CN208172859U - A kind of intelligent image acquisition device - Google Patents
A kind of intelligent image acquisition device Download PDFInfo
- Publication number
- CN208172859U CN208172859U CN201820630508.3U CN201820630508U CN208172859U CN 208172859 U CN208172859 U CN 208172859U CN 201820630508 U CN201820630508 U CN 201820630508U CN 208172859 U CN208172859 U CN 208172859U
- Authority
- CN
- China
- Prior art keywords
- module
- image
- camera
- slot
- acquisition 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.)
- Expired - Fee Related
Links
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The utility model discloses a kind of intelligent image acquisition devices, including, portion of the handle, connecting rod, the portion of the handle is equipped with the first button and the second button, the connection boom end is equipped with acquisition module, the acquisition module, including camera, micro-lens, imaging sensor, LED light, the camera camera shooting end is externally provided with for focusing, camera is set to shoot the micro-lens of very subtle object, the imaging sensor input terminal connect and carries out data transmission with camera output end, the microprocessor input terminal of the imaging sensor output end and primary processor connects and carries out data transmission；The primary processor signal input part also connect and carries out data transmission with gyroscope, memory, wireless module, key, LED light, power management module output end respectively.The utility model is compared with the existing technology, simple and convenient, widely used, and video capture range is wide, it can be achieved that automatically correcting to image.
Description
Technical field
The utility model relates to a kind of medical equipments, more particularly to a kind of intelligent image acquisition device.
Background technique
China always exists the problem of the difficulty of getting medical service at present, is mainly reflected in that patient is more, and doctor is few, sees a doctor Shi doctor's needs
It inquires, diagnose for each patient, see a doctor inefficient.The tooth disease diagnosing is the exception occurred according to tooth, gingival position
The method that lesion characteristics carry out auxiliary diagnosis often can be in tooth according to dentist it was verified that when the tooth of people is there are when illness
There are the anomalous variations such as corresponding form, color, texture in tooth or the different position of gum, and traditional teeth disease can be special based on these
The presentation of sign variation diagnoses dental disorders, but the personal experience that these diagnosis are based on doctor judges therefore, how to improve
The tooth disease diagnosing efficiency realizes that the tooth disease diagnosing of automation is always urgent problem.
Method (picture and slr camera, the photo after acquisition) (such as oral cavity, armpit in particular circumstances of traditional images acquisition
Inferior position) have following inconvenient place：
1, it is desirable that relatively high shooting skill；
2, the ancillary equipments such as mouth expander are needed to oral cavity acquisition, single-lens reflex camera cost is also high；
3, it is only capable of getting part oral cavity inner teeth gear image.
For the endoscope under oral environment, usual areas imaging is 1CM-2.5CM, and areas imaging is low, using dedicated volume
Code chip, does not have image processing function.Due to angular transformation when shooting, image will appear overturning or inversion, cannot automatic school
Just.
Therefore, applicant proposes a kind of intelligent image acquisition device, compact structure and has image processing function.
Utility model content
In view of the above drawbacks of the prior art, the technical problem to be solved by the utility model is to provide a kind of intelligent graphics
As acquisition device.
To achieve the above object, the utility model provides a kind of intelligent image acquisition device, including, portion of the handle, even
Extension bar, the portion of the handle are equipped with the first button and the second button, and the connection boom end is equipped with acquisition module, obtains
Modulus block is for obtaining tooth regions image to be detected；
The acquisition module, including camera, micro-lens, imaging sensor, LED light, the camera camera shooting
End is externally provided with the micro-lens for focusing, making camera to shoot very subtle object, the imaging sensor input
End connect and carries out data transmission with camera output end, the miniature processing of the imaging sensor output end and primary processor
Device input terminal connects and carries out data transmission；
The primary processor controls the current switching and size, frequency of each electrical equipment for receiving and dispatching, parsing control instruction
Rate；
The primary processor signal input part also respectively with gyroscope, memory, wireless module, key, LED indication
Lamp, power management module output end connect and carry out data transmission；
The gyroscope is used to detect the angle of camera rotation, in order to which later period primary processor is to the angle of shooting image
Degree is corrected；
The memory is for storing data；The wireless module is used to be wirelessly connected with external equipment, from
And it realizes and carries out wireless data transmission with external equipment；
The key is used to export control instruction, including the first button and the second button to primary processor；
The LED light is used to indicate master controller and receives the states such as preset instructions；The power management module
It powers for detecting battery capacity, while to power supply circuit.
Preferably, the primary processor, including power supply circuit and microprocessor；The power supply circuit is used for as camera shooting
Head, micro-lens, imaging sensor, LED light, gyroscope, memory, wireless module, microprocessor, LED light power supply.
Preferably, frequency modulator or FM circuit are additionally provided on the power supply circuit, the frequency modulator is for adjustment pair
The frequency of supply current or voltage.
Preferably, the acquisition module is encapsulated using miniature flexible encapsulation technology, is collected using FPC as sill, above
At having cmos image sensor, LED light, micro-lens.
Preferably, the power management module is connect into electric end with the one of current output terminal of wireless charging module, wirelessly
Another current output terminal of charging module connect conduction with battery current output terminal, and the wireless charging module can cooperate with external equipment to be realized
Wireless charging.
Preferably, the acquisition module is mounted in waterproof cover, is waterproof inner shell inside the waterproof cover, and described
Waterproof cover on be additionally provided with card slot, the card slot and the clamping of clamping end, the clamping end are arranged on elastic strip one end, institute
The elastic strip other end and the connecting rod stated are connected and fixed, and the connecting rod is equipped with holding cylinder on being provided with elastic strip one end,
It is connected between the holding cylinder and connecting rod by stage body, the stage body is adjacent to waterproof cover end face；
It is additionally provided with the first through slot and the second through slot in the holding cylinder, is equipped with hollow connection inside the connecting rod
Inner cylinder, and stop collar is additionally provided in holding cylinder, the holding drum outer wall are equipped with sealing ring, in the sealing ring and waterproof cover
Wall is adjacent to sealing；
Clamping cylinder is installed inside the holding cylinder, is equipped with outside the clamping cylinder and is each passed through the first through slot, the
The first card-tight part, the second card-tight part of two through slots and the clamping of waterproof cover inner wall；First through slot, the second through slot are respectively set
The two sides above and below sealing ring, first through slot, the second through slot respectively at least there are two, and be uniformly arranged on holding cylinder respectively
In circumferential direction.
Preferably, waterproof membrane is being equipped with bulge loop with clamping end corresponding position.
Preferably, the elastic strip is made of elastic material.
Preferably, the acquisition module includes：
Acquisition unit (camera), for acquiring image to be detected using image capture device；
Detection unit (imaging sensor), for detecting whether described image to be detected deposits based on AdaBoost detection algorithm
In tooth regions, if so, determining that described image to be detected is tooth regions image to be detected.
Preferably, further include：
Quality assessment module, for being obtained pair to the tooth regions image degree of comparing to be detected and brightness evaluation
Deviate angle value than degree and brightness deviates angle value, angle value is greater than first threshold and/or the brightness deviates when the contrast deviates
Angle value carries out enhancing processing to the tooth regions image to be detected when being greater than second threshold.
Another embodiment according to the present invention further includes odontopathy identification model training module, including：
Odontopathy coarse positioning and taxon, for inputting multiple tooth regions sample images to the MASK-RCNN convolution
Neural network classifier obtains the odontopathy coarse positioning and classification results of multiple tooth regions sample images；
Filter element, for filtering multiple described tooth regions sample graphs based on the odontopathy coarse positioning and classification results
Picture；
Color and Texture Matching unit, for carrying out color and texture to the filtered tooth regions sample image
With the processing odontopathy sample image that obtains that treated；
Model foundation unit, for establishing odontopathy identification model according to the odontopathy sample image.
The utility model has the beneficial effects that：The utility model is compared with the existing technology, simple and convenient, widely used, depending on
Frequency coverage is wide, it can be achieved that automatically correcting to image.It can be achieved to carry out image to the image of acquisition with embedded software cooperation
Enhancing, Texture Segmentation, target classification and identification etc. automatically process.
Detailed description of the invention
Fig. 1 is a kind of flow diagram of one embodiment of the tooth disease diagnosing method of the invention；
Fig. 2 is a kind of flow diagram of another embodiment of the tooth disease diagnosing method of the invention；
Fig. 3 is a kind of process signal of one embodiment of the odontopathy identification model training of the tooth disease diagnosing method of the invention
Figure；
Fig. 4 is a kind of structural block diagram of one embodiment of intelligent image acquisition device of the invention；
Fig. 5 is a kind of structural block diagram of another embodiment of intelligent image acquisition device of the invention；
Fig. 6 is the structural schematic diagram of MASK-RCNN convolutional neural networks of the invention.
Fig. 7 is a kind of main view of the specific embodiment of intelligent image acquisition device of the invention.
Fig. 8 is a kind of left view of the specific embodiment of intelligent image acquisition device of the invention.
Fig. 9 is a kind of top view of the specific embodiment of intelligent image acquisition device of the invention.
Figure 10 is that a kind of waterproof cover of the specific embodiment of intelligent image acquisition device of the invention and link rod part dispense
Distribution structure schematic diagram.
Figure 11 is assembled portion A-A cross-sectional view in Figure 10.
Figure 12 is clamping cylinder B-B cross-sectional view in Figure 10 (after removal sealing ring).
Figure 13 is a kind of electrical system schematic diagram of intelligent image acquisition device of the invention.
Specific embodiment
The utility model is described in further detail with reference to the accompanying drawings and examples：
On the one hand, as shown in Figure 1-3, the embodiment of the invention provides a kind of the tooth disease diagnosing methods, including：
Step 100：Obtain tooth regions image to be detected；
Step 200：Tooth regions image to be detected is input to odontopathy identification model and carries out odontopathy identification, and exports tooth
Sick recognition result, odontopathy recognition result include odontopathy position and odontopathy type.
The tooth disease diagnosing method of the embodiment of the present invention is by obtaining tooth regions image to be detected, and it is input to odontopathy
Identification model carries out odontopathy and identifies to obtain odontopathy position and odontopathy type, the convenient diagnosis for realizing odontopathy of intelligence.The present invention is real
The tooth disease diagnosing method of example is applied using the image dental diagnostic method based on deep learning, protracted experience will be needed in conventional dental
The diagnosis method of discrimination of accumulation is converted into the automatic recognition classification method of machine learning, effectively improves the efficiency of auxiliary diagnosis,
Realize the automation of the tooth disease diagnosing.
As one for example, the step 100 of the tooth disease diagnosing method of the embodiment of the present invention includes：
Step 101：Image to be detected is acquired using intelligent image acquisition device；
Image to be detected of the embodiment of the present invention can be by special intelligent image collecting device, can also be by peeping in oral cavity
The mobile terminals such as mirror, X-ray scanners or camera, mobile phone obtain to acquire.
It should be noted that the advantages of acquiring image using common camera is that adjustment mode is simple, it may make that image is complete
Office has more general visual effect, but can not carry out imaging control for specific dynamic object, especially in different illumination
Environmental condition under, tooth target can not be made to reach good imaging effect；Using the mobile terminals such as mobile phone acquisition image
Advantage is that versatility is stronger, carries out auto-focusing for selection region, while carrying out brightness imaging control based on selection region,
But it is more demanding for the image quality of odontopathy as the auxiliary diagnosis of mobile terminal, thus for the clarity of image and
Luminance contrast has independent judging quota, meanwhile, the position size and operability of regional choice can all have final imaging
It influences, also has higher operation requirement to the shooting skill of user, be not suitable for being applicable in for generality；Stomatology endoscope, X are penetrated
The selection that line scanner acquires its photo environment of image, angle and pattern measurement point is carried out by manual measurement, image enhancement
It is for the ease of DATA REASONING with processing, whole purpose is for doing data acquisition, and as sentencing to machine learning and automatically
Other image is simultaneously improper.Therefore, in order to guarantee the quality of picture to be detected, it is preferred to use special intelligent image collecting device.
Step 102：Image to be detected is detected with the presence or absence of tooth regions, if so, sentencing based on AdaBoost detection algorithm
Determining image to be detected is tooth regions image to be detected.
In image acquisition process, it would be desirable to the position of real-time monitoring tooth, the tooth disease diagnosing side of the embodiment of the present invention
Method carries out target detection using AdaBoost algorithm.AdaBoost algorithm is a series of Weak Classifier to be combined into one strong point
Class device provides example set first, then carries out circulate operation to the example set, circulation obtains a weak vacation first every time
If then calculating the error rate of the hypothesis, next circulation, algorithm are entered according to the weight that the error rate changes each example
Process is as follows：
1) the weight distribution of training data is initialized.If there is N number of image pattern, then when each training sample most starts
All it is endowed identical weight：1/N；
2) training Weak Classifier.In specific training process, if some sample point is accurately classified, in structure
It makes in next training set, its weight is just lowered；On the contrary, if some sample point is not classified accurately, it
Weight be just improved.Then, the sample set that right value update is crossed be used to train next classifier, and entire training process is such as
This is made iteratively down.
3) Weak Classifier that each training obtains is combined into strong classifier.The training process of each Weak Classifier terminates
Afterwards, the weight for increasing the small Weak Classifier of error in classification rate, makes it play biggish decisive action in final classification function,
And the weight of the big Weak Classifier of error in classification rate is reduced, so that it is played lesser decisive action in final classification function.
The tooth disease diagnosing method of the embodiment of the present invention detects mapping to be checked by AdaBoost detection algorithm trained in advance
As whether there is tooth regions, basis is provided for the positioning of subsequent odontopathy position.
As another for example, further including before the step 200 of the tooth disease diagnosing method of the embodiment of the present invention：
Step 300：Contrast is obtained to tooth regions image degree of comparing to be detected and brightness evaluation and deviates angle value
Deviate angle value with brightness, deviates when angle value is greater than second threshold pair when contrast deviates angle value and is greater than first threshold and/or brightness
Tooth regions image to be detected carries out enhancing processing.
For odontopathy image, the image at odontopathy position has part and tooth from the point of view of color and shape
Seam, gum, the root of the tongue or other normal positions for taking are similar, simultaneously because Image Acquisition quality problems, there is portion
It not is clearly that point contrast, which is not the odontopathy feature that very high odontopathy position is presented, it is therefore desirable to do and increase to image
Strength reason.The embodiment of the present invention enhances Retinex algorithm using retina, carries out to various types of image adaptive
Enhance to property, balance can be reached in terms of dynamic range, edge and color three.It is according to object that retina, which enhances Retinex algorithm,
The color of body determines by radioactivity of the object to light, and unrelated with intensity of illumination.Assuming that image S (x, y), can divide
Solution is reflection subject image at R (x, y) and L (x, y), R (x, y), and L (x, y) is incident light images, therefore, calculates each pixel
Between opposite relationship between light and dark, each pixel of image can be corrected, so that it is determined that the color of the pixel.
According to Retinex theory, the brightness that human eye perceives object depends on illumination and the body surface of environment
Reflection to irradiation light, mathematic(al) representation are：
I (x, y)=L (x, y) * R (x, y) (1)
Both sides take logarithm：Log [R (x, y)]=logpI (x, y)]-log [L (x, y)] (2)
Wherein I (x, y) represents the picture signal that observed or camera receives；L (x, y) represents the sub-irradiation of environment light
Amount；R (x, y) indicates to carry the reflecting component of the target object of image detail information.For image data I (x, y), calculate pair
The R (x, y) answered, then R (x, y) is considered that enhanced image, L (x, y) can be by carrying out Gauss to image data I (x, y)
It is fuzzy to obtain.Algorithm detailed process is as follows：
(1) it calculates original image and carries out the image L (x, y) after obscuring by specified scale；
(2) Gaussian Blur that each scale is carried out to original image, the image Li (x, y) after being obscured, wherein small tenon
I indicates scale parameter.
(3) to carrying out accumulation calculating under each scale
Log [R (x, y)]=Log [R (x, y)]+Weight (i) * (Log [Ii (x, y)]-Log [Li (x, y)])
(3)
Wherein Weight (i) indicates the corresponding weight of each scale, it is desirable that the sum of each scale weight is necessary for 1, classical
Value is equal weight.
(4) Log [R (x, y)] is quantified as the pixel value of 0 to 255 ranges, as final output.Amount
The mode of change is using the maximum value Max and minimum M in for calculating Log [R (x, y)], then to each value
Value, carries out equal interval quantizing, and formula is：
R (x, y)=(Value-Min)/(Max-Min) * (255-0) (4)
Brightness is the index of most visual evaluation dental imaging imaging.Based on experience value, select the desired value of mean intensity for
100,10 irrelevances of the grade as object brightness of each equal part between 0-100 and 100-255, setting weight is 0.4 i.e. the
One threshold value.For tooth, because of the influence of many factors such as the otherness of color, ambient lighting, simple brightness evaluation refers to
Number is insufficient as the completeness foundation of dental imaging reference, therefore introduces contrast evaluation simultaneously.Based on experience value, perfect condition
The desired value of lower contrast mean value is 25, therefore, by tooth contrast mean value from 0-25 etc. points of 10 grades, as target area
The irrelevance of contrast, weight are 0.15 i.e. second threshold.
The tooth disease diagnosing method of the embodiment of the present invention can be fed back evaluation result by the quality evaluation to image to be detected
Imaging control adjustment is carried out to camera, provides the shutter and gain imaging parameters of initialization deployment, later each frame upon start up
Imaging adjustment result can all carry out feedback and to camera carry out parameter setting, likewise, every time image obtained can also protect
The corresponding imaging parameters information of the frame image is stayed, the reference frame as subsequent imaging control.(1) when can't detect tooth at
As feature：First is that target is not present in coverage, second is that since ambient lighting problem makes picture imaging excessive lightness or darkness, this
When can be used center survey light mode, shooting camera imaging width be w, be highly h, the point centered on shooting center, obtain width
Degree is w/2, is highly the rectangle of h/2 as photometry region, calculates the brightness of image in the region, and establishing buffer length is 10
The regional luminance list of frame, zoning luminance mean value.(2) tooth detects imaging features：With the luminance mean value of tooth sequence and
Contrast mean value is as dental imaging feature.Tooth brightness is calculated, the tooth brightness list that buffer length is 10 frames is established, calculates
Tooth luminance mean value.Tooth histogram is counted, Threshold segmentation is done with maximum variance between clusters, calculates separately high portion's luminance mean value
Grayhigh and lower curtate luminance mean value graylow,
With formula:NContrast_LP=(grayhigh-graylow) * 100/256 (5)
Tooth contrast nContrast_LP is calculated, tooth contrast list is established, calculates tooth contrast list mean value.
(3) imaging parameters adjustment is after having determined imaging control adjustable strategies, and multi-parameter collaboration adjusts gain and shutter, so that mesh
Mark the imaging effect being optimal.Including brightness imaging control and contrast imaging control：
Brightness imaging control：When the brightness value for participating in calculating is lower than brightness lower limit, if fast gate value is not transferred to maximum,
It calculates expectation brightness and participates in the luminance difference calculated, luminance difference and shutter adjustment ratio mapping table (table 1) are searched, by adjustment
Ratio improves fast gate value, until maximum shutter；It is 1 increase gain according to adjustment amplitude, directly if shutter has been adjusted to the limit
To maximum gain；When participate in calculate brightness value be higher than the brightness upper limit when, if yield value be not transferred to it is minimum, according to adjustment walk
Long 1 reduces gain, until gain floor；If gain has been adjusted to lower limit, calculates expectation brightness and participates in the luminance difference calculated,
It searches luminance difference and shutter adjusts ratio mapping table, fast gate value is reduced in adjustment ratio, until fast gate value lower limit.
Table 1：Luminance difference and shutter adjust ratio mapping table
Contrast imaging control module：When the contrast value for participating in calculating is lower than contrast lower limit, if fast gate value does not have
It is transferred to maximum, calculate expectation contrast and participates in the contrast difference calculated, contrast difference is searched and shutter adjusts ratio
Mapping table (table 2) improves fast gate value in adjustment ratio, until maximum shutter；If shutter has been adjusted to the limit, according to adjustment
Amplitude is 1 increase gain, until maximum gain；When the brightness value for participating in calculating is higher than the brightness upper limit, if yield value does not have
It is transferred to minimum, reduces gain according to adjusting step 1, until gain floor；If gain has been adjusted to lower limit, expectation contrast is calculated
With the contrast difference for participating in calculating, searches contrast difference and shutter adjusts ratio mapping table, reduce shutter in adjustment ratio
Value, until fast gate value lower limit；When control adjustment is imaged with reference target degree of comparing, as contrast is lower than low threshold
Value, brightness are higher than high threshold, dim；Contrast is lower than Low threshold, and brightness is lower than Low threshold, lightens；It is compared when with tooth
When degree imaging control adjustment, if contrast is lower than Low threshold, when brightness is higher than desired value, imaging does not adjust；Contrast
It is lightened when brightness is lower than desired value lower than Low threshold.
Table 2：Contrast difference and shutter adjust ratio mapping table
The tooth disease diagnosing method of the embodiment of the present invention is evaluated tooth regions image degree of comparing to be detected and brightness
Evaluation obtains contrast and deviates angle value and brightness deviation angle value, and when contrast deviates, angle value is greater than first threshold and/or brightness is inclined
Enhancing processing is carried out to tooth regions image to be detected when being greater than second threshold from angle value, to guarantee the matter of dental imaging
Amount.
As another for example, the odontopathy identification model of the tooth disease diagnosing method of the embodiment of the present invention be based on
MASK-RCNN convolutional neural networks classifier training obtains, including：
Step 201：It inputs multiple tooth regions sample images to MASK-RCNN convolutional neural networks classifier and obtains multiple
The odontopathy coarse positioning and classification results of tooth regions sample image；
Step 202：Multiple tooth regions sample images are filtered based on odontopathy coarse positioning and classification results；
Step 203：Color and Texture Matching are carried out to filtered tooth regions sample image and handle to obtain that treated
Odontopathy sample image；
Step 204：Odontopathy identification model is established according to odontopathy sample image.
The odontopathy identification model of the embodiment of the present invention is based on MASK-RCNN convolutional neural networks classifier training and obtains, first
It first passes through MASK-RCNN convolutional neural networks classifier and odontopathy coarse positioning and classification is carried out to multiple tooth regions sample images,
Screening is filtered to image by artificial or other methods later, face then is carried out to filtered tooth regions sample image
Color and Texture Matching handle to obtain treated odontopathy sample image, establish odontopathy identification model based on odontopathy sample image.
Method training odontopathy identification model of the tooth disease diagnosing method of the embodiment of the present invention by deep learning, model robust
Property it is strong, classification quick and precisely.
As another for example, the MASK-RCNN convolutional neural networks of the tooth disease diagnosing method of the embodiment of the present invention
Classifier includes upper layer network and lower layer's network, and upper layer network is used to extract the candidate odontopathy position side of tooth regions sample image
Boundary's frame, lower layer's network are used to extract feature from each odontopathy location boundary frame and carry out classification and boundary recurrence, upper layer network
For the Faster R-CNN network with mask branch, lower layer's network is ResNet network.
As shown in fig. 6, in order to realize the quickly Accurate Segmentation in accurate odontopathy target detection and odontopathy region, based on built
Vertical odontopathy sample database, the embodiment of the present invention have selected the essence of MASK-RCNN convolutional neural networks classifier progress odontopathy target
Really detection and segmentation.Faster R-CNN is each candidate target output class label and frame offset, and Mask R-CNN exists
The branch of a prediction segmentation mask on each area-of-interest is added on the basis of Faster R-CNN.
Faster R-CNN is made of two stages, and the first stage proposes candidate target bounding box, and second stage uses
RoIPool extracts feature from each candidate frame and carries out classification and boundary recurrence.Mask R-CNN is in Faster R-CNN
It is parallel each RoI output binary mask with prediction class and frame offset on two-stage.On RoI after each sampling
Multitask loss function is defined as：L=Lcls+Lbox+Lmask
Wherein Lcls is Classification Loss, and Lbox is detection block loss, and Lmask is that average binary system intersects entropy loss.It is right
The definition of Lmask allows network to be that each class independently predicts binary mask, by dedicated classification branch prediction for selecting
The class label of output masking.Mask branch has the output of Km2 dimension, i.e. K classification to each RoI, and resolution ratio is the two of m*m
Value mask.Therefore single pixel sigmoid two-value cross entropy is used, two-value cross entropy can make the mask of every one kind not competing mutually
It strives, rather than compares with the mask of other classes.
In Faster R-CNN, small characteristic pattern is extracted from each RoI using RoIPool, RoIPool is first by floating number
The RoI of expression, which is zoomed to, finally summarizes each piece of covering then by the RoI piecemeal after scaling with the matched granularity of characteristic pattern
The characteristic value in region.Such calculating makes RoI and the feature of extraction misplace.Although this may not influence to classify, because of classification
There is certain robustness to transformation by a small margin, but it has very big negative effect to the accurate mask of prediction pixel grade.
Mask R-CNN proposes the RoIAlign layers of dislocation to remove RoIPool, by the feature of extraction and input accurate alignment.?
The exact value that bilinear interpolation calculates each position is used in RoIAlign, and result is summarized (using maximum or average pond
Change), to carry out the alignment of pixel to pixel pixel-to-pixel.
For the classification and Detection and segmentation of a variety of odontopathy illness images, it is as follows that we construct MASK-RCNN network：For with
In lower layer's convolutional network of the feature extraction in whole image, we use depth for 50 layers of ResNet, in MASK-RCNN
In from the final convolutional layer of fourth stage extract feature.For upper layer network, the Faster proposed in ResNet and FPN is extended
The upper layer network of R-CNN is added to a mask branch respectively.
As another for example, the step 203 of the tooth disease diagnosing method of the embodiment of the present invention includes：
Step 2031：Color characteristic matching is carried out to filtered tooth regions sample image using histogram method；
Step 2032：Textural characteristics matching is carried out to filtered tooth regions sample image using Tamura algorithm；
Step 2033：Odontopathy position is carried out to tooth regions sample image and odontopathy type marks to obtain odontopathy sample graph
Picture.
The method that the color-match of the embodiment of the present invention uses Histogram Matching, calculation formula are as follows：
H1And H2The respectively histogram of template image and overlapping region image calculates two histograms
Bhattacharyya distance is as follows：
The Texture Matching of the embodiment of the present invention carries out textural characteristics matching using Tamura algorithm.Tamura
Six components of textural characteristics correspond to six attribute of textural characteristics on Psychological Angle, are roughness respectively
(coarseness), contrast (contrast), direction degree (directionality), line picture degree (linelikeness), rule
Whole degree (regularity) and rough degree (roughness).The embodiment of the present invention mainly utilizes roughness, contrast and direction degree
Calculate the similarity of odontopathy template texture and target image to be detected.
(1) roughness：
The calculating of roughness can be divided into following steps progress.Firstly, calculating size in image is 2k × 2k picture
The average intensity value of pixel, that is, have in the active window of element
Wherein k=0,1 ..., 5 and g (i, j) is pixel intensity value positioned at (i, j).Then, for each pixel, respectively
The mean intensity calculated between the window that it is not overlapped in the horizontal and vertical directions is poor.
Wherein for each pixel, the k value that E value can be made to reach maximum (no matter direction) is used to that optimum size Sbest is arranged
(x, y)=2k.Finally, roughness can be obtained by calculating the average value of Sbest in entire image, it is expressed as：
(2) contrast
Contrast is obtained by the statistics to pixel intensity distribution situation, that is, passes through α4=μ4/σ4Come what is defined,
Middle μ4It is four squares and σ2It is variance.Contrast is measured by following formula:
The value gives the global measurement of contrast in whole image or region.
(3) direction degree
The calculating of direction degree needs to calculate the gradient vector at each pixel first.The vector field homoemorphism and side
To being respectively defined as：
| Δ G |=(| ΔH|+|ΔV|)/2
θ=tan-1(ΔV/ΔH)+π/2 (12)
Wherein .H and .V be respectively by image convolution following two 3x3 operator it is resulting both horizontally and vertically on
Variable quantity.
After the gradient vector of all pixels is all computed, a histogram HD is configured to expression θ value.This is straight
Side's figure carries out discretization to the codomain range of θ first, has then counted corresponding in each bin | .G | greater than given threshold value
Pixel quantity.This histogram can show peak value for the image with obvious directionality, for the image without obvious direction
Then show relatively flat.Finally, the directionality of image totality can be obtained by calculating the acuity of peak value in histogram,
It is expressed as follows：
P in above formula represents the peak value in histogram, npFor peak value all in histogram.For some peak value p, WpGeneration
All bin that the table peak value is included, and φpIt is the bin with peak.
On the other hand, as illustrated in figures 4-5, the embodiment of the invention also provides a kind of the tooth disease diagnosing equipment, including：
Module 10 is obtained, for obtaining tooth regions image to be detected；
Identification module 20 carries out odontopathy identification for tooth regions image to be detected to be input to odontopathy identification model,
And odontopathy recognition result is exported, odontopathy recognition result includes odontopathy position and odontopathy type.
As one for example, the acquisition module 10 of the tooth disease diagnosing equipment of the embodiment of the present invention includes：
Acquisition unit 11, for acquiring image to be detected using intelligent image acquisition device；
Detection unit 12, for detecting image to be detected with the presence or absence of tooth regions based on AdaBoost detection algorithm, if
It is then to determine that image to be detected is tooth regions image to be detected.
The tooth disease diagnosing equipment of the embodiment of the present invention obtains tooth regions image to be detected by obtaining module, and its is defeated
Enter to detection module, odontopathy is carried out by odontopathy identification model and identifies to obtain odontopathy position and odontopathy type, intelligence is convenient real
The diagnosis of existing odontopathy.The tooth disease diagnosing equipment of the embodiment of the present invention differentiates the diagnosis for needing protracted experience to accumulate in conventional dental
It is converted into the automatic recognition classification of machine learning, effectively improves the efficiency of auxiliary diagnosis, realizes the automation of the tooth disease diagnosing.
As another for example, the tooth disease diagnosing equipment of the embodiment of the present invention further includes：
Quality assessment module 30, for being compared to tooth regions image degree of comparing to be detected and brightness evaluation
Degree deviates angle value and brightness and deviates angle value, and when contrast deviates, angle value is greater than first threshold and/or brightness deviates angle value and is greater than the
Enhancing processing is carried out to tooth regions image to be detected when two threshold values.
As another for example, the tooth disease diagnosing equipment of the embodiment of the present invention further includes odontopathy identification model training mould
Block 40, including：
Odontopathy coarse positioning and taxon 41, for inputting multiple tooth regions sample images to MASK-RCNN convolution mind
The odontopathy coarse positioning and classification results of multiple tooth regions sample images are obtained through network classifier；
Filter element 42, for filtering multiple tooth regions sample images based on odontopathy coarse positioning and classification results；
Color and Texture Matching unit 43, for carrying out color and Texture Matching to filtered tooth regions sample image
Processing obtains that treated odontopathy sample image；
Model foundation unit 44, for establishing odontopathy identification model according to odontopathy sample image.
In another aspect, as illustrated in figures 7 to 13, the embodiment of the invention also provides a kind of intelligent image acquisition device, including it is upper
The acquisition portion 210 at end and the hand-held part 110 of lower end are connecting rod 120, the external setting in acquisition portion between hand-held part and acquisition portion
There is waterproof cover 130, internal that image capture module 50 is arranged, hand-held part includes being set to positive first button 111 and setting
The second button 112 in side.
As one for example, the image capture module 50 of the embodiment of the present invention includes：Main processor unit 51, with
The image acquisition units 52 of main processor modules connection, LED light filling unit 53, gyro sensors unit 54, communication unit 55, electricity
Source control unit 56 and storage unit 57, main processor unit 51 include that arm processor and video encoding processor (do not show
Out), for realizing the control of Video coding processing, image procossing, Interface Controller and light filling, image acquisition units 52 include microspur
Camera lens and imaging sensor (not shown), LED light filling unit 53 include blue LED lamp and white LED lamp, gyro sensors unit
54 for measuring rotation or defection signal in image acquisition process, and communication unit 55 is WiFi communication, Power Management Unit 56
Including battery subelement and wireless charging subelement (not shown).
As one for example, being waterproof inside the waterproof cover 130 of the intelligent image acquisition device of the embodiment of the present invention
Inner casing 131,130 lower end of waterproof cover are equipped with card slot 132, the fixed clamping of card slot 132 and clamping end 126, waterproof cover 130 and clamping end
126 external setting waterproof membrane 140 and bulge loop 141, clamping end 126 are set to one end of elastic strip 125, elastic strip 125 it is another
One end is connected and fixed with connecting rod 120, and connecting rod 120 is equipped with holding cylinder 127, holding cylinder in the one end connecting with elastic strip 125
It is connected between 127 and connecting rod 120 by stage body 122, stage body 122 is adjacent to 130 end face of waterproof cover, inside connecting rod 120 also
Equipped with hollow connection inner cylinder 121；
Holding cylinder 127 is equipped with the first through slot 123 and the second through slot 124, is equipped with stop collar 150 in holding cylinder 127,
Outer wall is equipped with sealing ring 410, and sealing ring 410 and 130 inner wall of waterproof cover are adjacent to sealing, clamping cylinder are equipped with inside holding cylinder 127
310, clamping cylinder outside is equipped with the first card for being each passed through the first through slot 123, the second through slot 124 and 130 inner wall clamping of waterproof cover
Tight portion 311, the second card-tight part 312, the first through slot 123, the second through slot 124 are separately positioned on about 410 two sides of sealing ring, and first
Through slot 123 and the second through slot 124 are uniformly arranged in 127 circumferential direction of holding cylinder.
In use, limiting clamping wound packages by stop collar enters position, then distinguished by first the second card-tight part of card-tight part
Guarantee the assembly intensity of waterproof cover and connecting rod with the clamping of waterproof cover inner wall.
The conducting wire 220 of the image capture module of the embodiment of the present invention is connected to power supply with power supply circuit, using fold line (and electricity
It is similar to talk about line), it can elongate, stretch when use, conducting wire can be prevented to be torn in this way.
Waterproof membrane is equipped with outside the card slot of the embodiment of the present invention, waterproof membrane upper and lower ends are respectively and near card slot upper and lower ends
It is sealing assembly, fixed, and waterproof membrane is made of highly elastic material, such as silica gel, rubber, when needing to take out waterproof cover, it is only necessary to
Clamping end is pressed by waterproof membrane, directly pulls out waterproof cover after so that clamping end is released card slot.Waterproof membrane with clamping end
Corresponding position is equipped with bulge loop, and whens use can further press clamping end by bulge loop, presses so that increasing to clamping end
Distance is pressed, taking-up waterproof cover is facilitated.
The elastic strip of the embodiment of the present invention is made of elastic material, can be flexible plastic sheet, in use, passing through its bullet
Property is clamped on clamping end in card slot.
The above is a preferred embodiment of the present invention, it is noted that for those skilled in the art
For, without departing from the principles of the present invention, it can also make several improvements and retouch, these improvements and modifications
It should be regarded as protection scope of the present invention.
Referring to Fig. 7-Figure 13, a kind of intelligent image acquisition device (the tooth disease diagnosing equipment that can be Fig. 4-Fig. 5), including hand
Part 110, connecting rod 120 are held, the portion of the handle 110 is equipped with the first button 111 and the second button 112, the company
120 end of extension bar, which is equipped with, obtains module 210；
The acquisition module 210, including camera, micro-lens, imaging sensor, LED light, the camera are taken the photograph
As end is externally provided with the micro-lens for focusing, making camera to shoot very subtle object, the imaging sensor is defeated
Enter end and connect and carry out data transmission with camera output end, the miniature place of the imaging sensor output end and primary processor
Reason device input terminal connects and carries out data transmission；
The LED light is for illuminating, in use, obtaining image by the light that LED light issues for camera provides light,
And LED light can issue the light of different colours according to the control of primary processor, to be adapted to shoot different images；
The primary processor is for receiving and dispatching, parsing control instruction, including power supply circuit and microprocessor (miniature CPU)；
The power supply circuit be used for for camera, micro-lens, imaging sensor, LED light, gyroscope, memory, wireless module,
Microprocessor, LED light power supply, are mainly converted into the standard that can be used by each electrical equipment for voltage or electric current
Voltage or electric current；
Frequency modulator or FM circuit are additionally provided on the power supply circuit, the frequency modulator is for adjusting to supply current
Frequency；
The primary processor signal input part also respectively with gyroscope, memory, wireless module, key, LED indication
Lamp, power management module output end connect and carry out data transmission；
The gyroscope is used to detect the angle of camera rotation, in order to which later period primary processor is to the angle of shooting image
Degree is corrected；
The memory for storing data, can be flash memory, RAM card, SD card etc.；
The wireless module is carried out with external equipment without line number for being wirelessly connected with external equipment to realize
According to transmission, WIFI module, 4G module, bluetooth module, ZigBee module etc. can be；
The key is used to export control instruction, such as shooting photo, adjustment focal length to primary processor, including first presses
Button and the second button；
The LED light is used to indicate master controller and receives the states such as preset instructions, such as passes through different colours, difference
Flicker frequency come indicate not enough power supply, in charging, in use, different faults etc.；
The power management module is powered for detecting battery capacity, while to power supply circuit.The power supply circuit,
Power management module, microprocessor, image processor etc. can refer in existing radio scan rifle, similar functional component.
Further, the acquisition module utilizes miniature flexible encapsulation technology, is integrated using FPC as sill, above
Cmos image sensor, LED light (white light and 420nm blue light), micro-lens, cooperation software algorithm extend to areas imaging
0.8CM-7CM.LED light uses white light LEDs and blue-ray LED, and White LED is opened when generally taking pictures, and is such as used for the plaque of tooth
Detection can control unlatching blue-ray LED, detected automatically using the plaque that can achieve after algorithm process.Miniature processing
Device can be ARM9 processor, and certainly, the microprocessor can mutually transmit data with video encoding processor, and video is compiled
H.264, code processor is encoded for completing video；
The functions such as Interface Controller, the control of LED light light filling, image procossing, can be communicated by wireless module and mobile phone terminal.
When shooting dental imaging, the image of left and right sides acquisition can be flipped, and gyroscope can do the movement of rotation, deflection
Measurement well, therefore we have used gyro sensor when hardware design, so that can feel in shooting process
Know overturning variable signal, software is recycled to correct automatically by picture position.
Further, the power management module is connect into electric end with the one of current output terminal of wireless charging module, nothing
Another current output terminal of line charging module connect conduction with battery current output terminal, and the wireless charging module can cooperate real with external equipment
The wireless charging technology of existing mobile phone can be directly used in existing wireless charging, technology；
When needing electricity consumption, if wireless charging module is charging, by wireless charging module directly to electrical equipment
Power supply；If wireless charging module does not charge, by the electricity in battery be led to power management module carry out using；
The battery is that this design of lithium battery can effectively charge to battery by wireless charger, can be with
Without charge port is arranged, to improve waterproof and dustproof effect.
Referring to Figure 10-Figure 12, installation, the later period maintenance of module are obtained for convenience, it can be using such as flowering structure：
The acquisition module 210 is mounted in waterproof cover 130, is waterproof inner shell 131 inside the waterproof cover 130,
And card slot 132 is additionally provided on the waterproof cover 130, and the card slot 132 and 126 clamping of clamping end, the clamping end
126 are arranged on 125 one end of elastic strip, and 125 other end of elastic strip is connected and fixed with connecting rod 120, the connection
Bar 120 is equipped with holding cylinder 127 on being provided with 125 one end of elastic strip, passes through between the holding cylinder 127 and connecting rod 120
Stage body 122 connects, and the stage body 122 is adjacent to waterproof cover end face；
The first through slot 123 and the second through slot 124 are additionally provided in the holding cylinder 127, inside the connecting rod 127
Equipped with hollow connection inner cylinder 121, and stop collar 150 is additionally provided in holding cylinder, the holding drum outer wall is equipped with sealing ring
410, the sealing ring 410 and waterproof cover inner wall are adjacent to sealing；
Clamping cylinder 310 is installed inside the holding cylinder, is equipped with outside the clamping cylinder and is each passed through the first through slot
123, the first card-tight part 311, the second card-tight part 312 of the second through slot 124 and the clamping of waterproof cover inner wall；First through slot
123, the second through slot 124 is separately positioned on sealing ring two sides up and down, and first through slot 123, the second through slot 124 difference are at least
There are two, and be uniformly arranged in holding cylinder circumferential direction respectively；
In use, limiting clamping wound packages by stop collar enters position, then pass through the first card-tight part 311, the second card-tight part
312 guarantee the assembly intensity of waterproof cover and connecting rod with the clamping of waterproof cover inner wall respectively；
The acquisition module is connected to power supply with power supply circuit by conducting wire 220, is equipped with waterproof outside the card slot 132
Film 140,140 upper and lower ends of waterproof membrane nearby seal assembly, fixation with 132 upper and lower ends of card slot respectively, and described
Waterproof membrane is made of highly elastic material, such as silica gel, rubber.When needing to take out waterproof cover, it is only necessary to be pressed by waterproof membrane 140
Clamping end directly pulls out waterproof cover after so that clamping end is released card slot 132.
Further, described 220 fold line (similar with telephone wire) is used, it can elongate, stretch when use, in this way
Conducting wire can be prevented to be torn.
Further, waterproof membrane 140 is being equipped with bulge loop 141 with 126 corresponding position of clamping end, and whens use can pass through bulge loop
141 further press clamping end, so that increasing the pressing distance to clamping end, facilitate taking-up waterproof cover.
Further, the elastic strip is made of elastic material, can be flexible plastic sheet, in use, passing through it
Elasticity is clamped on clamping end in card slot.
Place is not described in detail for the utility model, is the well-known technique of those skilled in the art.
The preferred embodiments of the present invention have been described in detail above.It should be appreciated that the ordinary skill people of this field
Member according to the present utility model can conceive without creative work makes many modifications and variations.Therefore, all this technology necks
Technical staff passes through logic analysis, reasoning or limited reality according to the design of the utility model on the basis of existing technology in domain
Available technical solution is tested, it all should be within the scope of protection determined by the claims.
Claims (8)
1. a kind of intelligent image acquisition device, it is characterized in that：Including, portion of the handle, connecting rod, the portion of the handle is equipped with
First button and the second button, the connection boom end are equipped with acquisition module, obtain module for obtaining tooth to be detected
Tooth area image；
The acquisition module, including camera, micro-lens, imaging sensor, LED light, the camera image outside end
Equipped with for focusing, making camera to shoot the micro-lens of very subtle object, the imaging sensor input terminal with
Camera output end connects and carries out data transmission, and the microprocessor of the imaging sensor output end and primary processor is defeated
Enter end to connect and carry out data transmission；
The primary processor controls the current switching and size, frequency of each electrical equipment for receiving and dispatching, parsing control instruction；
The primary processor signal input part also respectively with gyroscope, memory, wireless module, key, LED light, electricity
Source control module output end connects and carries out data transmission；
The gyroscope be used for detect camera rotation angle, in order to later period primary processor to shooting image angle into
Row correction；
The memory is for storing data；The wireless module with external equipment for being wirelessly connected, thus real
Now wireless data transmission is carried out with external equipment；
The key is used to export control instruction, including the first button and the second button to primary processor；
The LED light is used to indicate master controller and receives preset instructions state；The power management module is for examining
Battery capacity is surveyed, while being powered to power supply circuit.
2. intelligent image acquisition device as described in claim 1, it is characterized in that：The primary processor, including power supply circuit
With microprocessor；The power supply circuit is used to be camera, micro-lens, imaging sensor, LED light, gyroscope, storage
Device, wireless module, microprocessor, LED light power supply.
3. intelligent image acquisition device as described in claim 1, it is characterized in that：Frequency modulator is additionally provided on the power supply circuit
Or FM circuit, the frequency modulator are used to adjust the frequency to supply current or voltage.
4. intelligent image acquisition device as described in claim 1, it is characterized in that：The acquisition module is sealed using miniature flexible
The encapsulation of dress technology, using FPC as sill, is integrated with cmos image sensor, LED light, micro-lens above.
5. intelligent image acquisition device as described in claim 1, it is characterized in that：The power management module is into electric end and nothing
The one of current output terminal connection of line charging module, another current output terminal of wireless charging module connect conduction with battery current output terminal, described
Wireless charging module can with external equipment cooperate realize wireless charging.
6. intelligent image acquisition device as described in claim 1, it is characterized in that：The acquisition module is mounted on waterproof cover
It is interior, it is waterproof inner shell inside the waterproof cover, and card slot is additionally provided on the waterproof cover, the card slot and clamping end card
Tightly, the clamping end is arranged on elastic strip one end, and the elastic strip other end is connected and fixed with connecting rod, the company
Extension bar is equipped with holding cylinder on being provided with elastic strip one end, is connected between the holding cylinder and connecting rod by stage body, described
Stage body be adjacent to waterproof cover end face；
It is additionally provided with the first through slot and the second through slot in the holding cylinder, is equipped in hollow connection inside the connecting rod
Cylinder, and stop collar is additionally provided in holding cylinder, the holding drum outer wall is equipped with sealing ring, the sealing ring and waterproof cover inner wall
It is adjacent to sealing；
Clamping cylinder is installed inside the holding cylinder, is equipped with outside the clamping cylinder and is each passed through the first through slot, second logical
The first card-tight part, the second card-tight part of slot and the clamping of waterproof cover inner wall；First through slot, the second through slot are separately positioned on close
Seal up and down two sides, first through slot, the second through slot respectively at least there are two, and be uniformly arranged on respectively holding cylinder circumferential direction
On.
7. intelligent image acquisition device as claimed in claim 6, it is characterized in that：Waterproof membrane with clamping end corresponding position be equipped with it is convex
Ring.
8. intelligent image acquisition device as claimed in claim 6, it is characterized in that：The elastic strip uses elastic material system
At.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201820630508.3U CN208172859U (en) | 2018-04-28 | 2018-04-28 | A kind of intelligent image acquisition device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201820630508.3U CN208172859U (en) | 2018-04-28 | 2018-04-28 | A kind of intelligent image acquisition device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN208172859U true CN208172859U (en) | 2018-11-30 |
Family
ID=64368589
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201820630508.3U Expired - Fee Related CN208172859U (en) | 2018-04-28 | 2018-04-28 | A kind of intelligent image acquisition device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN208172859U (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109758756A (en) * | 2019-02-28 | 2019-05-17 | 国家体育总局体育科学研究所 | Gymnastics video analysis method and system based on 3D camera |
| CN109816669A (en) * | 2019-01-30 | 2019-05-28 | 云南电网有限责任公司电力科学研究院 | A kind of improvement Mask R-CNN image instance dividing method identifying power equipments defect |
| US10937108B1 (en) | 2020-01-17 | 2021-03-02 | Pearl Inc. | Computer vision-based claims processing |
| WO2021046241A1 (en) * | 2019-09-05 | 2021-03-11 | Pearl Inc. | Automated medical image annotation and analysis |
| US10984529B2 (en) | 2019-09-05 | 2021-04-20 | Pearl Inc. | Systems and methods for automated medical image annotation |
| CN113607732A (en) * | 2021-08-09 | 2021-11-05 | 深圳市航科量子科技有限公司 | Agricultural product quality monitoring sampling processing system |
| US11389131B2 (en) | 2018-06-27 | 2022-07-19 | Denti.Ai Technology Inc. | Systems and methods for processing of dental images |
| US11676701B2 (en) | 2019-09-05 | 2023-06-13 | Pearl Inc. | Systems and methods for automated medical image analysis |
| US11776677B2 (en) | 2021-01-06 | 2023-10-03 | Pearl Inc. | Computer vision-based analysis of provider data |
-
2018
- 2018-04-28 CN CN201820630508.3U patent/CN208172859U/en not_active Expired - Fee Related
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11389131B2 (en) | 2018-06-27 | 2022-07-19 | Denti.Ai Technology Inc. | Systems and methods for processing of dental images |
| CN109816669A (en) * | 2019-01-30 | 2019-05-28 | 云南电网有限责任公司电力科学研究院 | A kind of improvement Mask R-CNN image instance dividing method identifying power equipments defect |
| CN109758756B (en) * | 2019-02-28 | 2021-03-23 | 国家体育总局体育科学研究所 | Gymnastics video analysis method and system based on 3D camera |
| CN109758756A (en) * | 2019-02-28 | 2019-05-17 | 国家体育总局体育科学研究所 | Gymnastics video analysis method and system based on 3D camera |
| WO2021046241A1 (en) * | 2019-09-05 | 2021-03-11 | Pearl Inc. | Automated medical image annotation and analysis |
| US10984529B2 (en) | 2019-09-05 | 2021-04-20 | Pearl Inc. | Systems and methods for automated medical image annotation |
| US11676701B2 (en) | 2019-09-05 | 2023-06-13 | Pearl Inc. | Systems and methods for automated medical image analysis |
| US11055789B1 (en) | 2020-01-17 | 2021-07-06 | Pearl Inc. | Systems and methods for insurance fraud detection |
| US11328365B2 (en) | 2020-01-17 | 2022-05-10 | Pearl Inc. | Systems and methods for insurance fraud detection |
| US10937108B1 (en) | 2020-01-17 | 2021-03-02 | Pearl Inc. | Computer vision-based claims processing |
| US11587184B2 (en) | 2020-01-17 | 2023-02-21 | Pearl Inc. | Computer vision-based claims processing |
| US11776677B2 (en) | 2021-01-06 | 2023-10-03 | Pearl Inc. | Computer vision-based analysis of provider data |
| CN113607732A (en) * | 2021-08-09 | 2021-11-05 | 深圳市航科量子科技有限公司 | Agricultural product quality monitoring sampling processing system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN208172859U (en) | A kind of intelligent image acquisition device | |
| CN108389207A (en) | A kind of the tooth disease diagnosing method, diagnostic device and intelligent image harvester | |
| CN110490041B (en) | Face image acquisition device and method | |
| US11039119B2 (en) | Photography system with depth and position detection | |
| CN106874871B (en) | Living body face double-camera identification method and identification device | |
| CN108197546B (en) | Illumination processing method and device in face recognition, computer equipment and storage medium | |
| CN110168562B (en) | Depth-based control method, depth-based control device and electronic device | |
| US7953261B2 (en) | Image processing apparatus and image processing method | |
| CN103764013A (en) | Automatic exposure control device, control device, endoscope device and automatic exposure control method | |
| CN107945107A (en) | Image processing method, device, computer-readable recording medium and electronic equipment | |
| CN107886484A (en) | U.S. face method, apparatus, computer-readable recording medium and electronic equipment | |
| CN104811684B (en) | A kind of three-dimensional U.S. face method and device of image | |
| CN104586364A (en) | Skin detection system and method | |
| CN111563887A (en) | Intelligent analysis method and device for oral cavity image | |
| CN207491128U (en) | A kind of RGB+IR image capture devices | |
| CN107800965B (en) | Image processing method, device, computer readable storage medium and computer equipment | |
| JP2004318204A (en) | Image processing device, image processing method, and photographing device | |
| CN101872106A (en) | Intelligent infrared camera and intelligent infrared light intensity adjustment method thereof | |
| CN102697446A (en) | Image processing device and image processing method | |
| WO2010054092A1 (en) | Video infrared retinal image scanner | |
| CN107749053A (en) | A kind of binocular image collection and pretreatment unit and method for vision prosthesis | |
| CN108324247B (en) | Method and system for evaluating skin wrinkles at specified positions | |
| CN106859595A (en) | Tongue picture acquisition methods, device and system | |
| CN108093170B (en) | User photographing method, device and equipment | |
| CN106934349B (en) | Dual-camera imaging and iris acquisition and recognition integrated equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20181130 Termination date: 20190428 |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| RR01 | Reinstatement of patent right |
Former decision: termination of patent right due to unpaid annual fee Former decision publication date: 20200414 |
|
| RR01 | Reinstatement of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20181130 Termination date: 20200428 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |