CN111820875A - Intelligent image acquisition and analysis system and method - Google Patents
Intelligent image acquisition and analysis system and method Download PDFInfo
- Publication number
- CN111820875A CN111820875A CN202010701384.5A CN202010701384A CN111820875A CN 111820875 A CN111820875 A CN 111820875A CN 202010701384 A CN202010701384 A CN 202010701384A CN 111820875 A CN111820875 A CN 111820875A
- Authority
- CN
- China
- Prior art keywords
- image
- color
- skin
- intelligent
- visual
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0077—Devices for viewing the surface of the body, e.g. camera, magnifying lens
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4848—Monitoring or testing the effects of treatment, e.g. of medication
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/48—Other medical applications
- A61B5/4854—Diagnosis based on concepts of traditional oriental medicine
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Pathology (AREA)
- Animal Behavior & Ethology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Alternative & Traditional Medicine (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
The invention relates to an intelligent image acquisition and analysis system and an image acquisition and analysis method, wherein the intelligent image acquisition and analysis system comprises: the system comprises a visible light image acquisition module, a visual 3D data acquisition module and an intelligent analysis module; the visible light image acquisition module and the visual 3D data acquisition module respectively acquire image color data and visual 3D depth data on human skin to send to the intelligent analysis module, namely the intelligent analysis module acquires image color depth, image spot size and density according to the image color data and the visual 3D depth data on the human skin to judge the image condition; according to the invention, the image data of the image and the visual 3D depth data of the image on the skin of the human body are collected, and the image condition is judged by the intelligent analysis module, so that the image can be automatically identified without a professional, the image is identified by objective standard, the subjective uncertainty of the judgment of the personnel is reduced, and the image is collected and stored for tracing and comparison.
Description
Technical Field
The invention belongs to the technical field of intelligent equipment, and particularly relates to an intelligent image acquisition and analysis system and an image acquisition and analysis method.
Background
The scraping therapy is a traditional Chinese medicine technology which applies instruments with blunt and smooth edges, such as a cow horn scraper, a porcelain spoon and the like, and scrapes skin at a certain part of the body surface of a human body by a certain medium to cause local subcutaneous skin spots or skin marks, thereby dredging skin striae, regulating qi and blood and expelling evil.
The skin flare, bright red, purple red or purple black, punctate or sheet-like spots, or slight obstruction of the skin, such as rash touching gravel, is known as "the" condition of skin rash ". The traditional Chinese medicine considers that the 'measles' is the menstrual bleeding which is exuded outside the pulse and contains a large amount of toxin. Western medicine considers that in the disease process, substances with toxin and toxicity are generated due to invasion of bacteria, viruses and the like, or when the functions of human tissues and organs are reduced and diseases occur, metabolites cannot be timely discharged out of the body, retention with different degrees occurs in the body, and endotoxin is formed, and the toxin causes abnormal permeability of capillary vessels, so that congestion or congestion points appear under mucous membranes and skin, namely 'measles'. In conclusion, eruption is not only the manifestation of dysfunction of viscera and imbalance of qi and blood, but also the manifestation of the disease pathogen going out after treatment.
The analysis of the disease manifestations mainly includes observing the color, shape, position and range of the disease, the speed of the disease taking out, the time of the disease going back, etc. The objective and accurate image recognition and analysis can guide disease diagnosis, make treatment schemes and judge treatment effects, and has very important significance for health preservation and health care, clinical treatment and rehabilitation. The method comprises the following specific steps: 1. and (3) diagnosing the disease position: the location of the eruptive organ directly reflects the health condition of the viscera, meridians and tissues corresponding to the location. According to the traditional Chinese medical image-hiding theory, the meridian theory and the western biological holographic theory, a human body is an integral body which takes the internal organs as the center and connects six internal organs, four limbs bones, five sense organs and nine orifices through meridians, qi, blood and body fluids; the meridians and collaterals are the pathways through which the human body circulates qi and blood, connects viscera, communicates the interior and exterior, and runs through the upper and lower parts, and the acupoints are the special parts of the body surface where qi of the viscera and meridians and collaterals is infused; each relatively independent part of the human body is the overall miniature, and the corresponding part of the corresponding zang-fu organ in these local organs and tissues is the holographic acupoint of the corresponding zang-fu organ. Therefore, the eruption phenomenon in the treatment of scraping therapy can directly reflect the pathological changes of viscera, meridians or tissues. 2. Clear nature: the size, shape, density and color of the area of the body are reflected in the severity, course and location of the disease. The eruption is bright red, bright and punctate, and mostly indicates heat pathogen in the body, shallow disease location, short course of disease and mild disease condition; the eruption is dark red or purple black, and is flaky or stagnant, which mostly indicates cold or stasis in the body, deeper disease location, long course of disease and serious disease condition; for most cases, there are abundant qi and blood, excessive heat, blood stasis, or phlegm-dampness; the symptoms of malaise, eruption and scanty eruption are usually qi and blood deficiency. 3. Judging the severity of the disease: the disease is classified by the shape, size and color of the disease macula, the disease manifestations are light, medium and heavy, and the disease manifestations of different degrees reflect different severity of disease. Mild disease usually occurs with scattered disease, and the color is light, which is mostly seen in healthy people or mild sub-healthy people; the moderate eruption is mostly purple red or purple, the eruption spots are usually higher than the surrounding skin and are often accompanied by corresponding malaise reaction, which indicates that the part has long-term microcirculation disturbance and can be seen in sub-health or disease state; the severe acute eruption is manifested as dark cyan, purple black, wrapped block-shaped, and green muscle-like acute eruption spots, which are significantly higher than the skin surface and often accompanied by pain, indicating that microcirculation disturbance exists in local tissues and the disease condition is severe. 4. Judging the constitution: the patients with different constitutions have different skin-scraping symptoms when being subjected to skin scraping, and the following laws are presented. The quality is mild: the scraping therapy does not occur or only has a bit of flaky light red treatment, and no positive reactions such as stringy objects, nodules and the like exist during the scraping therapy; ② qi deficiency and yang deficiency: the eruption speed is slow, only scattered at the eruption point, slight ache during the scraping therapy, and the eruption is accompanied by positive reactants such as cord-like and nodulation; ③ Qi depression: the amount of the resulting product is small, the color is light, the product feels distending pain when scraping the skin, and the product has positive reactions such as streak-like substances and nodules; phlegm dampness and damp-heat: the Guasha is quick in Guasha speed, light red in color and mostly distending pain in pain nature, the Guasha has stagnation and unsmooth feeling under a Guasha board, and severe patients have positive reactions such as skin water seepage and the like; blood stasis: the treatment is quick, and the treatment usually presents purple or black spots, and the treatment with scraping has obvious stabbing pain and often has positive reactions such as nodules. 5. Guiding health preservation and treatment and rehabilitation: according to different treatment conditions, the disease position, disease nature and disease course are analyzed, so as to guide the position, angle, force, speed, length, degree and direction of the treatment by scraping, the clinical medication principle, the diet principle and the method, and the like.
At present, the analysis of the image is mainly performed by professionals with medical knowledge who need relevant knowledge to understand the image, and the image viewed by people has subjectivity and difference of individual judgment.
Therefore, it is necessary to develop a new intelligent image collecting and analyzing system and method to solve the above problems.
Disclosure of Invention
The invention aims to provide an intelligent image acquisition and analysis system and an image acquisition and analysis method.
In order to solve the above technical problems, the present invention provides an intelligent image acquisition and analysis system, which comprises: the system comprises a visible light image acquisition module, a visual 3D data acquisition module and an intelligent analysis module; the visible light image acquisition module and the visual 3D data acquisition module respectively acquire the image color image data and the visual 3D depth data on the human skin to send to the intelligent analysis module, namely the intelligent analysis module acquires the image color depth, the size of the skin spots and the density according to the image color image data and the visual 3D depth data on the human skin to judge the image condition.
Further, the intelligent image acquisition and analysis system further comprises: a lighting module; the lighting module is suitable for providing visible light illumination to assist the visible light image acquisition module in acquiring the color image data of the image on the skin of the human body.
Further, the visible light image acquisition module includes: the lens, the optical filter, the image sensor and the analog-to-digital converter are arranged in sequence; the light irradiated on the skin of the human body is focused on the light sensing surface of the image sensor through the lens, and the optical filter is suitable for filtering out invisible light in the light; and the image sensor outputs RGB original image data to the intelligent analysis module through the analog-to-digital converter.
Further, the visual 3D data acquisition module includes: an image processor, an infrared structured light projector, an infrared camera, and a color camera; the image processor controls the infrared structured light projector to emit infrared light to be projected to the surface of the skin of the human body through a lens; reflecting infrared light rays from the surface of the skin of the human body to a corresponding lens on the infrared camera, and focusing the infrared light rays to the infrared camera by the lens so that the infrared camera acquires a structured light infrared camera image; the image processor acquires a color camera image through a corresponding lens on the color camera; and the image processor acquires visual 3D depth data according to the structured light infrared camera image and the color camera image.
Further, the intelligent analysis module comprises: the system comprises a processing unit, an AMBA3.0 bus electrically connected with the processing unit, an MIPI bus electrically connected with the AMBA3.0 bus and a USB3.0 communication bus; the MIPI bus acquires the image-capturing color image data output by the visible light image acquisition module, and the USB3.0 communication bus acquires the visual 3D depth data output by the visual 3D data acquisition module; the processing unit acquires image color image data transmitted by an MIPI bus and visual 3D depth data transmitted by a USB3.0 communication bus through an AMBA3.0 bus; and the processing unit acquires the depth of the skin color, the size of skin spots and the density according to the skin color image data and the visual 3D depth data on the skin of the human body so as to judge the skin condition.
Further, the lighting module includes: the constant current driving circuit and the white light LED lamp are electrically connected with the intelligent analysis module; the intelligent analysis module is suitable for sending a PWM control signal to the constant current driving circuit so as to drive the white light LED lamp to work.
Further, a popular treatment for sunstroke is obtained through the visible light image acquisition module, and the intelligent analysis module conducts feature recognition training on the popular treatment for sunstroke to obtain a feature recognition neural network for Sharpa recognition; the intelligent analysis module utilizes the characteristic recognition neural network to recognize the skin rash patches in the skin rash image picture, and converts the recognized skin rash patches from RGB original image data through the color space of HSV image data so as to extract the skin rash color and the skin rash color depth; visual 3D depth data are acquired through the visual 3D data acquisition module, and the size of the rash blocks and the density of the rash images are determined, namely the intelligent analysis module judges the condition of the rash images according to the depth of the rash blocks, the size of the rash blocks and the density of the rash images.
In another aspect, the present invention provides a method for collecting and analyzing a skin test image, comprising: white light illumination, collecting image pictures; identifying the rash marks in the image; converting the identified rash patches from RGB original image data to HSV image data through color space conversion to extract the color of the rash image and the depth of the rash color; collecting visual 3D depth data, and determining the size of the rash blocks and the density of the rash images; according to the depth of the color, the size of the spot and the density, the condition of the disease is judged.
Furthermore, the image recognition is carried out through deep learning feature recognition, and the neural network is trained through the feature recognition.
Furthermore, the method for collecting and analyzing the image is suitable for collecting and analyzing the image by adopting the intelligent image collecting and analyzing system.
The invention has the advantages that the visual image acquisition module and the visual 3D data acquisition module are used for acquiring the image color data and the visual 3D depth data of the patient on the skin of the human body, and the intelligent analysis module is used for judging the condition of the patient, so that the patient can be automatically identified without a professional, the objective standard for identifying the patient is provided, the subjective uncertainty of the judgment of the person is reduced, and the image is acquired and stored for tracing and comparison.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a schematic block diagram of an intelligent image acquisition and analysis system according to the present invention;
FIG. 2 is a circuit diagram of the intelligent image acquisition and analysis system of the present invention;
FIG. 3 is a flow chart of the method for collecting and analyzing the skin test images of the present invention;
FIG. 4 is a data processing diagram of the image acquisition and analysis method of the present invention;
fig. 5 is a feature recognition training process of the image acquisition and analysis method of the present invention.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the scope of protection of the present invention.
Example 1
FIG. 1 is a schematic block diagram of an intelligent image acquisition and analysis system according to the present invention;
fig. 2 is a circuit diagram of the intelligent image acquisition and analysis system of the invention.
In this embodiment, as shown in fig. 1 and fig. 2, the present embodiment provides an intelligent image capturing and analyzing system, which includes: the system comprises a visible light image acquisition module, a visual 3D data acquisition module and an intelligent analysis module; the visible light image acquisition module and the visual 3D data acquisition module respectively acquire the image color data and the visual 3D depth data on the human skin to send to the intelligent analysis module, namely the intelligent analysis module acquires the image color depth, the size of the image spot and the density according to the image color data and the visual 3D depth data on the human skin to judge the image condition.
In the embodiment, the visual image acquisition module and the visual 3D data acquisition module are used for acquiring the image color data and the visual 3D depth data of the patient's skin, and the intelligent analysis module is used for judging the condition of the patient's skin, so that the patient's skin can be automatically identified without a professional, the objective standard is provided for identifying the patient's skin, the subjective uncertainty of the judgment of the person is reduced, and the image is acquired and stored for tracing and comparison.
In this embodiment, the intelligent image capturing and analyzing system further includes: a lighting module; the lighting module is suitable for providing visible light illumination to assist the visible light image acquisition module in acquiring the image-forming color image data on the skin of a human body.
In this embodiment, the lighting module is responsible for providing local active visible light illumination, and the white light LED with high luminous efficiency realizes lower power consumption and higher illumination brightness, and reduces the influence of the external illumination environment on the visible light image acquisition module.
In this embodiment, the visible light image capturing module includes: the lens, the optical filter, the image sensor and the analog-to-digital converter are arranged in sequence; the light irradiated on the skin of the human body is focused on the photosensitive surface of the image sensor through the lens, and the optical filter is suitable for filtering out invisible light in the light; and the image sensor outputs RGB raw image data to the intelligent analysis module through the analog-digital converter.
In this embodiment, the image sensor may be, but is not limited to, a high-definition wide dynamic low-illumination CMOS process image sensor, which can well restore a real image, provide an image with high color restoration for the intelligent analysis module to identify the image, and improve the image identification accuracy.
In this embodiment, the visual 3D data acquisition module includes: an image processor, an infrared structured light projector, an infrared camera, and a color camera; the image processor controls the infrared structured light projector to emit infrared light to be projected to the surface of the skin of the human body through a lens; reflecting infrared light rays from the surface of the skin of the human body to a corresponding lens on the infrared camera, and focusing the infrared light rays to the infrared camera by the lens so that the infrared camera acquires a structural light infrared camera image; the image processor acquires a color camera image through a corresponding lens on the color camera; and the image processor acquires visual 3D depth data according to the structured light infrared camera image and the color camera image.
In this embodiment, the infrared camera may be, but is not limited to, an infrared structured light 3D camera, provides a micron-sized high-precision detection, realizes an ultra-high speed surface scanning mode, outputs a full-field-of-view three-dimensional point cloud at one time, and supports real-time high-precision measurement.
In this embodiment, the intelligent analysis module includes: the system comprises a processing unit, an AMBA3.0 bus electrically connected with the processing unit, an MIPI bus electrically connected with the AMBA3.0 bus and a USB3.0 communication bus; the MIPI bus acquires the image-capturing color image data output by the visible light image acquisition module, and the USB3.0 communication bus acquires the visual 3D depth data output by the visual 3D data acquisition module; the processing unit acquires image color image data transmitted by an MIPI bus and visual 3D depth data transmitted by a USB3.0 communication bus through an AMBA3.0 bus; and the processing unit acquires the depth of the skin color, the size of skin spots and the density according to the skin color image data and the visual 3D depth data of the human body so as to judge the skin condition.
In the embodiment, the processing unit adopts a circuit module taking a Cortex A7 processor as a core, stores the circuit module in a flash memory, and loads the circuit module into a dynamic memory for execution by starting the functions of the memory and the static memory; acquiring a color image output by a visible light image acquisition module through an MIPI bus, and acquiring visual 3D depth data output by a visual 3D data acquisition module through a USB3.0 communication bus; the processing unit is internally provided with image data related circuit components such as an image processing unit, a video graphic unit, a video processing unit, a video codec, a neural network acceleration engine and the like, so that the image acquisition and storage of the image picture in a local flash memory and the image processing-based image recognition analysis are realized.
In this embodiment, the lighting module includes: the constant current driving circuit and the white light LED lamp are electrically connected with the intelligent analysis module; the intelligent analysis module is suitable for sending a PWM control signal to the constant current driving circuit so as to drive the white light LED lamp to work.
In this embodiment, the constant current driving circuit lights the white LED lamp, and the brightness is controlled by the PWM signal sent by the intelligent analysis module.
In the embodiment, a popular treatment for sunstroke is obtained by the visible light image acquisition module, and the intelligent analysis module performs feature recognition training on the popular treatment for sunstroke to obtain a feature recognition neural network for Sharpa recognition; the intelligent analysis module utilizes the characteristic recognition neural network to recognize the rash blocks in the image picture, and converts the recognized rash blocks from RGB original image data to HSV image data through color space conversion so as to extract the color and the shade of the rash blocks; visual 3D depth data are acquired through the visual 3D data acquisition module, and the size of the rash blocks and the degree of density of the rash image are determined, namely the intelligent analysis module judges the condition of the rash image according to the depth of the rash block, the size of the rash blocks and the degree of density.
Example 2
FIG. 3 is a flow chart of the method for collecting and analyzing the skin test images of the present invention;
fig. 4 is a data processing diagram of the image acquisition and analysis method of the present invention.
On the basis of embodiment 1, as shown in fig. 3 and 4, the present embodiment provides a method for collecting and analyzing a measles image, which includes: white light illumination, collecting image pictures; identifying the rash marks in the image; converting the identified rash patches from RGB original image data through the color space of HSV image data to extract the color and the shade of the rash image; collecting visual 3D depth data, and determining the size of the rash blocks and the density of the rash images; according to the depth of the color, the size of the spot and the density, the condition of the disease is judged.
In this embodiment, as shown in fig. 4, in the data processing process of the image acquisition and analysis method, after the image is obtained, the image is subjected to feature recognition training to obtain a feature recognition neural network for sarsa identification, and then the feature recognition neural network is used to identify the skin rash in the image.
Fig. 5 is a feature recognition training process of the image acquisition and analysis method of the present invention.
In the present embodiment, as shown in fig. 5, the sural image recognition is performed by deep learning feature recognition, and the neural network is trained by the feature recognition.
In this embodiment, the training process of the feature recognition training neural network is as follows: firstly, initializing a weight value by a network; and secondly, carrying out convolution, linear rectification, pooling and forward transmission of the input data in a complete connection mode to obtain an output value. Convolution layer, convolution kernel is a set of parallel characteristic maps, and a certain operation is executed by sliding different convolution kernels on an input image. The linear rectification layer obtains the output of the convolutional layer nerves using linear rectification f (x) max (0, x) as an excitation function. Pooling layer, which is a nonlinear form of down-sampling; the pooling window selects a 2 x 2 two-dimensional maximum pooling, divides 2 x 2 blocks from the image every 2 elements, then maximizes the 4 numbers in each block,
and the characteristic graph is subjected to characteristic extraction of the convolution layer and the pooling layer, the extracted characteristics are transmitted to the full connection layer, classification is carried out through the full connection layer, a classification model is obtained, and a final result is obtained. And thirdly, solving the error between the output value of the network and the target value. A loss function layer for deciding how the training process "penalizes" the differences between the predicted and true results of the network; and fourthly, when the error is larger than the expected value, the error is transmitted back to the network for back propagation training, and the errors of the full-connection layer, the pooling layer and the convolution layer are obtained in sequence. The error of each layer can be understood as the total error of the network, and the network can bear the total error; when the error is equal to or less than our expected value, the training is finished; and fifthly, updating the weight according to the obtained error, and then entering the second step.
In this embodiment, the method for collecting and analyzing the image is suitable for collecting and analyzing the image by using the intelligent system for collecting and analyzing the image as provided in embodiment 1.
In the present embodiment, the intelligent image collecting and analyzing system is described in the above embodiments.
In summary, the visual image acquisition module and the visual 3D data acquisition module are used for acquiring the image color data and the visual 3D depth data of the patient's skin, and the intelligent analysis module is used for judging the condition of the patient's skin, so that the patient's skin can be automatically identified without a professional, the objective standard for identifying the patient's skin is provided, the subjective uncertainty of the judgment of the person is reduced, and the image is acquired and stored for tracing and comparison.
The components selected for use in the present application (components not illustrated for specific structures) are all common standard components or components known to those skilled in the art, and the structure and principle thereof can be known to those skilled in the art through technical manuals or through routine experiments.
In the description of the embodiments of the present invention, unless otherwise explicitly specified or limited, the terms "mounted," "connected," and "connected" are to be construed broadly, e.g., as meaning either a fixed connection, a removable connection, or an integral connection; can be mechanically or electrically connected; either directly or indirectly through intervening media, or may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
In the description of the present invention, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the devices or elements referred to must have a specific orientation, be constructed in a specific orientation, and be operated, and thus are not to be construed as limiting the present invention.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed.
Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.
In light of the foregoing description of the preferred embodiment of the present invention, many modifications and variations will be apparent to those skilled in the art without departing from the spirit and scope of the invention. The technical scope of the present invention is not limited to the content of the specification, and must be determined according to the scope of the claims.
Claims (10)
1. An intelligent image acquisition and analysis system is characterized by comprising:
the system comprises a visible light image acquisition module, a visual 3D data acquisition module and an intelligent analysis module; wherein
The visible light image acquisition module and the visual 3D data acquisition module respectively acquire the image color image data and the visual 3D depth data of the human skin to send to the intelligent analysis module, namely
The intelligent analysis module obtains the depth of the skin color, the size of skin spots and the density according to the skin color image data and the visual 3D depth data on the skin of a human body so as to judge the skin condition.
2. The intelligent image acquisition and analysis system of claim 1,
the intelligent image acquisition and analysis system further comprises: a lighting module;
the lighting module is suitable for providing visible light illumination to assist the visible light image acquisition module in acquiring the image-forming color image data on the skin of a human body.
3. The intelligent image acquisition and analysis system of claim 1,
the visible light image acquisition module includes: the lens, the optical filter, the image sensor and the analog-to-digital converter are arranged in sequence;
the light irradiated on the skin of the human body is focused on the photosensitive surface of the image sensor through the lens, and the optical filter is suitable for filtering out invisible light in the light; and
the image sensor outputs RGB raw image data to the intelligent analysis module through the analog-to-digital converter.
4. The intelligent image acquisition and analysis system of claim 1,
the visual 3D data acquisition module includes: an image processor, an infrared structured light projector, an infrared camera, and a color camera;
the image processor controls the infrared structured light projector to emit infrared light to be projected to the surface of the skin of the human body through a lens;
reflecting infrared light rays from the surface of the skin of the human body to a corresponding lens on the infrared camera, and focusing the infrared light rays to the infrared camera by the lens so that the infrared camera acquires a structural light infrared camera image;
the image processor acquires a color camera image through a corresponding lens on the color camera; and
the image processor acquires visual 3D depth data according to the structured light infrared camera image and the color camera image.
5. The intelligent image acquisition and analysis system of claim 1,
the intelligent analysis module comprises: the system comprises a processing unit, an AMBA3.0 bus electrically connected with the processing unit, an MIPI bus electrically connected with the AMBA3.0 bus and a USB3.0 communication bus;
the MIPI bus acquires the image-capturing color image data output by the visible light image acquisition module, and the USB3.0 communication bus acquires the visual 3D depth data output by the visual 3D data acquisition module;
the processing unit acquires image color image data transmitted by an MIPI bus and visual 3D depth data transmitted by a USB3.0 communication bus through an AMBA3.0 bus; and
the processing unit obtains the depth of the skin color, the size of skin spots and the density according to the skin color image data and the visual 3D depth data on the skin of the human body so as to judge the skin condition.
6. The intelligent image acquisition and analysis system of claim 2,
the lighting module includes: the constant current driving circuit and the white light LED lamp are electrically connected with the intelligent analysis module;
the intelligent analysis module is suitable for sending a PWM control signal to the constant current driving circuit so as to drive the white light LED lamp to work.
7. The intelligent image acquisition and analysis system of claim 1,
acquiring a sural image picture through a visible light image acquisition module, and performing feature recognition training on the sural image picture through an intelligent analysis module to obtain a feature recognition neural network for Sharpa recognition;
the intelligent analysis module utilizes the characteristic recognition neural network to recognize the rash blocks in the image of the rash, and converts the recognized rash blocks from RGB original image data to HSV image data through color space conversion so as to extract the color and the shade of the rash blocks;
visual 3D depth data are acquired through a visual 3D data acquisition module, and the size of the rash spots and the density of the rash images are determined, namely
The intelligent analysis module judges the condition of the disease symptoms according to the color depth, the size and the density of the disease spots.
8. A method for collecting and analyzing a sural image is characterized by comprising the following steps:
white light illumination, collecting image pictures;
identifying the rash marks in the image;
converting the identified rash patches from RGB original image data to HSV image data through color space conversion to extract the color of the rash image and the depth of the rash color;
collecting visual 3D depth data, and determining the size of the rash blocks and the density of the rash images;
according to the depth of the color, the size of the spot and the density, the condition of the disease is judged.
9. The method of claim 8, wherein the image is collected and analyzed,
the image recognition is carried out through the deep learning characteristic recognition, and the neural network is trained through the characteristic recognition.
10. The method of claim 8, wherein the image is collected and analyzed,
the method for collecting and analyzing the test images is suitable for collecting and analyzing the test images by adopting the intelligent test image collecting and analyzing system according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010701384.5A CN111820875A (en) | 2020-07-20 | 2020-07-20 | Intelligent image acquisition and analysis system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010701384.5A CN111820875A (en) | 2020-07-20 | 2020-07-20 | Intelligent image acquisition and analysis system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111820875A true CN111820875A (en) | 2020-10-27 |
Family
ID=72924384
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010701384.5A Pending CN111820875A (en) | 2020-07-20 | 2020-07-20 | Intelligent image acquisition and analysis system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111820875A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115381690A (en) * | 2021-05-22 | 2022-11-25 | 左点实业（湖北）有限公司 | Scraping and cupping device suitable for home physiotherapy |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106725314A (en) * | 2016-12-05 | 2017-05-31 | 牛欣 | The traditional Chinese medical science based on Quick Response Code, topological code quantifies to distinguish color Diagnostic technique and procedure |
| TWM576459U (en) * | 2018-03-19 | 2019-04-11 | 王景嫻 | Moxibustion gua sha vase |
| CN111420301A (en) * | 2019-01-10 | 2020-07-17 | 中国科学院沈阳自动化研究所 | Robotized body surface focus area positioning and tracking system |
-
2020
- 2020-07-20 CN CN202010701384.5A patent/CN111820875A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106725314A (en) * | 2016-12-05 | 2017-05-31 | 牛欣 | The traditional Chinese medical science based on Quick Response Code, topological code quantifies to distinguish color Diagnostic technique and procedure |
| TWM576459U (en) * | 2018-03-19 | 2019-04-11 | 王景嫻 | Moxibustion gua sha vase |
| CN111420301A (en) * | 2019-01-10 | 2020-07-17 | 中国科学院沈阳自动化研究所 | Robotized body surface focus area positioning and tracking system |
Non-Patent Citations (1)
| Title |
|---|
| 李戈主编: "《新编实用刮痧疗法》", 30 June 2012, 金盾出版社 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115381690A (en) * | 2021-05-22 | 2022-11-25 | 左点实业（湖北）有限公司 | Scraping and cupping device suitable for home physiotherapy |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110600122B (en) | Digestive tract image processing method and device and medical system | |
| Yang et al. | Automatic identification of human helminth eggs on microscopic fecal specimens using digital image processing and an artificial neural network | |
| CN108670285A (en) | A kind of CT pulmonary tuberculosis detection artificial intelligence diagnosis and therapy system | |
| CN103892802B (en) | Novel tongue imaging intelligent auxiliary device | |
| CN105913075A (en) | Endoscopic image focus identification method based on pulse coupling nerve network | |
| CN109948671B (en) | Image classification method, device, storage medium and endoscopic imaging equipment | |
| CN110960193A (en) | Traditional Chinese medicine diagnosis analysis system and method based on face and tongue image acquisition | |
| Qiu et al. | GFANet: Gated fusion attention network for skin lesion segmentation | |
| CN111820875A (en) | Intelligent image acquisition and analysis system and method | |
| CN110390678A (en) | A kind of organization type dividing method of colorectal cancer IHC dye image | |
| Qiu et al. | Endoscopic image recognition method of gastric cancer based on deep learning model | |
| CN113749642A (en) | Method, system, medium and terminal for quantifying degree of skin flushing response | |
| CN109241963A (en) | Blutpunkte intelligent identification Method in capsule gastroscope image based on Adaboost machine learning | |
| CN111462082A (en) | Focus picture recognition device, method and equipment and readable storage medium | |
| CN1278421A (en) | Disease diagnosing and predicting system | |
| CN116453171A (en) | Method and device for detecting blood vessel color in white eye area, electronic equipment and medium | |
| CN116664592A (en) | Image-based arteriovenous blood vessel separation method and device, electronic equipment and medium | |
| CN205317657U (en) | Icteric sclera detector based on colorimetric analysis | |
| CN110516690A (en) | A kind of Tibetan medicine's urine color automatic recognition method based on deep learning | |
| AU2021104559A4 (en) | Personal health management system based on image recognition and big data | |
| CN115719329A (en) | Method and system for fusing RA ultrasonic modal synovial membrane scores based on deep learning | |
| Huang et al. | Real-time colonoscopy image segmentation based on ensemble knowledge distillation | |
| CN115035086A (en) | Intelligent tuberculosis skin test screening and analyzing method and device based on deep learning | |
| Lin et al. | Automatic sublingual vein feature extraction system | |
| CN203861194U (en) | Novel intelligent tongue image assisting device |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20201027 |
|
| RJ01 | Rejection of invention patent application after publication |