CN113033514B - Classroom student aggressiveness evaluation method based on network - Google Patents
Classroom student aggressiveness evaluation method based on network Download PDFInfo
- Publication number
- CN113033514B CN113033514B CN202110566458.3A CN202110566458A CN113033514B CN 113033514 B CN113033514 B CN 113033514B CN 202110566458 A CN202110566458 A CN 202110566458A CN 113033514 B CN113033514 B CN 113033514B
- Authority
- CN
- China
- Prior art keywords
- image
- value
- student
- eyeball
- pixel points
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/19—Sensors therefor
Abstract
The invention discloses a classroom student aggressiveness evaluation method based on a network, which is characterized by comprising the following steps of: s1, recording and uploading the live video of the student in the learning process of the student; s2, extracting a frame image; s3, obtaining a preprocessed image I [ x, y ] of the human face](ii) a S4, establishing a vertical gray scale integral projection curve to obtain a rising point n1And a falling point n2(ii) a S5, cutting the left and right boundaries of the image to obtain a cut face image; s6, performing binarization processing to obtain a binarized image; s7, obtaining eyeball pixel points, taking the intermediate position of the eyeball pixel points in the same range, and calculating the connecting line length L of the two eyeball pixel points; s8, counting the number of the connecting line length L, marking the data lower than the set range of the number as abnormal length data, and counting the length number of the abnormal data. The invention can effectively reflect extreme learning of the student.
Description
Technical Field
The invention relates to a classroom student aggressiveness evaluation method based on a network.
Background
With the advance of education informatization in China, online classroom teaching is developed rapidly, but technical tools adopted by online classrooms are not effectively related, so that the technology which should bring remarkable changes to the current classroom situation cannot excite the huge potential of online classrooms.
Compared with an offline class, the online class can select a favorite teacher according to the requirement, the course can be played circularly for multiple times, and the relative utilization time is convenient.
However, there are some disadvantages in online class, such as poor learning quality, which is of great importance in some stage education.
Disclosure of Invention
The invention aims to provide a system capable of effectively improving the online classroom learning quality.
In order to solve the problems, the invention provides a method for evaluating the activeness of students in class based on a network, which comprises the following steps:
s1, recording and uploading the live video of the student in the learning process of the student;
s2, extracting and uploading at least one frame of image of the live video according to a set time interval;
s3, preprocessing the image extracted in the step S2, wherein the preprocessing comprises graying processing and normalization processing, and thus a preprocessed image I [ x, y ] of the face is obtained;
s4, pre-processing image I [ x, y ]]Establishing a vertical gray scale integral projection curve, and obtaining a rising point n of the minimum function value in continuous rising in the vertical gray scale integral projection curve1And a point n of drop of the minimum function value in the successive drops2;
S5, setting the rising point n1As the left boundary of the face image, the descending point n is used2Cutting the right boundary of the face recognition to obtain a cut face image;
s6, performing binarization processing on the cut face image to obtain a binarized image;
s7, scanning the binary image from left to right or from right to left, defining pixel points with RGB values of 0 in a continuous threshold range as eyeball pixel points, taking the middle point position of the eyeball pixel points in the same range, and calculating the connecting line length L of the two eyeball pixel points;
and S8, counting the number of the connecting line length L, marking the data in the range lower than the number setting range of the connecting line length L as abnormal length data, and counting the number of the abnormal length data.
As a further improvement of the present invention, in step S4, the preprocessed image I [ x, y ] is processed]The vertical gray scale integral projection curve function on the image M multiplied by N is defined asAnd using the M × D image blocks to pre-process the image I [ x, y]Shifting to calculate the value of the vertical gray scale integral projection curve function with the formulaWherein M is the height of the preprocessed image I, N and D are the width of the preprocessed image, and the value of D is 5.
As a further improvement of the present invention, in step S7, when scanning the binarized image and when the number of pixels having an adjacent RGB value of 0 of a certain pixel exceeds a set number, the RGB values of the adjacent pixels of the certain pixel are all set to 0.
As a further improvement of the invention, the method also comprises a step S7.5 of measuring the maximum height difference of the pixel points of the eyeballs on each side to obtain the height value H of the eyeballs,
in step S8, the height value H is counted, data within a set range lower than the height value H is marked as abnormal height data, and the number of the abnormal height data is counted.
As a further improvement of the present invention, the step S2 includes:
s2.1, dividing the received video into a plurality of video segments according to set time;
s2.2 stores the video segments and marks them in chronological order, and the video segment stored earliest is extracted in the step S3 according to the chronological mark and deleted after being extracted.
As a further improvement of the present invention, the normalization process in step S3 includes:
s3.1, carrying out initial positioning on the eyes, arbitrarily intercepting an eye image in the stored face sample set as an eye template image, and definingIn which ITThe face image is opposite to the eye template; i is the extracted face image,is a mean operator; i isTI is the product of the images;the standard mean square error of the image area is taken as the position of the eyes, and the position where the correlation coefficient of the extracted face image matched with the eye template has the maximum value is taken as the position of the eyes;
and S3.2, after the eyes are positioned, rotating according to the connecting line of the two eyes, so that the connecting line of the two eyes is superposed with the horizontal line.
As a further improvement of the present invention, in step S3.1, the scale sizes of the clipped eye template images are set to 0.6, 0.8, 1.0, 1.2, and 1.4 respectively as corrected eye template images, the largest one of the maximum correlation coefficients at the matching positions of the face image and each corrected eye template image is taken as a finally selected corrected eye template, and the scale of the face image is adjusted according to the selected corrected eye template scale size.
As a further improvement of the present invention, an 8-bit grayscale image is obtained after the graying processing in step S3.
The method has the advantages that the whole-course video shooting is carried out on the student in the learning process of the student, the real-time video is uploaded and analyzed through the streaming media technology, the image is extracted according to the set time interval, the positions of two eyeballs in the image are calibrated, the distance between the two eyeballs is measured, the eyeball distance is counted, the reasonable value range of the eyeballs is obtained, the eyeball distance data which are lower than the reasonable value range are marked to be abnormal, and the learning volume of the student can be reflected by the times of abnormal data.
Detailed Description
The technical solution of the present invention is further explained by the following embodiments.
The invention comprises the following steps:
s1, recording and uploading the live video of the student in the learning process of the student;
s2, extracting and uploading at least one frame of image of the live video according to a set time interval;
s3, preprocessing the image extracted in the above steps, wherein the preprocessing comprises graying processing and normalization processing, so as to obtain a preprocessed image I [ x, y ] of the face;
s4, pre-processing image I [ x, y ]]Establishing a vertical gray scale integral projection curve, and obtaining a rising point n of the minimum function value in continuous rising in the vertical gray scale integral projection curve1And a point n of drop of the minimum function value in the successive drops2;
S5, setting the rising point n1As the left boundary of the face image, the above-mentioned dropping point n is used2Cutting the right boundary of the face recognition to obtain a cut face image;
s6, performing binarization processing on the cut face image to obtain a binarized image;
s7, scanning the binary image from left to right or from right to left, defining pixel points with RGB value of 0 in a continuous threshold range as eyeball pixel points, taking the middle point position of the eyeball pixel points in the same range, and calculating the connecting line length L of the two eyeball pixel points;
s8, counting the number of the connecting line length L, marking the data lower than the set range of the number as abnormal length data, and counting the length number of the abnormal data.
As a further improvement of the present invention, in step S4, the preprocessed image I [ x, y ] is processed]The vertical gray scale integral projection curve function on the image M multiplied by N is defined asAnd using the M × D image blocks to pre-process the image I [ x, y]Shifting to calculate the value of the vertical gray scale integral projection curve function with the formulaWherein M is the height of the preprocessed image I, N and D are the width of the preprocessed image, and the value of D is 5.
As a further improvement of the present invention, in step S7, when scanning the binarized image and when the number of pixels having an adjacent RGB value of 0 of a certain pixel exceeds a set number, the RGB values of the adjacent pixels of the certain pixel are all set to 0.
As a further improvement of the present invention,
further comprises a step S7.5 of measuring the maximum height difference of the eyeball pixel points on each side to obtain an eyeball height value H,
in step S8, the height value H may be counted, and the height number of the abnormal data may be counted by marking the data lower than the set range as abnormal data.
As a further improvement of the present invention, the step S2 includes:
s2.1, dividing the received video into a plurality of video segments according to set time;
s2.2 stores the above video segments and marks them in chronological order, and the video segment stored earliest is extracted in the step S3 in chronological order, and deleted after the extraction.
As a further improvement of the present invention, the normalization process in step S3 includes:
s3.1, carrying out initial positioning on the eyes, arbitrarily intercepting an eye image in the stored face sample set as an eye template image, and definingIn which ITThe face image is opposite to the eye template; i is the extracted face image,is a mean operator; i isTI is the product of the images;the standard mean square error of the image area is taken as the position of the eyes, and the position where the correlation coefficient of the extracted face image matched with the eye template has the maximum value is taken as the position of the eyes;
and S3.2, after the eyes are positioned, rotating according to the connecting line of the two eyes, so that the connecting line is superposed with the horizontal line.
As a further improvement of the present invention, in step S3.1, the scale sizes of the clipped eye template images are respectively set to 0.6, 0.8, 1.0, 1.2, and 1.4 as corrected eye template images, and the largest one of the maximum correlation coefficients at the matching position between the face image and each corrected eye template image is taken as a finally selected corrected eye template, and the scale of the face image is adjusted according to the selected corrected eye template scale.
As a further improvement of the present invention, an 8-bit grayscale image is obtained after the graying processing in step S3.
The first embodiment,
S1, recording and uploading the live video of the student in the learning process of the student;
s2, extracting and uploading at least one frame of image of the live video according to a set time interval;
s3, preprocessing the image extracted in the above steps, wherein the preprocessing comprises graying processing and normalization processing, so as to obtain a preprocessed image I [ x, y ] of the face;
s4, pre-processing image I [ x, y ]]Establishing a vertical gray scale integral projection curve, and obtaining a rising point n of the minimum function value in continuous rising in the vertical gray scale integral projection curve1And a point n of drop of the minimum function value in the successive drops2;
S5, setting the rising point n1As the left boundary of the face image, the above-mentioned dropping point n is used2Cutting the right boundary of the face recognition to obtain a cut face image;
s6, performing binarization processing on the cut face image to obtain a binarized image;
s7, scanning the binary image from left to right or from right to left, defining pixel points with RGB value of 0 in a continuous threshold range as eyeball pixel points, taking the middle point position of the eyeball pixel points in the same range, and calculating the connecting line length L of the two eyeball pixel points;
s8, counting the number of the connecting line length L, marking the data lower than the set range of the number as abnormal length data, and counting the length number of the abnormal data.
Example II,
S1, recording and uploading the live video of the student in the learning process of the student;
s2, extracting and uploading at least one frame of image of the live video according to a set time interval;
s3, preprocessing the image extracted in the above steps, wherein the preprocessing comprises graying processing and normalization processing, so as to obtain a preprocessed image I [ x, y ] of the face;
s4, pre-processing image I [ x, y ]]Establishing a vertical gray scale integral projection curve, and processing the preprocessed image I [ x, y ]]The vertical gray scale integral projection curve function on the image M multiplied by N is defined asAnd using the M × D image blocks to pre-process the image I [ x, y]Shifting to calculate the value of the vertical gray scale integral projection curve function with the formulaWherein M is the height of the preprocessed image I, N and D are the width of the preprocessed image, and the value of D is 5 in the vertical gray scale integral projection curve;
s5, setting the rising point n1As the left boundary of the face image, the above-mentioned dropping point n is used2Cutting the right boundary of the face recognition to obtain a cut face image;
s6, performing binarization processing on the cut face image to obtain a binarized image;
s7, scanning the binary image from left to right or from right to left, defining pixel points with RGB value of 0 in a continuous threshold range as eyeball pixel points, taking the middle point position of the eyeball pixel points in the same range, and calculating the connecting line length L of the two eyeball pixel points;
s8, counting the number of the connecting line length L, marking the data lower than the set range of the number as abnormal length data, and counting the length number of the abnormal data.
Example III,
S1, recording and uploading the live video of the student in the learning process of the student;
s2, extracting and uploading at least one frame of image of the live video according to a set time interval;
s3, preprocessing the image extracted in the above steps, wherein the preprocessing comprises graying processing and normalization processing, so as to obtain a preprocessed image I [ x, y ] of the face;
s4, pre-processing image I [ x, y ]]Establishing a vertical gray scale integral projection curve, and processing the preprocessed image I [ x, y ]]The vertical gray scale integral projection curve function on the image M multiplied by N is defined asAnd using M × D image blocks inPreprocessing an image I [ x, y ]]Shifting to calculate the value of the vertical gray scale integral projection curve function with the formulaWherein M is the height of the preprocessed image I, N and D are the width of the preprocessed image, and the value of D is 5 in the vertical gray scale integral projection curve;
s5, setting the rising point n1As the left boundary of the face image, the above-mentioned dropping point n is used2Cutting the right boundary of the face recognition to obtain a cut face image;
s6, performing binarization processing on the cut face image to obtain a binarized image;
s7, scanning the binary image from left to right or from right to left, defining the pixel point with the RGB value of 0 in the continuous threshold range as an eyeball pixel point, in addition, when the number of the pixel points with the adjacent RGB value of 0 of a certain pixel point exceeds the set number, setting the RGB values of the adjacent pixel points of the pixel point to be 0, taking the middle point position of the eyeball pixel point in the same range, and calculating the connecting line length L of the two eyeball pixel points;
s8, counting the number of the connecting line length L, marking the data lower than the set range of the number as abnormal length data, and counting the length number of the abnormal data.
Example four,
S1, recording and uploading the live video of the student in the learning process of the student;
s2, extracting and uploading at least one frame of image of the live video according to a set time interval;
s3, preprocessing the image extracted in the above steps, wherein the preprocessing comprises graying processing and normalization processing, so as to obtain a preprocessed image I [ x, y ] of the face;
s4, pre-processing image I [ x, y ]]Establishing a vertical gray scale integral projection curve, and processing the preprocessed image I [ x, y ]]The vertical gray scale integral projection curve function on the image M multiplied by N is defined asAnd using the M × D image blocks to pre-process the image I [ x, y]Shifting to calculate the value of the vertical gray scale integral projection curve function with the formulaWherein M is the height of the preprocessed image I, N and D are the width of the preprocessed image, and the value of D is 5 in the vertical gray scale integral projection curve;
s5, setting the rising point n1As the left boundary of the face image, the above-mentioned dropping point n is used2Cutting the right boundary of the face recognition to obtain a cut face image;
s6, performing binarization processing on the cut face image to obtain a binarized image;
s7, scanning the binary image from left to right or from right to left, defining the pixel point with the RGB value of 0 in the continuous threshold range as an eyeball pixel point, in addition, when the number of the pixel points with the adjacent RGB value of 0 of a certain pixel point exceeds the set number, setting the RGB values of the adjacent pixel points of the pixel point to be 0, taking the middle point position of the eyeball pixel point in the same range, and calculating the connecting line length L of the two eyeball pixel points;
s7.5, measuring the maximum height difference of the eyeball pixel points on each side to obtain an eyeball height value H;
s8, counting the number of the connection length L, marking the data lower than the set range of the number as abnormal length data, and counting the length number of the abnormal data; and meanwhile, counting the height value H, marking the data lower than the value within a set range as abnormal data, and counting the height number of the abnormal data.
Example V,
S1, recording and uploading the live video of the student in the learning process of the student;
s2, extracting and uploading at least one frame of image of the live video according to a set time interval;
s3, preprocessing the image extracted in the above steps, wherein the preprocessing comprises graying processing and normalization processing, so as to obtain a preprocessed image I [ x, y ] of the face;
s3.1, carrying out initial positioning on the eyes, arbitrarily intercepting an eye image in the stored face sample set as an eye template image, and definingIn which ITThe face image is opposite to the eye template; i is the extracted face image,is a mean operator; i isTI is the product of the images;the standard mean square error of the image area is taken as the position of the eyes, and the position where the correlation coefficient of the extracted face image matched with the eye template has the maximum value is taken as the position of the eyes;
and S3.2, after the eyes are positioned, rotating according to the connecting line of the two eyes, so that the connecting line is superposed with the horizontal line.
As a further improvement of the present invention, in step S3.1, the scale sizes of the clipped eye template images are respectively set to 0.6, 0.8, 1.0, 1.2, and 1.4 as corrected eye template images, and the largest one of the maximum correlation coefficients at the matching position between the face image and each corrected eye template image is taken as a finally selected corrected eye template, and the scale of the face image is adjusted according to the selected corrected eye template scale.
S4, pre-processing image I [ x, y ]]Establishing a vertical gray scale integral projection curve, and processing the preprocessed image I [ x, y ]]The vertical gray scale integral projection curve function on the image M multiplied by N is defined asAnd using the M × D image blocks to pre-process the image I [ x, y]Shifting to calculate the value of the vertical gray scale integral projection curve function with the formulaWherein M is the height of the preprocessed image I, N and D are the width of the preprocessed image, and the value of D is 5 in the vertical gray scale integral projection curve;
s5, setting the rising point n1As the left boundary of the face image, the above-mentioned dropping point n is used2Cutting the right boundary of the face recognition to obtain a cut face image;
s6, performing binarization processing on the cut face image to obtain a binarized image;
s7, scanning the binary image from left to right or from right to left, defining the pixel point with the RGB value of 0 in the continuous threshold range as an eyeball pixel point, in addition, when the number of the pixel points with the adjacent RGB value of 0 of a certain pixel point exceeds the set number, setting the RGB values of the adjacent pixel points of the pixel point to be 0, taking the middle point position of the eyeball pixel point in the same range, and calculating the connecting line length L of the two eyeball pixel points;
s7.5, measuring the maximum height difference of the eyeball pixel points on each side to obtain an eyeball height value H;
s8, counting the number of the connection length L, marking the data lower than the set range of the number as abnormal length data, and counting the length number of the abnormal data; and meanwhile, counting the height value H, marking the data lower than the value within a set range as abnormal data, and counting the height number of the abnormal data.
The technical principle of the present invention is described above in connection with specific embodiments. The description is made for the purpose of illustrating the principles of the invention and should not be construed in any way as limiting the scope of the invention. Based on the explanations herein, those skilled in the art will be able to conceive of other embodiments of the present invention without inventive effort, which would fall within the scope of the present invention.
Claims (7)
1. A classroom student aggressiveness evaluation method based on a network is characterized by comprising the following steps:
s1, recording and uploading the live video of the student in the learning process of the student;
s2, extracting and uploading at least one frame of image of the live video according to a set time interval;
s3, preprocessing the image extracted in the step S2, wherein the preprocessing comprises graying processing and normalization processing, and thus a preprocessed image I [ x, y ] of the face is obtained;
s4, pre-processing image I [ x, y ]]Establishing a vertical gray scale integral projection curve, and obtaining a rising point n of the minimum function value in continuous rising in the vertical gray scale integral projection curve1And a point n of drop of the minimum function value in the successive drops2;
S5, setting the rising point n1As the left boundary of the face image, the descending point n is used2Cutting the right boundary of the face recognition to obtain a cut face image;
s6, performing binarization processing on the cut face image to obtain a binarized image;
s7, scanning the binary image from left to right or from right to left, defining pixel points with RGB values of 0 in a continuous threshold range as eyeball pixel points, taking the middle point position of the eyeball pixel points in the same range, and calculating the connecting line length L of the two eyeball pixel points;
s8, counting the value of the connection length L, marking the data in the value setting range lower than the connection length L as abnormal length data, counting the number of the abnormal length data, and reflecting the extreme learning of the student according to the number of the abnormal data;
wherein:
in the step S4, the preprocessed image I [ x, y ] is processed]The vertical gray scale integral projection curve function on the image M multiplied by N is defined asAnd using the M × D image blocks to pre-process the image I [ x, y]Shifting to calculate the value of the vertical gray scale integral projection curve function with the formulaWherein M is the height of the preprocessed image I, N and D are the width of the preprocessed image, and the value of D is 5.
2. The method as claimed in claim 1, wherein in step S7, when the binary image is scanned and the number of pixels with RGB value 0 adjacent to a certain pixel exceeds a predetermined number, the RGB values of the adjacent pixels of the certain pixel are all set to 0.
3. The method as claimed in claim 2, further comprising a step S7.5 of obtaining a height value H of the eyeball by measuring the maximum height difference of the pixel points of the eyeball at each side,
in step S8, the height value H is counted, data within a set range lower than the height value H is marked as abnormal height data, and the number of the abnormal height data is counted.
4. The method for evaluating the activeness of classroom members based on internet according to claim 3, wherein the step S2 includes:
s2.1, dividing the received video into a plurality of video segments according to set time;
s2.2 stores the video segments and marks them in chronological order, and the video segment stored earliest is extracted in the step S3 according to the chronological mark and deleted after being extracted.
5. The method for evaluating the activeness of a classroom student based on internet according to claim 4, wherein the normalization process in step S3 includes:
s3.1, carrying out initial positioning on the eyes, arbitrarily intercepting an eye image in the stored face sample set as an eye template image, and definingIn which ITThe face image is opposite to the eye template; i is the extracted face image, which is a mean operator; i isTI is the product of the images;the standard mean square error of the image area is taken as the position of the eyes, and the position where the correlation coefficient of the extracted face image matched with the eye template has the maximum value is taken as the position of the eyes;
and S3.2, after the eyes are positioned, rotating according to the connecting line of the two eyes, so that the connecting line of the two eyes is superposed with the horizontal line.
6. The method as claimed in claim 5, wherein in step S3.1, the captured eye template images are respectively modified to have the proportional sizes of 0.6, 0.8, 1.0, 1.2 and 1.4, and the largest of the maximum correlation coefficients at the matching positions of the face image and each modified eye template image is taken as the finally selected modified eye template, and the proportion of the face image is adjusted according to the selected modified eyeball template proportional size.
7. The method for evaluating the activeness of classroom members based on internet according to claim 6, wherein an 8-bit grayed image is obtained after the graying process in step S3.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110566458.3A CN113033514B (en) | 2021-05-24 | 2021-05-24 | Classroom student aggressiveness evaluation method based on network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110566458.3A CN113033514B (en) | 2021-05-24 | 2021-05-24 | Classroom student aggressiveness evaluation method based on network |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113033514A CN113033514A (en) | 2021-06-25 |
CN113033514B true CN113033514B (en) | 2021-08-17 |
Family
ID=76455710
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110566458.3A Active CN113033514B (en) | 2021-05-24 | 2021-05-24 | Classroom student aggressiveness evaluation method based on network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113033514B (en) |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101305913B (en) * | 2008-07-11 | 2010-06-09 | 华南理工大学 | Face beauty assessment method based on video |
CN108256392A (en) * | 2016-12-29 | 2018-07-06 | 广州映博智能科技有限公司 | Pupil region localization method based on projecting integral and area grayscale extreme value |
CN111860423A (en) * | 2020-07-30 | 2020-10-30 | 江南大学 | Improved human eye positioning method of integral projection method |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101739546A (en) * | 2008-11-05 | 2010-06-16 | 沈阳工业大学 | Image cross reconstruction-based single-sample registered image face recognition method |
US10533850B2 (en) * | 2013-07-12 | 2020-01-14 | Magic Leap, Inc. | Method and system for inserting recognized object data into a virtual world |
CN106682603B (en) * | 2016-12-19 | 2020-01-21 | 陕西科技大学 | Real-time driver fatigue early warning system based on multi-source information fusion |
CN109446880A (en) * | 2018-09-05 | 2019-03-08 | 广州维纳斯家居股份有限公司 | Intelligent subscriber participation evaluation method, device, intelligent elevated table and storage medium |
CN112329631A (en) * | 2020-11-05 | 2021-02-05 | 浙江点辰航空科技有限公司 | Method for carrying out traffic flow statistics on expressway by using unmanned aerial vehicle |
-
2021
- 2021-05-24 CN CN202110566458.3A patent/CN113033514B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101305913B (en) * | 2008-07-11 | 2010-06-09 | 华南理工大学 | Face beauty assessment method based on video |
CN108256392A (en) * | 2016-12-29 | 2018-07-06 | 广州映博智能科技有限公司 | Pupil region localization method based on projecting integral and area grayscale extreme value |
CN111860423A (en) * | 2020-07-30 | 2020-10-30 | 江南大学 | Improved human eye positioning method of integral projection method |
Also Published As
Publication number | Publication date |
---|---|
CN113033514A (en) | 2021-06-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109034036B (en) | Video analysis method, teaching quality assessment method and system and computer-readable storage medium | |
CN106778676B (en) | Attention assessment method based on face recognition and image processing | |
CN109460762B (en) | Answer sheet scoring method based on image recognition | |
CN106033535B (en) | Electronic paper marking method | |
CN112183238B (en) | Remote education attention detection method and system | |
CN108876195A (en) | A kind of intelligentized teachers ' teaching quality evaluating system | |
CN113762107A (en) | Object state evaluation method and device, electronic equipment and readable storage medium | |
CN108345833A (en) | The recognition methods of mathematical formulae and system and computer equipment | |
CN111144151A (en) | High-speed dynamic bar code real-time detection method based on image recognition | |
CN110443800A (en) | The evaluation method of video image quality | |
CN110929562A (en) | Answer sheet identification method based on improved Hough transformation | |
CN105678301B (en) | method, system and device for automatically identifying and segmenting text image | |
CN111444389A (en) | Conference video analysis method and system based on target detection | |
CN109886945A (en) | Based on contrast enhancing without reference contrast distorted image quality evaluating method | |
CN111259844B (en) | Real-time monitoring method for examinees in standardized examination room | |
CN112801965A (en) | Sintering belt foreign matter monitoring method and system based on convolutional neural network | |
CN106033534B (en) | Electronic paper marking method based on straight line detection | |
CN109034590A (en) | A kind of intelligentized teaching quality evaluation for teachers management system | |
CN117152648A (en) | Auxiliary teaching picture recognition device based on augmented reality | |
CN113592839B (en) | Distribution network line typical defect diagnosis method and system based on improved fast RCNN | |
CN113033514B (en) | Classroom student aggressiveness evaluation method based on network | |
US20170358273A1 (en) | Systems and methods for resolution adjustment of streamed video imaging | |
CN113989608A (en) | Student experiment classroom behavior identification method based on top vision | |
CN107067399A (en) | A kind of paper image segmentation processing method | |
CN104077562B (en) | A kind of scanning direction determination methods of test paper |
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 |