mirror by arranging the mirror surface 2 on the mirror box 1, and the mirror further comprises the camera device 5, wherein the camera device 5 faces the outside of the mirror surface 2, so that the camera device 5 can clearly see a diagnostician in front of the mirror, acquire images of the diagnostician, further analyze and process human body images, and realize trend analysis and remote diagnosis of health conditions; in addition, the sensor 4 for sensing the state parameters of the human body is arranged in the mirror box 1 of the mirror provided by the invention, so that the mirror can automatically sense the human body, is convenient to use, and the action sensor 42 senses the action characteristics of the human body in front of the mirror, so that a diagnostician can acquire images of the human body without adjusting the posture, is convenient and quick, and can acquire the images of the human body even if the diagnostician is in an unstable environment, such as a vehicle or in the process of walking, so that the mirror is suitable for various environments; the mirror that provides in this scheme can set up to various patterns, satisfies people's different demands, for example can set up to toilet glass or be convenient for carry the little mirror in the pocket, and is small, simple structure moreover, simple to operate.
In another preferred implementation manner based on the above embodiment, in this implementation manner, as shown in fig. 2, specifically, the processing system 9 includes an image segmentation module 91, where the image segmentation module 91 is configured to segment a human body image and screen a facial image from the segmented image.
Specifically, the image segmentation module 91 is specifically configured to uniformly segment the human body image into a plurality of first image blocks, and select an image block including facial features from the plurality of first image blocks; and further dividing the image block containing the facial features into a plurality of second image blocks, selecting m image blocks containing forehead and cheek features from the plurality of second image blocks, and marking as m1，m2，...，mmSelecting p image blocks containing tongue features from the second image blocks, and marking as p1，p2，...，ppThe m + p image blocks are taken as face image data.
In particular, the image segmentation module 91 is also particularly useful forMarking out the whole face image by using a rectangular bounding box in the m + p image blocks, taking the image in the rectangular bounding box as a positive sample image block, and marking as A1,A2,..,Am+p。
Specifically, A is1,A2,..,Am+pHeight H of each image block1,H2,..,HnAnd width W1,W2,..,WnAs a two-dimensional data sample set { H1,W1},{H2,W3},...,{Hn,WnH, a two-dimensional data sample set H1,W1},{H2,W3},...,{Hn,WnClustering into N classes by using a clustering algorithm, wherein the central point of each cluster is
Specifically, the image segmentation module 91 is further configured to segment the sample image, uniformly segment the sample image into a plurality of third image blocks, and select an image block including a facial feature from the plurality of third image blocks; and further dividing the image block containing the facial features into a plurality of fourth image blocks, selecting q image blocks containing forehead and cheek features from the plurality of fourth image blocks, and marking as q1，q2，...，qqSelecting r image blocks containing tongue features from the fourth image blocks, and recording as r1，r2，...，rr(ii) a The q + r image blocks are taken as sample image data.
Specifically, the image segmentation module 91 is further specifically configured to mark out the entire sample image with a rectangular bounding box among the q + r image blocks, and mark an image in the rectangular bounding box as a negative sample image block, as B1,B2,..,Bq+r。
Specifically, B1,B2,..,Bq+rHeight H of each image block1 -,H2 -,..,Hn -And width W1 -,W2 -,..,Wn -As a two-dimensional data sample set { H1 -,W1 -},{H2 -,W3 -},...,{Hn -,Wn -H, a two-dimensional data sample set H1 -,W1 -},{H2 -,W3 -},...,{Hn -,Wn -Clustering into N classes by using a clustering algorithm, wherein the central point of each cluster is
Specifically, the processing system 9 further includes a training module 92, and the training module 92 is configured to train the sample image and match the trained sample image with a preset human body state parameter to generate training data.
Specifically, the image segmentation module 91 segments the pre-fabricated sample image, transmits the segmented sample image to the training module 92 for data training, and matches the trained image data with the preset human body state parameter data, so that each trained image corresponds to one human body state parameter.
It can be seen that the algorithm for processing and analyzing the collected human body images by the mirror is a deep learning algorithm, and the algorithm can be trained by increasing the sample size, so that the accuracy and consistency of the detection result are continuously improved.
Specifically, the training module 92 is specifically configured to train the center point of each cluster after the image data is retrained
All correspond to a human body state parameter, the central point of the human body state parameter and each cluster
Correspondingly, N human body state parameters R are recorded as R1,R2,..,RNThe training module 92 generates a subset of human status parameters { R }1,R2,..,RN}. Center of each clusterDot
Linking a subset of human state parameters R1,R2,..,RNHuman body state parameter in.
Specifically, the processing system 9 further includes a comparison module 93, and the comparison module 93 is configured to compare the facial image with the training data, and output the human body state parameter according to the comparison result.
Specifically, the comparison module 93 is specifically configured to receive the positive sample image blocks and the negative sample image blocks, extract, for each of the positive sample image blocks and the negative sample image blocks, the RGB color histogram feature, the histogram of oriented gradients feature, and the local binary pattern feature, respectively, link the three features into a vector, use the vector as the feature of the sample image block, and record the feature of each positive sample image block as the feature of the sample image block
Characterize each negative sample image block
Features of all positive sample image blocks
And features of all negative sample image blocks
Comparing; features of current sample image block
And features of all negative sample image blocks
When the difference between the positive sample image and the negative sample image approaches to 0, the positive sample image and the negative sample image can be confirmed to be the same, and the human body state parameter subset { R corresponding to the negative sample image can be confirmed1,R2,..,RNPeople in (1) }A body state parameter. That is, the human body state parameter corresponding to the face image data is determined by calculating the difference between the face image data and the training image data. Specifically, when the minimum difference exists between the acquired face image data and the training image data, the human body state parameter information corresponding to the face image data can be confirmed.
In particular, the processing system 9 further comprises a classifier, utilizing
As training data, a classifier for classifying the human body state parameters is trained using the training data.
Specifically, after the positive sample images are acquired, all the negative sample images are sequentially traversed for the positive sample images, the difference values between the positive sample images and all the negative sample images are calculated, the traversal structure is classified through a classifier, and when the minimum difference value occurs in the classification result, the negative sample image corresponding to the minimum difference value is the human body state parameter of the positive sample image.
Specifically, when the image capturing device 5 captures a human body image in real time and is segmented by the image segmentation module 91, the segmented image data is compared with the training image data by the comparison module 93, so that the human body parameter information corresponding to the human body image captured by the image capturing device 5 in real time can be determined quickly and accurately.
Therefore, the human body image is segmented, the human body image is trained, and the human body image data is compared with the training data, so that the human body state information can be output quickly and accurately.
Specifically, the image processing module 94 is also configured to adjust the white balance parameter of the camera device 5 through white paper correction.
Specifically, the image processing module 94 sets the white balance parameters of the image pickup apparatus by white paper correction; when the camera shooting equipment collects images and shoots, related white balance parameters are called, meanwhile, the highest point of the face of a human body is used as a reference point through focusing, exposure processing is carried out in a self-adaptive mode according to the brightness of the lamp strip, and therefore color restoration of shooting of the camera shooting equipment is guaranteed.
Specifically, the processing system 9 further includes: and the image processing module 94 is used for correcting the colors of the human body image and the surrounding environment through a histogram algorithm.
It can be seen that the mirror also corrects the collected human body image by combining the colors of the surrounding environment through a histogram algorithm so as to ensure the relatively real color restoration of the human body face.
Specifically, the processing system 9 incorporates an offline algorithm.
Furthermore, when the mirror processes and analyzes the collected human body image, the mirror can perform local off-line processing through a built-in off-line algorithm, and can transmit the collected human body image to a cloud server through a network for remote processing, and finally human body state parameters are output.
It can be seen that, in the mirror, the mirror case 1 is provided with the mirror surface 2 which can be used as a common mirror, and the mirror further comprises the camera device 5, the camera device 5 faces the outside of the mirror surface 2, so that the camera device 5 can clearly see a diagnostician in front of the mirror, and can acquire images of the diagnostician, and further analyze and process the human body images, thereby realizing trend analysis and remote diagnosis of health conditions; in addition, the sensor 4 for sensing the state parameters of the human body is arranged in the mirror box 1 of the mirror provided by the invention, so that the mirror can automatically sense the human body, is convenient to use, and the action sensor 42 senses the action characteristics of the human body in front of the mirror, so that a diagnostician can acquire images of the human body without adjusting the posture, is convenient and quick, and can acquire the images of the human body even if the diagnostician is in an unstable environment, such as a vehicle or in the process of walking, so that the mirror is suitable for various environments; the mirror ensures the consistency and accuracy of the result of image analysis through the white balance setting of the camera equipment, the exposure control in the photographing process, the color reduction of the photographed histogram, and the image segmentation and analysis algorithm based on deep learning after imaging; according to the mirror, the image processing and analyzing algorithm is based on deep learning, and the algorithm can be continuously evolved by increasing sample training; the mirror provided by the invention uses an off-line algorithm and a mobile power supply, so that the convenience in use of the mirror is ensured; the mirror that provides in this scheme can set up to various patterns, satisfies people's different demands, for example can set up to toilet glass or be convenient for carry the little mirror in the pocket, and is small, simple structure moreover, simple to operate.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A mirror, comprising: the human body image acquisition system comprises a mirror box, a camera device and a processing system, wherein a mirror surface is arranged on the mirror box, and the camera device faces the outer side of the mirror surface so as to acquire a human body image; the processing system is arranged in the mirror box and is connected with the camera device, wherein,
the processing system is used for carrying out region segmentation on the human body image and selecting a face image from the segmented image;
the processing system is also used for outputting human body state parameters according to the comparison result of the facial image and the training image.
2. The mirror according to claim 1, wherein said processing system comprises:
and the image segmentation module is used for segmenting the human body image and screening the face image from the segmented image.
3. The mirror as claimed in claim 2, wherein said processing system further comprises:
the training module is used for training the sample image and matching the trained sample image with the preset human body state parameters to generate training data.
4. The mirror according to claim 3, wherein said processing system further comprises:
and the comparison module is used for comparing the facial image with the training data and outputting the human body state parameters according to a comparison result.
5. The mirror according to claim 1, wherein said processing system further comprises:
and the image processing module is used for correcting the colors of the human body image combined with the surrounding environment through a histogram algorithm.
6. The mirror according to claim 5, wherein said image processing module is further configured to adjust white balance parameters of said camera device by white paper correction.
7. The mirror according to claim 1, further comprising a strip light source for providing a steady light to said camera device, said strip light source being symmetrically disposed on said mirror surface.
8. The mirror according to claim 1, wherein said processing system incorporates an off-line algorithm.
9. The mirror according to claim 1, further comprising: a control system, a distance sensor and a motion sensor, wherein the camera device, the distance sensor and the motion sensor are respectively connected with the control system,
the distance sensor is used for sensing the distance between the human body and the mirror surface and outputting distance data;
the motion sensor is used for sensing the motion characteristics of a human body in front of the mirror and outputting motion characteristic data;
and the control system controls the camera device to shoot the human body image according to the distance data and the action characteristic data.
10. A mirror according to claim 9, said camera means being adapted to dynamically capture an image of the body of the person closest to it and to automatically analyze the size and quality of the image of the face of the person in the captured image of the body.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911369545.9A CN111210438A (en) | 2019-12-26 | 2019-12-26 | Mirror |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911369545.9A CN111210438A (en) | 2019-12-26 | 2019-12-26 | Mirror |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111210438A true CN111210438A (en) | 2020-05-29 |
Family
ID=70786505
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911369545.9A Pending CN111210438A (en) | 2019-12-26 | 2019-12-26 | Mirror |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111210438A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112151190A (en) * | 2020-10-09 | 2020-12-29 | 中南大学湘雅二医院 | Intelligent self-sampling mirror capable of being used for reducing cross infection |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102426652A (en) * | 2011-10-10 | 2012-04-25 | 北京工业大学 | Traditional Chinese medicine face color identifying and retrieving method based on image analysis |
| US20150279113A1 (en) * | 2014-03-25 | 2015-10-01 | Metaio Gmbh | Method and system for representing a virtual object in a view of a real environment |
| CN104978584A (en) * | 2014-04-14 | 2015-10-14 | 航天信息股份有限公司 | Fumigation medicine detection method and device based on video monitoring |
| CN105054898A (en) * | 2015-07-24 | 2015-11-18 | 新绎健康科技有限公司 | Mirror |
| CN204889399U (en) * | 2015-08-18 | 2015-12-23 | 蒋彬 | Intelligence body -building mirror |
| US20180293442A1 (en) * | 2017-04-06 | 2018-10-11 | Ants Technology (Hk) Limited | Apparatus, methods and computer products for video analytics |
| CN108851833A (en) * | 2018-06-01 | 2018-11-23 | 辽宁工程技术大学 | Smart pier glass and its training method based on machine learning training algorithm |
-
2019
- 2019-12-26 CN CN201911369545.9A patent/CN111210438A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102426652A (en) * | 2011-10-10 | 2012-04-25 | 北京工业大学 | Traditional Chinese medicine face color identifying and retrieving method based on image analysis |
| US20150279113A1 (en) * | 2014-03-25 | 2015-10-01 | Metaio Gmbh | Method and system for representing a virtual object in a view of a real environment |
| CN104978584A (en) * | 2014-04-14 | 2015-10-14 | 航天信息股份有限公司 | Fumigation medicine detection method and device based on video monitoring |
| CN105054898A (en) * | 2015-07-24 | 2015-11-18 | 新绎健康科技有限公司 | Mirror |
| CN204889399U (en) * | 2015-08-18 | 2015-12-23 | 蒋彬 | Intelligence body -building mirror |
| US20180293442A1 (en) * | 2017-04-06 | 2018-10-11 | Ants Technology (Hk) Limited | Apparatus, methods and computer products for video analytics |
| CN108851833A (en) * | 2018-06-01 | 2018-11-23 | 辽宁工程技术大学 | Smart pier glass and its training method based on machine learning training algorithm |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112151190A (en) * | 2020-10-09 | 2020-12-29 | 中南大学湘雅二医院 | Intelligent self-sampling mirror capable of being used for reducing cross infection |
| CN112151190B (en) * | 2020-10-09 | 2023-07-14 | 中南大学湘雅二医院 | Intelligent self-sampling mirror capable of reducing cross infection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109190540B (en) | Biopsy region prediction method, image recognition device, and storage medium | |
| CN108553081B (en) | Diagnosis system based on tongue fur image | |
| CN107874739A (en) | Eye fundus image capture systems | |
| KR101998595B1 (en) | Method and Apparatus for jaundice diagnosis based on an image | |
| CN109101873A (en) | For providing the electronic equipment for being directed to the characteristic information of external light source of object of interest | |
| US20120157800A1 (en) | Dermatology imaging device and method | |
| CN111128382B (en) | Artificial intelligence multimode imaging analysis device | |
| KR20150107565A (en) | Electronic apparatus for providing health status information, method for controlling the same, and computer-readable storage medium | |
| CN104143086A (en) | Application technology of portrait comparison to mobile terminal operating system | |
| TW201839718A (en) | Skin detection device and the method therefor | |
| KR20110094037A (en) | Video infrared retinal image scanner | |
| CN106859595B (en) | Tongue picture acquisition method, device and system | |
| CN110811564A (en) | Intelligent face image and tongue image acquisition terminal system and face image and tongue image acquisition method | |
| CN102479322A (en) | System, apparatus and method for analyzing facial defect by facial image with angle | |
| CN108353129A (en) | Capture apparatus and its control method | |
| CN110581954A (en) | shooting focusing method and device, storage medium and terminal | |
| CN109008909A (en) | A kind of low-power consumption capsule endoscope Image Acquisition and three-dimensional reconstruction system | |
| CN105054898A (en) | Mirror | |
| CN111210438A (en) | Mirror | |
| CN109117819B (en) | Target object identification method and device, storage medium and wearable device | |
| WO2018150554A1 (en) | Pulse wave measuring device, mobile terminal device, and pulse wave measuring method | |
| CN115359548B (en) | Handheld intelligent pupil detection device and detection method | |
| KR20130063430A (en) | Analysis device of user cognition and method for analysis of user cognition | |
| CN110960194B (en) | Ear phase acquisition device and acquisition method | |
| CN204839460U (en) | Mirror |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |