CN111091910B - Intelligent evaluation system based on painting clock test - Google Patents
Intelligent evaluation system based on painting clock test Download PDFInfo
- Publication number
- CN111091910B CN111091910B CN201911300342.4A CN201911300342A CN111091910B CN 111091910 B CN111091910 B CN 111091910B CN 201911300342 A CN201911300342 A CN 201911300342A CN 111091910 B CN111091910 B CN 111091910B
- Authority
- CN
- China
- Prior art keywords
- detection module
- area
- included angle
- clock
- unit
- 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.)
- Active
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 32
- 238000011156 evaluation Methods 0.000 title claims abstract description 24
- 238000010422 painting Methods 0.000 title claims description 10
- 238000001514 detection method Methods 0.000 claims abstract description 113
- 239000013598 vector Substances 0.000 claims description 58
- 238000004364 calculation method Methods 0.000 claims description 29
- 238000000034 method Methods 0.000 claims description 28
- 230000006870 function Effects 0.000 claims description 9
- 239000003973 paint Substances 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000013527 convolutional neural network Methods 0.000 claims description 5
- 230000035945 sensitivity Effects 0.000 claims description 5
- 108010001267 Protein Subunits Proteins 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 2
- 238000012549 training Methods 0.000 description 6
- 208000024827 Alzheimer disease Diseases 0.000 description 5
- 206010039966 Senile dementia Diseases 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000005259 measurement Methods 0.000 description 4
- 206010012289 Dementia Diseases 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 208000010877 cognitive disease Diseases 0.000 description 2
- 230000003920 cognitive function Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 208000028698 Cognitive impairment Diseases 0.000 description 1
- 206010020772 Hypertension Diseases 0.000 description 1
- 208000036626 Mental retardation Diseases 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000001631 hypertensive effect Effects 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
- G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Public Health (AREA)
- Epidemiology (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Geometry (AREA)
- Pathology (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The application relates to the field of artificial intelligence, in particular to an intelligent evaluation system based on a picture clock test, which aims to solve the problem that scoring results given by different doctors have gaps. The system comprises a roundness detection module, an integrity detection module, a correctness detection module and a scoring module. The roundness detection module is configured to detect a clock outline in an image to be evaluated, draw a minimum circumcircle of the clock outline, and calculate the ratio of the area surrounded by the outline to the area of the minimum circumcircle; the integrity detection module is configured to detect whether numbers, hour hands and minute hands exist in the image to be evaluated, and acquire corresponding coordinate values; the correctness detection module is configured to detect whether the digital position, the hour hand and the minute hand are correctly pointed according to the coordinate values respectively; the scoring module is configured to score according to the detection result. The application solves the problem that the patient is inconvenient to go to the hospital to participate in the test, and effectively avoids the problem that the scoring results are different due to different doctors.
Description
Technical Field
The application relates to the field of artificial intelligence, in particular to an intelligent evaluation system based on a painting clock test.
Background
With the advent of aging society, dementia, mental retardation, and other disorders associated with senile cognitive impairment have begun to draw widespread attention in various areas of society. However, since the early symptoms of senile dementia are not obvious and are easily ignored, most of senile dementia patients reach middle and late stages when finding, and the best therapeutic intervention opportunity is missed. Thus studies indicate that potentially at risk populations, including hypertensive patients, should be regularly subjected to a clock test for cognitive dysfunction.
The painting clock test (Clock Drawing Test, CDT) is a simple and feasible screening test for the dyszhision, which has high accuracy and small cultural correlation, can comprehensively reflect the cognitive function, and can be used as an early screening tool for detecting the senile dementia. The device can detect the reconstruction capability of the vision memory graph of the old, the planning performance of actions, the executive function, the anti-interference capability and other performances. The related data show that the accuracy of the picture clock test for senile dementia is as high as 80% -90%.
The paint clock test has a plurality of scoring forms, but the essence is not limited in the following aspects: 1. drawing a locked circle (dial); 2. drawing scales uniformly distributed in the circle; 3. marking numbers corresponding to the scales; 4. the hour and minute hands are drawn for the time specified by the tester. The resulting image of the paint clock test is ultimately scored by the clinician. However, the above-described approaches are limited by insufficient medical resources and inconvenience in patient's assessment to the hospital, and there are fluctuations and gaps in scoring results given by different doctors.
Disclosure of Invention
In order to solve the problems in the prior art, the application provides an intelligent evaluation system based on a picture clock test, which solves the problem that a patient cannot conveniently go to a hospital to participate in the test and effectively avoids the problem that scoring results are different due to different doctors.
The application provides an intelligent evaluation system based on a painting clock test, which comprises: the system comprises a roundness detection module, an integrity detection module, a correctness detection module and a scoring module;
the roundness detection module is configured to: detecting a clock outline in an image to be evaluated, drawing a minimum circumcircle of the clock outline, and calculating the ratio of the area surrounded by the clock outline to the area of the minimum circumcircle;
the integrity detection module is configured to: detecting whether numbers, hour hands and minute hands exist in the image to be evaluated, and acquiring corresponding coordinate values;
the correctness detection module is configured to: according to the coordinate values, respectively detecting whether the digital position is correct or not and whether the directions of the hour hand and the minute hand are correct or not;
the scoring module is configured to: and scoring the clocks drawn in the image to be evaluated according to the detection results of the roundness detection module, the integrity detection module and the correctness detection module.
Preferably, the roundness detection module includes: the device comprises a preprocessing unit, a contour detection unit, a circumscribing circle drawing unit and an area rate calculation unit;
the preprocessing unit is configured to: converting the image to be evaluated into a gray scale;
the contour detection unit is configured to: detecting the timepiece contour in the gray scale map;
the circumscribed circle drawing unit is configured to: drawing a minimum circumcircle of the clock outline;
the area ratio calculation unit is configured to: and respectively calculating the area surrounded by the clock outline and the area of the minimum circumscribing circle, and obtaining the ratio of the two areas.
Preferably, the area ratio calculating unit includes: a first area calculation subunit, a second area calculation subunit, and a ratio calculation subunit;
the first area calculation subunit is configured to: calculating the number of pixels with the pixel value of 255 in the clock outline, and further calculating the area surrounded by the clock outline;
the second area calculation subunit is configured to: calculating the area of the minimum circumscribing circle;
the ratio calculation subunit is configured to: calculating the ratio of the area enclosed by the clock outline and the area of the minimum circumscribing circle.
Preferably, the integrity detection module comprises: convolutional neural networks based on masked regions.
Preferably, the correctness detection module includes: a digital position detection unit, an hour hand and a minute hand pointing to the detection unit;
the digital position detection unit is configured to: respectively detecting whether the positions of 12 numbers in the image to be evaluated are accurate or not;
the hour hand and minute hand pointing detection unit is configured to: and respectively detecting whether the directions of the hour hand and the minute hand in the image to be evaluated are accurate.
Preferably, the digital position detection unit includes: the device comprises a vector drawing subunit, an included angle calculating subunit and a digital judging subunit;
the vector painting subunit is configured to: respectively drawing vectors x pointing to 12 numbers by taking the center of the minimum circumscribing circle as a starting point 0 、x 1 、x 2 、…、x 11 ；
The included angle calculation subunit is configured to: respectively calculating vectors x 0 、x 1 、x 2 、…、x 11 Vector x 0 Obtain the included angle value A 0 、A 1 、A 2 、…、A 11 ；
The digital judgment subunit is configured to: according to the included angle value A 0 、A 1 、A 2 、…、A 6 Judging A in turn 1 、A 2 、…、A 6 Whether each included angle is larger than the previous oneThe absolute value of the difference value between the included angle and the previous included angle meets the preset included angle range; according to the included angle value A 7 、A 8 、…、A 11 、A 0 Judging A in turn 7 、A 8 、…、A 11 Whether each included angle is larger than the latter included angle or not and the absolute value of the difference value between the included angle and the latter included angle meets the preset included angle range.
Preferably, the hour hand pointing direction detecting unit includes: a pointer region sub-unit, a pointer vector drawing sub-unit and a pointer judging sub-unit;
the pointer region molecular unit is configured to: distinguishing an hour hand from a minute hand according to the length relation of the two pointers in the image to be evaluated;
the pointer vector drawing subunit is configured to: respectively drawing a vector of an hour hand and a vector of a minute hand in the image to be evaluated and a standard hour hand vector and a standard minute hand vector pointing to a target time point;
the pointer judgment subunit is configured to: judging whether the included angle between the drawn hour hand vector and the standard hour hand vector meets a preset first error range or not; and judging whether the included angle between the drawn minute hand vector and the standard minute hand vector meets a preset second error range.
Preferably, the scoring module is specifically configured to: scoring the clocks drawn in the image to be evaluated according to preset scoring standards and detection results of the roundness detection module, the integrity detection module and the correctness detection module;
wherein, the preset scoring criteria are:
if the ratio of the area surrounded by the clock outline and the minimum circumscribing area meets a preset area ratio range, marking 1 minute;
if 12 numbers are all present, 1 point is recorded;
if the positions of the 12 numbers are accurate, 1 minute is recorded;
if the pointer points accurately, 1 minute is recorded.
Preferably, the roundness detection module further includes: a sensitivity improving unit;
the sensitivity-improving unit is configured to: the gray-scale image is input to the contour detection unit after being subjected to sensitivity-improving processing.
Preferably, the system further comprises: an image acquisition module;
the image acquisition module is configured to: and acquiring the image to be evaluated.
Preferably, the system further comprises: a display module;
the display module is configured to: and displaying the grading result.
Compared with the closest prior art, the application has the following beneficial effects:
the intelligent evaluation system based on the painting clock test provided by the application comprises: the device comprises a roundness detection module, an integrity detection module, a correctness detection module and a scoring module.
The roundness detection module measures roundness by calculating the ratio of the area surrounded by the clock outline to the minimum circumscribing area. The disadvantage of realizing circle fitting by using a least squares method is avoided by using a least circumscribed circle method: the least squares method is very severely affected by outliers, even with a few outliers, and the result will vary very strongly and sensitively. In addition, the module uses a pixel counting method to calculate the area surrounded by the outline of the clock, and is the most effective and simplest means for calculating the area of the irregular graph.
The integrity detection module adopts a fast-RCNN network structure to detect whether numbers, hour hands and minute hands exist in an image to be evaluated, and obtains corresponding coordinate values, the performance and efficiency of the network far exceed those of the prior fast-RCNN network, the training speed is extremely rapid, and the problem of precision and pixel loss of the ROIALigh in the fast-RCNN network is perfectly solved.
The correctness detection module respectively detects whether the digital position is correct or not and whether the directions of the hour hand and the minute hand are correct or not according to the coordinate value returned by the integrity detection module. The coordinate information obtained in the integrity detection module is skillfully combined, and the digital position, the hour hand and the minute hand pointing accuracy are detected by utilizing the knowledge of a trigonometric function and a vector; a more reliable error range is set, so that the confidence coefficient of the experimental result is higher; after a large amount of data training, the effect is obvious.
The evaluation system automatically carries out intelligent evaluation on the painting clock test image by utilizing the computer vision principle, solves the problem that a patient cannot conveniently go to a hospital to participate in the test, and effectively avoids the problem that scoring results are different due to different doctors.
Drawings
FIG. 1 is a schematic diagram of the main components of a first embodiment of the intelligent evaluation system based on the clock test of the present application;
fig. 2 is a schematic diagram of a second embodiment of the intelligent evaluation system based on the clock test.
Detailed Description
Preferred embodiments of the present application are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely for explaining the technical principles of the present application, and are not intended to limit the scope of the present application.
It should be noted that in the description of the present application, the terms "first," "second," and the like are merely used for convenience of description and are not to be construed as limiting the application as to the relative importance of the device, element or parameter being described or implied.
FIG. 1 is a schematic diagram of the first embodiment of the intelligent evaluation system based on the clock test. As shown in fig. 1, the intelligent evaluation system of the present embodiment includes: a roundness detection module 10, an integrity detection module 20, a correctness detection module 30, and a scoring module 40.
Wherein the roundness detection module 10 is configured to: detecting a clock outline in an image to be evaluated, drawing a minimum circumcircle of the clock outline, and calculating the ratio of the area surrounded by the clock outline to the area of the minimum circumcircle; the integrity detection module 20 is configured to: detecting whether numbers, hour hands and minute hands exist in the image to be evaluated, and acquiring corresponding coordinate values; the correctness detection module 30 is configured to: respectively detecting the digital position and whether the directions of the hour hand and the minute hand are accurate according to the acquired coordinate values; the scoring module 40 is configured to: and scoring the clocks drawn in the image to be evaluated according to the detection results of the roundness detection module, the integrity detection module and the correctness detection module. The 4 modules may all be disposed on the same CPU (for example, x86 chip), or the roundness detection module 10 may be disposed on the DSP, and the remaining 3 modules may be disposed on the CPU.
Roundness measurement is a measurement concept used to assess whether an actual circle (i.e., a circle manually drawn by a person involved in a clock tester) is sufficiently close to an ideal circle. The circle is a two-dimensional graph which can be presented in the form of pixels in a computer and which is programmed to derive the geometric problem, which is therefore both a geometric problem and a computer vision problem.
In roundness measurement, the prior art generally adopts one of the following three methods:
(1) Least squares circle method: the circle center of the circle with the smallest sum of squares of the distances from the corresponding points to the circumference on the measured circle outline is taken as the circle center, and the radius difference of the two concentric circles containing the measured circle outline is the roundness error.
(2) Minimum circumscribed circle method: the minimum circumscribing circle of the actual contour is calculated, and the area ratio=the area of the actual contour and the area of the minimum circumscribing circle are calculated, wherein the area ratio is more nearly 1, and the roundness is more.
(3) Maximum inscribed circle method: the maximum inscribed circle of the actual contour is obtained, and the area ratio=the maximum inscribed circle area/actual contour containing area is obtained, so that the closer the area ratio is to 1, the higher the roundness is.
In the application, a method of combining a minimum circumscribing method with an area ratio is adopted, namely after the minimum circumscribing method is obtained, the area ratio is calculated, and then the roundness of an actual circle is judged.
Specifically, the roundness detection module 10 in this embodiment may include: the device comprises a preprocessing unit, a contour detection unit, a circumscribing circle drawing unit and an area rate calculating unit.
Wherein the preprocessing unit is configured to convert the image to be evaluated into a gray scale; the profile detection unit is configured to detect a clock profile in the greyscale map (e.g. the profile may be detected using the RETR_EXTERNAL method in cv 2); the circumscribed circle drawing unit is configured to draw a minimum circumscribed circle of the clock outline (for example, a pointPolygontest (cnt, (j, i), true) method in cv2 can be utilized to adjust pixel points in the outline so as to realize image segmentation, and finally, a minEnclosingcircle method and a circle method in cv2 are used to draw the minimum circumscribed circle; the area ratio calculating unit is configured to calculate an area surrounded by the outline of the timepiece and an area of the minimum circumscribed circle, respectively, and calculate a ratio of the two.
Specifically, the area ratio calculation unit in the present embodiment may include: the device comprises a first area calculation subunit, a second area calculation subunit and a ratio calculation subunit.
Wherein the first area calculation subunit is configured to: calculating the number of pixels with the pixel value of 255 in the clock outline, and further calculating the area surrounded by the clock outline; the second area calculation subunit is configured to: calculating the area of the minimum circumscribing circle (because the minimum circumscribing circle is fitted, and meanwhile, the circle center coordinate and the radius information are obtained); the ratio calculation subunit is configured to: the ratio of the area enclosed by the clock outline to the area of the smallest circumcircle, i.e. the area ratio, is calculated. The closer the area ratio to 1, the closer the timepiece contour to an ideal circle.
The roundness measurement module in this embodiment has the following advantages:
(1) The disadvantage of the least square method for realizing circle fitting is avoided: the least squares method is very severely affected by outliers, even if there are few outliers, the result will vary very drastically and sensitively;
(2) The pixel count method is used, which is the most efficient and simplest means of calculating the irregular pattern area.
Specifically, the integrity detection module 20 in the present embodiment may include: mask-area based convolutional neural networks (Mask-RCNN). The module judges whether 12 numbers 1 to 12 exist or not, no missing exists, and returns the position coordinates of the 12 targets; in addition, whether the hour hand and the minute hand exist or not is judged, no missing exists, and the position coordinates of the two targets are returned. The returned coordinate values include: the coordinates of the center point of the bounding box surrounding each digit, hour hand, and minute hand.
If numbers, hour and minute hands are considered as target individuals, the best way to detect their presence and location coordinates is currently the very widely used fast-RCNN and Mask-RCNN in the industry.
In the system of this embodiment, mask-RCNN is selected. The Mask-RCNN comprises the following components from bottom to top: backbone, FPN, RPN, anchors, roIAlign, classification, box regress, and mask.
The Backbone is a convolutional neural network (ResNet 101 is generally used) for extracting image features, the ResNet is used for training a deeper neural network (because the performance of the neural network is degraded when the number of layers is high), and the ResNet uses cross-layer connection, so that training is easier; the backbone of the FPN is a standard convolutional neural network (typically, res net50 and res net 101) that acts as a feature extractor. The bottom layer detects low-level features (edges and corners, etc.), and the higher layer detects higher-level features (car, person, sky, etc.). The FPN improves the performance of the standard feature extraction pyramid by adding a second pyramid that can select advanced features from the first pyramid and pass on to the underlying layer. Through this process, it allows the features of each stage to be combined with the high-level and low-level features. The final effect of FPN is: the shallow level features can detect simple targets, and the deep level features can detect more complex targets; the function of the RPN is to recommend object proposals based on the region screened by the FPN. And extracting the characteristics of the characteristic diagram output by the last layer of the FPN through a convolution network by using a sliding window of n x n. Respectively judging the target category and performing fine adjustment of the size of the binding box through the CLS and the REG; anchor is used to generate a series of boxes on the pixel points of feature maps, the size of each box is determined by two parameters, scale= [128], ratio= [0.5,1,1.5], then each pixel point can generate 3 boxes of different sizes. The three frames are formed by maintaining the area of the frames unchanged to change the aspect ratio thereof by the value of ratio, thereby generating frames of different sizes; roialign is used to extract more deep features in the feature map provided by RPN. This is a more novel idea of Mask-RCNN than Fast-RCNN, which solves the problem of loss of accuracy that occurs in Fast-RCNN; classification is used to determine what class the object project belongs to; the Regression is used for fine tuning the binding box; the prediction of the mask is performed through a fully connected neural network and belongs to semantic segmentation. Mask-RCNN differs from other segmentation frameworks by first classifying and then segmenting.
The integrity detection module of the embodiment has the following advantages:
(1) Performance and efficiency far exceed those of the prior Faster-RCNN;
(2) The training speed is abnormally rapid;
(3) ROIAligh perfectly solves the accuracy and pixel loss problems of roikooling in fast-RCNN.
Specifically, the correctness detection module 30 in the present embodiment may include: a digital position detection unit and an hour hand and minute hand pointing to the detection unit.
Wherein the digital position detection unit is configured to: respectively detecting whether the positions of 12 numbers in the image to be evaluated are accurate or not; the hour hand and minute hand pointing detection unit is configured to: and detecting whether the directions of the hour hand and the minute hand in the image to be evaluated are accurate or not respectively.
The principle of detecting the accuracy of the digital position in this embodiment is as follows:
because the bounding box and the target number are nearly tangential, the center of the bounding box can be considered as the specific coordinates of the number. Taking the center position of the binding box corresponding to 12 and the center of the circumscribing circle to form a vector x 0 (from the circumscribed circle center to "12"). Similarly, the centers of the binding boxes corresponding to the other 11 digital categories can respectively form a vector x with the centers of the circumscribed circles 1 、x 2 、…、x 11 The method comprises the steps of carrying out a first treatment on the surface of the . The centers of the 12 digital categories of the binding boxes are ordered, and each vector x in the ideal state at this time i And x 0 The sequence of angles found using the inverse trigonometric function should be 0, 30, 60, 90, 120, 150, 180, 150, 120, 90, 60, 30 (degrees). Thus if one wants to know the order of 12 digital binding boxesWhether the arrangement of the included angles of the seven numbers 12, 1, 6 meets the requirement of A [ i ] can be judged firstly or not]＜A[i+1]And |A [ i+1 ]]-A[i]| < = 40.0 (where 40 = 30+10, 10 degrees is the error range), then determining if the angular arrangement of the next few digits (7, 8, …, 11) satisfies ai]＞A[i+1]And |A [ i+1 ]]-A[i]|＜＝40.0。
Specifically, the digital position detection unit in this embodiment may include: the device comprises a vector drawing subunit, an included angle calculating subunit and a digital judging subunit.
Wherein the vector drawing subunit is configured to: respectively drawing vectors x pointing to 12 numbers by taking the center of the minimum circumscribing circle as a starting point 0 、x 1 、x 2 、…、x 11 The method comprises the steps of carrying out a first treatment on the surface of the The included angle calculation subunit is configured to: respectively calculating vectors x 0 、x 1 、x 2 、…、x 11 Vector x 0 Obtain the included angle value A 0 、A 1 、A 2 、…、A 11 The method comprises the steps of carrying out a first treatment on the surface of the The digital judgment subunit is configured to: according to the included angle value A 0 、A 1 、A 2 、…、A 6 Judging A in turn 1 、A 2 、…、A 6 Whether each included angle is larger than the previous included angle or not and the absolute value of the difference value between the included angle and the previous included angle meets the preset included angle range (for example, 40 degrees); according to the included angle value A 7 、A 8 、…、A 11 、A 0 Judging A in turn 7 、A 8 、…、A 11 Whether each included angle is larger than the latter included angle or not and the absolute value of the difference value between the two included angles meets the preset included angle range (for example, 40 degrees).
The principle of judging the pointing accuracy of the hour hand in this embodiment is as follows:
under the condition that the hour hand and the minute hand are tangent by the marking box, the coordinate information can be used for easily obtaining which is the minute hand and which is the hour hand (adopting a geometric length method: making simple long-short relation judgment). The two centering boxes are respectively taken as center points to obtain a new center coordinate, and two vectors corresponding to the hour hand and the minute hand can be obtained at the time.
Examples: the target time point of "10:45" needs to be judged. The "target time point" referred to herein is a time designated in advance and at which a subject who is required to participate in the clock test is pointed in the drawn clock chart.
The vector (namely, the standard hour hand vector) formed by the circle center and the target 10 approximately coincides with the hour hand vector within a certain error range, so that the accurate pointing of the drawn hour hand is indicated. The 45 minutes can be judged to correspond to the number 9 by simple calculation, and the fact that the minute hand vector formed by the circle center and the 9, namely the standard minute hand vector, and the minute hand vector are approximately overlapped in a certain error range indicates that the drawn minute hand points are accurate.
Specifically, the hour hand and minute hand pointing detection unit in the present embodiment may include: the pointer region sub-unit, the pointer vector drawing sub-unit and the pointer judging sub-unit.
Wherein the pointer region molecular unit is configured to: distinguishing an hour hand from a minute hand according to the length relation of two pointers in an image to be evaluated; the pointer vector drawing subunit is configured to: respectively drawing a vector of an hour hand and a vector of a minute hand in the image to be evaluated and a standard hour hand vector and a standard minute hand vector pointing to a target time point; the pointer judgment subunit is configured to: judging whether the included angle between the drawn hour hand vector and the standard hour hand vector meets a preset first error range or not; and judging whether the included angle between the drawn minute hand vector and the standard minute hand vector meets a preset second error range.
The correctness detection module of the embodiment has the following advantages:
(1) The coordinate information obtained in the integrity detection module is skillfully combined;
(2) The detection of the digital position, the hour hand and the minute hand pointing accuracy is completed by utilizing the trigonometric function and the knowledge of the vector;
(3) A more reliable error range is set, so that the confidence coefficient of the experimental result is higher;
(4) After a large amount of data training, the effect is obvious.
Further, the scoring module 40 in this embodiment may be specifically configured to: and scoring the clocks drawn in the image to be evaluated according to a preset scoring standard and the detection results of the roundness detection module, the integrity detection module and the correctness detection module.
The picture clock test can be used for judging senile dementia, and the freehand picture clock is a complex behavioral activity, besides space construction skills, a lot of knowledge functions are needed to participate, and various cognitive functions such as memory, attention, abstract thinking, design, layout arrangement, application, numbers, calculation, time and space orientation concepts, operation sequence and the like are involved. The operation is simpler, time-saving and more acceptable to patients. There are various evaluation methods for the painting test, including a 3-point evaluation method, a 4-point evaluation method, a 5-point evaluation method, a 7-point evaluation method, a 10-point evaluation method, a 30-point evaluation method, and the like. However, the 4-Point method (0-4 Point method) is simple, sensitive and easy to implement, and the dementia diagnosis rate can reach 75%, so that a patient with dementia is often impossible to draw a clock dial completely.
In this embodiment, a 4-point assessment method is adopted, and preset scoring criteria are as follows:
(1) If the ratio of the area surrounded by the clock outline and the minimum circumscribing area meets the preset area ratio range, marking 1 minute;
(2) If 12 numbers are all present, 1 point is recorded;
(3) If the positions of the 12 numbers are accurate, 1 minute is recorded;
(4) If the pointer points accurately, 1 minute is recorded.
In an alternative embodiment, the roundness detection module 10 may further include: sensitivity improving unit.
Wherein the sensitivity improving unit is arranged between the preprocessing unit and the contour detecting unit and is configured to: the gray level image output by the preprocessing unit is subjected to sensitivity improvement processing (such as Canny algorithm), and then input to the contour detection unit.
Fig. 2 is a schematic diagram of a second embodiment of the intelligent evaluation system based on the clock test. As shown in fig. 2, the intelligent evaluation system of the present embodiment includes an image acquisition module 50 and a display module 60 in addition to the roundness detection module 10, the integrity detection module 20, the correctness detection module 30, and the scoring module 40.
The configurations of the roundness detection module 10, the integrity detection module 20, the correctness detection module 30, and the scoring module 40 are the same as those of the first embodiment, and are not described herein again; the image acquisition module 50 is configured to: collecting an image to be evaluated; the display module 60 is configured to: and displaying the grading result.
For example, the image to be evaluated is photographed by the image acquisition module 50 (e.g., a digital camera) for detection by the roundness detection module 10, the integrity detection module 20 and the correctness detection module 30, and then scored by the scoring module 40 according to the detection result, the scoring result may be displayed by the display module 60 (e.g., a liquid crystal display screen), and the acquired image to be evaluated may be displayed as required.
In the application, the intelligent evaluation system based on the clock test is divided into modules, units and sub-units, which are only used for better understanding the functions related to the technical scheme of the application, and in practice, the functions corresponding to the modules can be loaded and executed by single or multiple hardware programs.
Those of skill in the art will appreciate that the various illustrative method steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of functionality in order to clearly illustrate the interchangeability of electronic hardware and software. Whether such functionality is implemented as electronic hardware or software depends upon the particular application and design constraints imposed on the solution. Those skilled in the art may implement the described functionality using different approaches for each particular application, but such implementation is not intended to be limiting.
Thus far, the technical solution of the present application has been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present application is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present application, and such modifications and substitutions will be within the scope of the present application.
Claims (6)
1. An intelligent assessment system based on a paint clock test, the system comprising: the system comprises a roundness detection module, an integrity detection module, a correctness detection module and a scoring module;
the roundness detection module is configured to: detecting a clock outline in an image to be evaluated, drawing a minimum circumcircle of the clock outline, and calculating the ratio of the area surrounded by the clock outline to the area of the minimum circumcircle; the roundness detection module calculates the area surrounded by the clock outline by using a pixel counting method;
the roundness detection module includes: the device comprises a preprocessing unit, a contour detection unit, a circumscribing circle drawing unit and an area rate calculation unit;
the preprocessing unit is configured to: converting the image to be evaluated into a gray scale;
the contour detection unit is configured to: detecting the timepiece contour in the gray scale map;
the circumscribed circle drawing unit is configured to: drawing a minimum circumcircle of the clock outline;
the area ratio calculation unit is configured to: calculating the area surrounded by the clock outline and the area of the minimum circumscribing circle respectively, and obtaining the ratio of the area surrounded by the clock outline and the area of the minimum circumscribing circle;
the area ratio calculation unit includes: a first area calculation subunit, a second area calculation subunit, and a ratio calculation subunit;
the first area calculation subunit is configured to: calculating the number of pixels with the pixel value of 255 in the clock outline, and further calculating the area surrounded by the clock outline;
the second area calculation subunit is configured to: calculating the area of the minimum circumscribing circle;
the ratio calculation subunit is configured to: calculating the ratio of the area enclosed by the clock outline to the area of the minimum circumcircle;
the integrity detection module is configured to: detecting whether numbers, hour hands and minute hands exist in the image to be evaluated, and acquiring corresponding coordinate values;
the correctness detection module is configured to: according to the coordinate values, respectively detecting whether the digital position is correct or not and whether the directions of the hour hand and the minute hand are correct or not; the correctness detection module utilizes trigonometric functions and vectors to detect the pointing accuracy of the digital position, the hour hand and the minute hand; the correctness detection module sets an error range;
the correctness detection module comprises: a digital position detection unit, an hour hand and a minute hand pointing to the detection unit;
the digital position detection unit is configured to: respectively detecting whether the positions of 12 numbers in the image to be evaluated are accurate or not;
the digital position detection unit includes: the device comprises a vector drawing subunit, an included angle calculating subunit and a digital judging subunit;
the vector painting subunit is configured to: respectively drawing vectors x pointing to 12 numbers by taking the center of the minimum circumscribing circle as a starting point 0 、x 1 、x 2 、…、x 11 ；
The included angle calculation subunit is configured to: respectively calculating vectors x 0 、x 1 、x 2 、…、x 11 Vector x 0 Obtain the included angle value A 0 、A 1 、A 2 、…、A 11 ；
The digital judgment subunit is configured to: according to the included angle value A 0 、A 1 、A 2 、…、A 6 Judging A in turn 1 、A 2 、…、A 6 Whether each included angle is larger than the previous included angle or not and the absolute value of the difference value between the included angle and the previous included angle meets the preset included angle range; according to the included angle value A 7 、A 8 、…、A 11 、A 0 Judging A in turn 7 、A 8 、…、A 11 Whether each included angle is larger than the latter included angle or not and the absolute value of the difference value between the included angle and the latter included angle meets the preset included angle range;
the hour hand and minute hand pointing detection unit is configured to: respectively detecting whether the directions of the hour hand and the minute hand in the image to be evaluated are accurate;
the hour hand minute hand direction detecting unit includes: a pointer region sub-unit, a pointer vector drawing sub-unit and a pointer judging sub-unit;
the pointer region molecular unit is configured to: distinguishing an hour hand from a minute hand according to the length relation of the two pointers in the image to be evaluated;
the pointer vector drawing subunit is configured to: respectively drawing a vector of an hour hand and a vector of a minute hand in the image to be evaluated and a standard hour hand vector and a standard minute hand vector pointing to a target time point;
the pointer judgment subunit is configured to: judging whether the included angle between the drawn hour hand vector and the standard hour hand vector meets a preset first error range or not; judging whether the included angle between the drawn minute hand vector and the standard minute hand vector meets a preset second error range or not;
the scoring module is configured to: and scoring the clocks drawn in the image to be evaluated according to the detection results of the roundness detection module, the integrity detection module and the correctness detection module.
2. The paint clock test-based intelligent assessment system of claim 1, wherein the integrity detection module comprises: convolutional neural networks based on masked regions.
3. The paint clock test-based intelligent assessment system of claim 1, wherein the scoring module is specifically configured to: scoring the clocks drawn in the image to be evaluated according to preset scoring standards and detection results of the roundness detection module, the integrity detection module and the correctness detection module;
wherein, the preset scoring criteria are:
if the ratio of the area surrounded by the clock outline and the minimum circumscribing area meets a preset area ratio range, marking 1 minute;
if 12 numbers are all present, 1 point is recorded;
if the positions of the 12 numbers are accurate, 1 minute is recorded;
if the pointer points accurately, 1 minute is recorded.
4. The paint clock test-based intelligent assessment system of claim 1, wherein the roundness detection module further comprises: a sensitivity improving unit;
the sensitivity-improving unit is configured to: the gray-scale image is input to the contour detection unit after being subjected to sensitivity-improving processing.
5. The intelligent evaluation system based on the paint clock test of any one of claims 1-4, further comprising: an image acquisition module;
the image acquisition module is configured to: and acquiring the image to be evaluated.
6. The paint clock test-based intelligent assessment system of claim 5, further comprising: a display module;
the display module is configured to: and displaying the grading result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911300342.4A CN111091910B (en) | 2019-12-17 | 2019-12-17 | Intelligent evaluation system based on painting clock test |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911300342.4A CN111091910B (en) | 2019-12-17 | 2019-12-17 | Intelligent evaluation system based on painting clock test |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111091910A CN111091910A (en) | 2020-05-01 |
| CN111091910B true CN111091910B (en) | 2023-11-03 |
Family
ID=70395641
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911300342.4A Active CN111091910B (en) | 2019-12-17 | 2019-12-17 | Intelligent evaluation system based on painting clock test |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111091910B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111739636A (en) * | 2020-06-19 | 2020-10-02 | 智恩陪心(北京)科技有限公司 | PPAT-based psychological intelligent analysis system |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1755754A (en) * | 2004-02-27 | 2006-04-05 | 佳能株式会社 | Image display apparatus |
| CN104715157A (en) * | 2015-03-25 | 2015-06-17 | 成都信息工程学院 | Cognition impairment evaluating system and method based on clock drawing test |
| CN108197564A (en) * | 2017-12-29 | 2018-06-22 | 复旦大学附属中山医院 | A kind of assessment system and method for drawing clock experiment |
| CN108492870A (en) * | 2017-02-23 | 2018-09-04 | 中国科学院软件研究所 | Picture clock test detection method based on digital pen and system |
| CN110384484A (en) * | 2019-07-25 | 2019-10-29 | 科大讯飞股份有限公司 | A kind of pattern evaluation method, device, equipment and storage medium |
| CN110859599A (en) * | 2019-11-26 | 2020-03-06 | 复旦大学 | Cerebrovascular disease nerve injury patient cognitive function automatic screening system |
| RU2745282C1 (en) * | 2020-06-02 | 2021-03-23 | Государственное бюджетное учреждение здравоохранения Московской области "Московский областной научно-исследовательский клинический институт им. М.Ф. Владимирского" (ГБУЗ МО МОНИКИ им. М.Ф. Владимирского) | Method for diagnosing severity of vascular cognitive impairment |
| CA3103781A1 (en) * | 2019-12-23 | 2021-06-23 | Peter Anthony Hall | Method and system for assessing cognitive function of an individual |
| CN113795815A (en) * | 2019-05-06 | 2021-12-14 | 苹果公司 | Clock face for electronic equipment |
-
2019
- 2019-12-17 CN CN201911300342.4A patent/CN111091910B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1755754A (en) * | 2004-02-27 | 2006-04-05 | 佳能株式会社 | Image display apparatus |
| CN104715157A (en) * | 2015-03-25 | 2015-06-17 | 成都信息工程学院 | Cognition impairment evaluating system and method based on clock drawing test |
| CN108492870A (en) * | 2017-02-23 | 2018-09-04 | 中国科学院软件研究所 | Picture clock test detection method based on digital pen and system |
| CN108197564A (en) * | 2017-12-29 | 2018-06-22 | 复旦大学附属中山医院 | A kind of assessment system and method for drawing clock experiment |
| CN113795815A (en) * | 2019-05-06 | 2021-12-14 | 苹果公司 | Clock face for electronic equipment |
| CN110384484A (en) * | 2019-07-25 | 2019-10-29 | 科大讯飞股份有限公司 | A kind of pattern evaluation method, device, equipment and storage medium |
| CN110859599A (en) * | 2019-11-26 | 2020-03-06 | 复旦大学 | Cerebrovascular disease nerve injury patient cognitive function automatic screening system |
| CA3103781A1 (en) * | 2019-12-23 | 2021-06-23 | Peter Anthony Hall | Method and system for assessing cognitive function of an individual |
| RU2745282C1 (en) * | 2020-06-02 | 2021-03-23 | Государственное бюджетное учреждение здравоохранения Московской области "Московский областной научно-исследовательский клинический институт им. М.Ф. Владимирского" (ГБУЗ МО МОНИКИ им. М.Ф. Владимирского) | Method for diagnosing severity of vascular cognitive impairment |
Non-Patent Citations (5)
| Title |
|---|
| 多主干鱼骨型时钟树结构的设计方法及优化;袁书伟;钟传杰;朱兆伟;;微处理机(第04期);全文 * |
| 画钟测验在认知障碍老人中的鉴别作用;黄若燕;唐牟尼;佘生林;孙彬;林康广;郁俊昌;陈映梅;郭伟坚;肖;王怀坤;;中国神经精神疾病杂志(第08期) * |
| 老年2型糖尿病患者血清羧化不全骨钙素水平与认知功能的相关性研究;杨倩;《中国优秀硕士学位论文全文数据库医药卫生科技辑》(第第9期期);E065-51 * |
| 袁书伟 ; 钟传杰 ; 朱兆伟 ; .多主干鱼骨型时钟树结构的设计方法及优化.微处理机.2017,(第04期),全文. * |
| 黄若燕 ; 唐牟尼 ; 佘生林 ; 孙彬 ; 林康广 ; 郁俊昌 ; 陈映梅 ; 郭伟坚 ; 肖 ; 王怀坤 ; .画钟测验在认知障碍老人中的鉴别作用.中国神经精神疾病杂志.2013,(第08期), * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111091910A (en) | 2020-05-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | A detection and recognition system of pointer meters in substations based on computer vision | |
| CN112818988B (en) | Automatic identification reading method and system for pointer instrument | |
| CN105260709B (en) | Water meter calibration method, apparatus based on image procossing and system | |
| CN107229930B (en) | Intelligent identification method for numerical value of pointer instrument | |
| CN104392206B (en) | A kind of image processing method of readings of pointer type meters automatic identification | |
| CN105260710B (en) | Water meter calibration method, apparatus based on image procossing and system | |
| CN105300482B (en) | Water meter calibration method, apparatus based on image procossing and system | |
| CN109543682A (en) | A kind of readings of pointer type meters method based on deep learning | |
| US20170227942A1 (en) | Surface data acquisition, storage, and assessment system | |
| CN107066998A (en) | A kind of pointer-type circular single instrument board real-time identification method of utilization mobile device | |
| CN106529559A (en) | Pointer-type circular multi-dashboard real-time reading identification method | |
| CN109977191B (en) | Problem map detection method, device, electronic equipment and medium | |
| CN108197564B (en) | Evaluation system and method for picture clock test | |
| CN107194361A (en) | Two-dimentional pose detection method and device | |
| CN104732520A (en) | Cardio-thoracic ratio measuring algorithm and system for chest digital image | |
| US20240169518A1 (en) | Method and apparatus for identifying body constitution in traditional chinese medicine, electronic device, storage medium and program | |
| CN103136760B (en) | A kind of multi-sensor image matching process based on FAST Yu DAISY | |
| CN110826610A (en) | Method and system for intelligently detecting whether dressed clothes of personnel are standard | |
| CN107301408A (en) | Human body mask extracting method and device | |
| CN116338608B (en) | Method, device, equipment and storage medium for adjusting detection angle of microwave radar | |
| CN108645490A (en) | Cold-water meter vision detection system based on image processing techniques and detection method | |
| CN111091910B (en) | Intelligent evaluation system based on painting clock test | |
| Chen et al. | An intelligent vision recognition method based on deep learning for pointer meters | |
| CN111784660B (en) | Method and system for analyzing frontal face degree of face image | |
| CN116958983A (en) | Pointer type pressure gauge automatic calibrator indication reading method based on machine vision |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |