CN111310709A - Image-text annual newspaper emotion calibration method and system - Google Patents
Image-text annual newspaper emotion calibration method and system Download PDFInfo
- Publication number
- CN111310709A CN111310709A CN202010136298.4A CN202010136298A CN111310709A CN 111310709 A CN111310709 A CN 111310709A CN 202010136298 A CN202010136298 A CN 202010136298A CN 111310709 A CN111310709 A CN 111310709A
- Authority
- CN
- China
- Prior art keywords
- image
- pictures
- text
- grading
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000008451 emotion Effects 0.000 title claims abstract description 51
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000013499 data model Methods 0.000 claims description 12
- 239000000284 extract Substances 0.000 claims description 12
- 230000008921 facial expression Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 210000004709 eyebrow Anatomy 0.000 claims description 6
- 210000000887 face Anatomy 0.000 claims description 6
- 230000000007 visual effect Effects 0.000 claims description 3
- 238000001303 quality assessment method Methods 0.000 claims 1
- 238000011156 evaluation Methods 0.000 abstract description 12
- 238000013441 quality evaluation Methods 0.000 description 4
- 230000008909 emotion recognition Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
- G06V40/174—Facial expression recognition
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- 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
- 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
- G06V40/178—Human faces, e.g. facial parts, sketches or expressions estimating age from face image; using age information for improving recognition
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Multimedia (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
The method comprises the step of calibrating the emotion of the image-text annual newspaper according to the obtained characteristic values of age grading numerical values, smile grading numerical values and image quality grading numerical values of all pictures, wherein the calibration content comprises positive, negative, upward trend and downward trend. The method and the system can obviously improve the work efficiency of the part for emotion calibration of the image-text annual newspaper during self-evaluation in schools, realize automation and further improve the work of the part for feeding back the quality of the produced image-text annual newspaper; the image-text annual newspaper emotion calibration method and system of the machine are more uniform and objective.
Description
Technical Field
The invention relates to the field of picture emotion recognition, in particular to an emotion calibration method, system, electronic equipment and application of image-text annual newspaper.
Background
Schools of all levels including colleges and universities, college and secondary schools, high schools, junior schools and primary schools have teaching quality evaluation services, and receive internal self-evaluation or external evaluation; since 2017, the prosperous development of image-text social media enables the school subjects to publish paper or electronic annual image-text annual newspapers for showing progress or changes in teaching quality, teaching innovation and the like. At present, evaluation and calibration of the internal self-evaluation or external evaluation of the school to the image-text annual newspaper are important links in the whole teaching quality evaluation, because the industry considers that the evaluation can reflect certain problems in form or essence, such as whether the school is heavily invested and whether the school sufficiently pays attention. The method is an improvement from no calibration evaluation to artificial emotion calibration evaluation; however, such manual calibration evaluation has at least two disadvantages. Firstly, for a large number of image-text annual newspapers including various years and pages in different schools, a large amount of human resources are needed, and the efficiency is extremely low; secondly, subjective judgment and attitude of a plurality of manual calibration personnel are different, the scale standards are not uniform, and the same neutral judgment party does not exist.
In the prior art after being inquired, an emotion recognition method for a main text exists, and mainly relates to an algorithm of colleges and universities, a text emotion recognition device of a Baidu company and the like; however, these methods are not suitable for the situation calibration of the school image-text annual newspaper with pictures as main content at present, which is an application in a specific environment.
Disclosure of Invention
The invention aims to provide a method and a system for calibrating emotion of image-text annual newspaper, electronic equipment and application thereof, so as to solve the technical problems.
The technical scheme adopted by the invention is as follows:
a method for calibrating emotion of image-text annual newspaper is applied to electronic equipment and comprises the following steps:
traversing all pictures in the image-text annual report, identifying age classification numerical values of people in the pictures according to a human face appearance identification algorithm, and further obtaining representation values of the age classification numerical values of all the people in the pictures;
traversing all pictures in the image-text annual report, identifying smile grading values of characters in the pictures according to a facial expression identification algorithm, and further obtaining representation values of the smile grading values of all the characters in the pictures;
traversing all pictures in the image-text annual report, identifying the image quality grading numerical value of the pictures according to an image quality identification algorithm, and further obtaining the representation value of the image quality grading numerical value of all the pictures in the pictures;
and calibrating the emotion of the image-text annual newspaper according to the obtained representative values of the age grading numerical values, the smile grading numerical values and the image quality grading numerical values of all the pictures, wherein the calibration contents comprise positive, negative, upward trend and downward trend.
Further, the method also comprises the following steps: and acquiring the emotion calibration result of the image-text annual report of the historical year to obtain the upward trend or the downward trend in the calibration content.
Further, the picture quality identification algorithm includes one or more of the following indicators: definition, saturation, brightness, contrast, and converting the index into a data model for calculation of the algorithm.
Further, the human face appearance recognition algorithm extracts the characteristics of eyes, mouth corners, eyebrows, skins and chin of a human face in the picture, compares the characteristics with the characteristics of a plurality of levels of standard human faces with preset age spans, obtains the level of the age span with the highest similarity after weighting, determines the age grading value of the picture, and takes the arithmetic mean of the age grading values of all the pictures as the representation value of the age grading values of all the people in the image-text annual newspaper; the image quality identification algorithm extracts the indexes of each image in the image annual report, constructs a data model to calculate the image quality grading value of each image, and takes the arithmetic mean value of the image quality grading values of all the images as the representation value of the image quality grading values of all the images in the image annual report.
Correspondingly to the method, the invention also provides a system for calibrating the emotion of the image-text annual newspaper, which is applied to electronic equipment and comprises the following units:
the picture scanning and separating reading unit is used for acquiring the image-text content in the annual newspaper page by page and separating each picture for acquiring the subsequent numerical information of each picture;
the representative value acquisition unit of the age classification numerical value is used for traversing all pictures in the image-text annual report, identifying the age classification numerical value of the figures in the pictures according to a face appearance identification algorithm, and further obtaining the representative value of the age classification numerical value of all the figures in the pictures;
the representative value acquisition unit of the smile grading numerical value is used for traversing all pictures in the image-text annual report, identifying the smile grading numerical value of the figures in the pictures according to a facial expression identification algorithm and further obtaining the representative value of the smile grading numerical value of all the figures in the pictures;
the characteristic value acquisition unit of the image quality grading numerical value is used for traversing all the pictures in the image-text annual report, identifying the image quality grading numerical value of the pictures according to a picture image quality identification algorithm and further obtaining the characteristic value of the image quality grading numerical value of all the pictures in the pictures;
the image-text annual newspaper emotion calibrating unit is used for calibrating the emotion of the image-text annual newspaper according to the obtained characteristic values of the age grading numerical values, the smile grading numerical values and the image quality grading numerical values of all the pictures, and the calibrating content comprises positive, negative, upward trend and downward trend;
and the visual display unit is used for displaying the result of the calibration content.
Further, the historical data acquisition and storage unit is used for acquiring the emotion calibration result of the image-text annual report of the historical year so as to obtain the upward trend or the downward trend in the calibration content.
Further, the picture quality identification algorithm in the value-representative-value obtaining unit of the image quality classification value takes one or more of the following indexes into consideration: definition, saturation, brightness, contrast, and converting the index into a data model for calculation of the algorithm.
Further, the human face appearance recognition algorithm in the representative value acquisition unit of the age classification numerical value extracts the characteristics of eyes, mouth corners, eyebrows, skins and chin of a human face in the picture to be respectively compared with the characteristics of a plurality of levels of standard human faces with preset age spans, the level of the age span with the highest similarity is obtained after weighting, the age classification numerical value of the picture is determined, and the arithmetic average value of the age classification numerical values of all the pictures is used as the representative value of the age classification numerical values of all the people in the image-text annual newspaper;
and the picture quality identification algorithm in the representative value acquisition unit of the picture quality grading numerical value extracts the indexes of each picture in the picture annual report, constructs a data model to calculate the picture quality grading numerical value of each picture, and takes the arithmetic mean of the picture quality grading numerical values of all the pictures as the representative values of the picture quality grading numerical values of all the pictures in the picture annual report.
Correspondingly to the foregoing method, the present invention also provides an electronic device, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the teletext emotion marking method described above.
In practical application, the image-text annual newspaper emotion calibration method is used for teaching quality evaluation of schools.
Compared with the prior art, the invention has the beneficial effects that: the work efficiency of the part for emotion calibration of the image-text annual newspaper during self-evaluation in the school is remarkably improved, automation is realized, and the work of the part is further improved for feeding back the quality of the produced image-text annual newspaper; the image-text annual newspaper emotion calibration method and system of the machine are more uniform and objective.
Drawings
FIG. 1 is a schematic flow chart of the image-text annual newspaper emotion calibrating method of the present invention;
FIG. 2 is a schematic diagram of the composition of the image-text annual newspaper emotion marking system of the present invention;
the method comprises the steps of 00-image-text annual newspaper emotion calibrating method, 01-obtaining representing values of age grading numerical values of all characters, 02-obtaining representing values of smile grading numerical values of all characters, 03-obtaining representing values of image quality grading numerical values of all pictures, 04-calibrating emotion of image-text annual newspapers according to the representing values, E-electronic equipment, 0-image-text annual newspaper emotion calibrating system, 1-picture scanning separation reading unit, 2-representing value obtaining unit of age grading numerical values, 3-representing value obtaining unit of smile grading numerical values, 4-representing value obtaining unit of image quality grading numerical values, 5-image-text annual newspaper emotion calibrating unit and 6-visual display unit.
Detailed Description
The technical solutions in the present invention will be described clearly and completely with reference to the accompanying drawings, and it is obvious that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
First embodiment
Referring to fig. 1, fig. 1 is a schematic flow chart of the image-text annual newspaper emotion calibration method of the present invention. The image-text annual newspaper emotion calibration method 00 is applied to electronic equipment.
The image-text annual report takes an image as a main body and is matched with a small amount of text description, but the content quality and the surface quality of the image can be read to useful information, so that the quality and the emotion are reflected; electronic devices include, but are not limited to, cell phones, laptops, desktops, ipads, or servers, with an executable program of application software installed therein for performing the method.
The method comprises the following steps:
01-traversing all pictures in the image-text annual report, identifying age classification numerical values of people in the pictures according to a human face appearance identification algorithm, and further obtaining representation values of the age classification numerical values of all the people in the pictures;
02-traversing all pictures in the image-text annual report, identifying smile grading values of characters in the pictures according to a facial expression identification algorithm, and further obtaining representation values of the smile grading values of all the characters in the pictures;
03-traversing all pictures in the image-text annual report, identifying the image quality grading numerical values of the pictures according to an image quality identification algorithm, and further obtaining the representation values of the image quality grading numerical values of all the pictures in the pictures;
04-calibrating the emotion of the image-text annual newspaper according to the obtained representation values of the age grading numerical values, the smile grading numerical values and the image quality grading numerical values of all the pictures, wherein the calibration contents comprise positive, negative, upward trend and downward trend.
The sequence of the steps 01-03 allows the replacement of the steps one after the other, and the sequence of the steps can be almost ignored in the electronic equipment; the human face appearance recognition algorithm, the human face expression recognition algorithm and the picture quality recognition algorithm can adopt the existing algorithms stored in Baidu cloud, Tencent cloud, Google cloud or Ariicloud, and the calling can relate to partial payment protocols and also can be used for free or can modify the existing algorithms in the industry.
Generally, if the age rating value x is relatively centered, the higher the smile rating value y, the higher the quality rating value z, and the positive sentiment is calibrated. More complicated here is that the calibration will use a function F (x, y, z) to calculate the result of such calibration.
Second embodiment
As a preferred embodiment, further comprising the steps of: and acquiring the emotion calibration result of the image-text annual report of the historical year to obtain the upward trend or the downward trend in the calibration content.
Third embodiment
As a preferred embodiment, the picture quality identification algorithm takes into account one or more of the following criteria: definition, saturation, brightness, contrast, and converting the index into a data model for calculation of the algorithm.
Fourth embodiment
As a preferred embodiment, the human face appearance recognition algorithm extracts the characteristics of eyes, mouth corners, eyebrows, skins and chin of a human face in a picture and compares the characteristics with the characteristics of a plurality of levels of standard human faces with preset age spans respectively, the level of the age span with the highest similarity is obtained after weighting, the age grading numerical value of the picture is determined, and the arithmetic mean of the age grading numerical values of all pictures is used as the representation value of the age grading numerical values of all people in the picture-text annual newspaper;
and the picture quality identification algorithm extracts the indexes of each picture in the picture-text annual report, constructs a data model to calculate the picture quality grading value of each picture, and takes the arithmetic mean value of the picture quality grading values of all the pictures as the representation value of the picture quality grading values of all the pictures in the picture-text annual report.
Referring to fig. 2, fig. 2 is a schematic diagram of the composition of the image-text annual newspaper emotion calibration system of the present invention. And the image-text annual newspaper emotion calibration system 0 is positioned in the electronic equipment. The system comprises the following units:
the picture scanning and separating reading unit 1 is used for acquiring the image-text content in the annual newspaper page by page and separating each picture for acquiring the subsequent numerical information of each picture;
the representative value acquiring unit 2 of the age classification numerical value is used for traversing all pictures in the image-text annual report, identifying the age classification numerical value of the figures in the pictures according to a face appearance identification algorithm, and further obtaining the representative value of the age classification numerical value of all the figures in the pictures;
the representative value acquiring unit 3 of the smile classification numerical value is used for traversing all pictures in the image-text annual report, identifying the smile classification numerical value of the figures in the pictures according to a facial expression identification algorithm, and further obtaining the representative value of the smile classification numerical value of all the figures in the pictures;
the representation value acquisition unit 4 of the image quality grading numerical value is used for traversing all the pictures in the image-text annual report, identifying the image quality grading numerical value of the pictures according to a picture image quality identification algorithm, and further obtaining the representation values of the image quality grading numerical values of all the pictures in the pictures;
the image-text annual newspaper emotion calibrating unit 5 is used for calibrating the emotion of the image-text annual newspaper according to the obtained characteristic values of the age grading numerical values, the smile grading numerical values and the image quality grading numerical values of all the pictures, and the calibrating content comprises positive, negative, upward trend and downward trend;
and the visual display unit 6 is used for displaying the result of the calibration content.
The picture scanning and separating reading unit 1 is used for scanning and reading the image-text annual newspaper of the paper and separating the image-text annual newspaper into effective pictures. Furthermore, an electronic version of the yearbook is provided, in which an automated scanning and separate reading can be carried out for subsequent units 2 to 4.
Corresponding to the second embodiment of the method, the method further comprises a historical data acquisition and storage unit, which is used for acquiring the emotion calibration result of the image-text annual report of the historical year so as to obtain the upward trend or the downward trend in the calibration content.
In accordance with a third embodiment of the method, the picture quality identification algorithm in the unit for obtaining the characterization value of the value of quality classification takes one or more of the following criteria into consideration: definition, saturation, brightness, contrast, and converting the index into a data model for calculation of the algorithm.
Corresponding to the fourth embodiment of the method, wherein, the face appearance recognition algorithm in the representative value acquisition unit of the age classification numerical value extracts the characteristics of the eyes, the mouth corners, the eyebrows, the skins and the chin of the face in the picture to be respectively compared with the characteristics of a plurality of levels of standard faces with preset age spans, the level of the age span with the highest similarity is obtained after weighting, the age classification numerical value of the picture is determined, and the arithmetic average value of the age classification numerical values of all the pictures is used as the representative value of the age classification numerical values of all the people in the image-text annual newspaper; and the image quality identification algorithm in the representation value acquisition unit of the image quality grading numerical value extracts the indexes of each image in the image annual report, constructs a data model to calculate the image quality grading numerical value of each image, and takes the arithmetic mean value of the image quality grading numerical values of all the images as the representation values of the image quality grading numerical values of all the images in the image annual report.
For the embodiment of the method and system, it was actually developed as an electronic device having an application program, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the teletext emotion marking method as described above.
When the internal evaluation or the acceptance of the school is carried out, the application method of the image-text annual newspaper emotion calibration system in the electronic equipment is adopted for the teaching quality evaluation of the school.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention , and equivalent substitutions or changes according to the technical solution of the present invention and the inventive concept thereof should be covered by the scope of the present invention.
Claims (10)
1. A method for calibrating emotion of image-text annual newspaper is applied to electronic equipment and is characterized by comprising the following steps:
traversing all pictures in the image-text annual report, identifying age classification numerical values of people in the pictures according to a human face appearance identification algorithm, and further obtaining representation values of the age classification numerical values of all the people in the pictures;
traversing all pictures in the image-text annual report, identifying smile grading values of characters in the pictures according to a facial expression identification algorithm, and further obtaining representation values of the smile grading values of all the characters in the pictures;
traversing all pictures in the image-text annual report, identifying the image quality grading numerical value of the pictures according to an image quality identification algorithm, and further obtaining the representation value of the image quality grading numerical value of all the pictures in the pictures;
and calibrating the emotion of the image-text annual newspaper according to the obtained representative values of the age grading numerical values, the smile grading numerical values and the image quality grading numerical values of all the pictures, wherein the calibration contents comprise positive, negative, upward trend and downward trend.
2. The method for calibrating emotion of teletext according to claim 1, further comprising the steps of: and acquiring the emotion calibration result of the image-text annual report of the historical year to obtain the upward trend or the downward trend in the calibration content.
3. The method for emotion rating of yearbook newspaper as claimed in claim 2, wherein the picture quality recognition algorithm includes one or more of the following indicators: definition, saturation, brightness, contrast, and converting the index into a data model for calculation of the algorithm.
4. The emotion marking method for the image-text annual newspaper as recited in claim 3, wherein the human face appearance recognition algorithm extracts the characteristics of the eyes, the mouth corners, the eyebrows, the skins and the chin of the human face in the image, compares the characteristics with the characteristics of a plurality of levels of standard human faces with preset age spans respectively, obtains the level of the age span with the highest similarity after weighting, determines the age grading numerical value of the image, and takes the arithmetic average of the age grading numerical values of all the images as the representation value of the age grading numerical value of all the people in the image-text annual newspaper; the image quality identification algorithm extracts the indexes of each image in the image annual report, constructs a data model to calculate the image quality grading value of each image, and takes the arithmetic mean value of the image quality grading values of all the images as the representation value of the image quality grading values of all the images in the image annual report.
5. An emotion marking system for a teletext according to claim 1, applied to an electronic device, comprising:
the picture scanning and separating reading unit is used for acquiring the image-text content in the annual newspaper page by page and separating each picture for acquiring the subsequent numerical information of each picture;
the representative value acquisition unit of the age classification numerical value is used for traversing all pictures in the image-text annual report, identifying the age classification numerical value of the figures in the pictures according to a face appearance identification algorithm, and further obtaining the representative value of the age classification numerical value of all the figures in the pictures;
the representative value acquisition unit of the smile grading numerical value is used for traversing all pictures in the image-text annual report, identifying the smile grading numerical value of the figures in the pictures according to a facial expression identification algorithm and further obtaining the representative value of the smile grading numerical value of all the figures in the pictures;
the characteristic value acquisition unit of the image quality grading numerical value is used for traversing all the pictures in the image-text annual report, identifying the image quality grading numerical value of the pictures according to a picture image quality identification algorithm and further obtaining the characteristic value of the image quality grading numerical value of all the pictures in the pictures;
the image-text annual newspaper emotion calibrating unit is used for calibrating the emotion of the image-text annual newspaper according to the obtained characteristic values of the age grading numerical values, the smile grading numerical values and the image quality grading numerical values of all the pictures, and the calibrating content comprises positive, negative, upward trend and downward trend;
and the visual display unit is used for displaying the result of the calibration content.
6. The system for emotion rating of teletext according to claim 5, further comprising:
and the historical data acquisition and storage unit is used for acquiring the emotion calibration result of the image-text annual report of the historical year so as to obtain the upward trend or the downward trend in the calibration content.
7. The system according to claim 6, wherein the picture quality identification algorithm in the representation value obtaining unit of the image quality rating value includes one or more of the following indicators: definition, saturation, brightness, contrast, and converting the index into a data model for calculation of the algorithm.
8. The system for emotion rating of teletext according to claim 7, wherein,
the human face appearance recognition algorithm in the representative value acquisition unit of the age classification numerical value extracts the characteristics of eyes, mouth corners, eyebrows, skins and chin of a human face in the picture to be respectively compared with the characteristics of a plurality of levels of standard human faces with preset age spans, the level of the age span with the highest similarity is obtained after weighting, the age classification numerical value of the picture is determined, and the arithmetic mean value of the age classification numerical values of all the pictures is used as the representative value of the age classification numerical values of all the people in the image-text annual newspaper;
and the picture quality identification algorithm in the representative value acquisition unit of the picture quality grading numerical value extracts the indexes of each picture in the picture annual report, constructs a data model to calculate the picture quality grading numerical value of each picture, and takes the arithmetic mean of the picture quality grading numerical values of all the pictures as the representative values of the picture quality grading numerical values of all the pictures in the picture annual report.
9. An electronic device, comprising: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the teletext emotion marking method according to any one of claims 1 to 4.
10. Use of the method for emotion rating of teletext according to any one of claims 1 to 5 for school education quality assessment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010136298.4A CN111310709A (en) | 2020-03-02 | 2020-03-02 | Image-text annual newspaper emotion calibration method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010136298.4A CN111310709A (en) | 2020-03-02 | 2020-03-02 | Image-text annual newspaper emotion calibration method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111310709A true CN111310709A (en) | 2020-06-19 |
Family
ID=71147867
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010136298.4A Pending CN111310709A (en) | 2020-03-02 | 2020-03-02 | Image-text annual newspaper emotion calibration method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111310709A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107423441A (en) * | 2017-08-07 | 2017-12-01 | 珠海格力电器股份有限公司 | A kind of picture correlating method and its device, electronic equipment |
| CN108388544A (en) * | 2018-02-10 | 2018-08-10 | 桂林电子科技大学 | A kind of picture and text fusion microblog emotional analysis method based on deep learning |
| CN108764268A (en) * | 2018-04-02 | 2018-11-06 | 华南理工大学 | A kind of multi-modal emotion identification method of picture and text based on deep learning |
| CN108876061A (en) * | 2018-08-01 | 2018-11-23 | 深圳大学 | Predict method, apparatus, electronic equipment and the storage medium of stock trend |
| CN109558833A (en) * | 2018-11-28 | 2019-04-02 | 厦门市巨龙信息科技有限公司 | A kind of face recognition algorithms evaluating method and device |
| WO2019109526A1 (en) * | 2017-12-06 | 2019-06-13 | 平安科技（深圳）有限公司 | Method and device for age recognition of face image, storage medium |
| CN110162774A (en) * | 2019-02-22 | 2019-08-23 | 北京捷风数据技术有限公司 | A kind of automation the emotion of news scaling method and device based on financial market market |
| CN110838102A (en) * | 2019-10-24 | 2020-02-25 | 开望(杭州)科技有限公司 | Intelligent image uploading method |
-
2020
- 2020-03-02 CN CN202010136298.4A patent/CN111310709A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107423441A (en) * | 2017-08-07 | 2017-12-01 | 珠海格力电器股份有限公司 | A kind of picture correlating method and its device, electronic equipment |
| WO2019109526A1 (en) * | 2017-12-06 | 2019-06-13 | 平安科技（深圳）有限公司 | Method and device for age recognition of face image, storage medium |
| CN108388544A (en) * | 2018-02-10 | 2018-08-10 | 桂林电子科技大学 | A kind of picture and text fusion microblog emotional analysis method based on deep learning |
| CN108764268A (en) * | 2018-04-02 | 2018-11-06 | 华南理工大学 | A kind of multi-modal emotion identification method of picture and text based on deep learning |
| CN108876061A (en) * | 2018-08-01 | 2018-11-23 | 深圳大学 | Predict method, apparatus, electronic equipment and the storage medium of stock trend |
| CN109558833A (en) * | 2018-11-28 | 2019-04-02 | 厦门市巨龙信息科技有限公司 | A kind of face recognition algorithms evaluating method and device |
| CN110162774A (en) * | 2019-02-22 | 2019-08-23 | 北京捷风数据技术有限公司 | A kind of automation the emotion of news scaling method and device based on financial market market |
| CN110838102A (en) * | 2019-10-24 | 2020-02-25 | 开望(杭州)科技有限公司 | Intelligent image uploading method |
Non-Patent Citations (3)
| Title |
|---|
| 凌海彬 等: "多特征融合的图文微博情感分析", 《计算机应用研究》 * |
| 凌海彬 等: "多特征融合的图文微博情感分析", 《计算机应用研究》, 6 June 2019 (2019-06-06), pages 1 - 7 * |
| 叶继华 等: "人脸表情识别综述", 《数据采集与处理》, vol. 35, no. 1, pages 175 - 182 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104143094B (en) | A kind of paper automatic marking processing method and system without answering card | |
| Cromey | Avoiding twisted pixels: ethical guidelines for the appropriate use and manipulation of scientific digital images | |
| Furness | The use of digital images in pathology | |
| CN110597806A (en) | Wrong question set generation and answer statistics system and method based on reading and amending identification | |
| CN110909035A (en) | Personalized review question set generation method and device, electronic equipment and storage medium | |
| CN110263651B (en) | Method, device and storage medium for assisting in on-line reading test questions | |
| CN108876195A (en) | A kind of intelligentized teachers ' teaching quality evaluating system | |
| CN110555830A (en) | Deep neural network skin detection method based on deep Labv3+ | |
| CN112381099A (en) | Question recording system based on digital education resources | |
| CN111062260A (en) | Automatic generation method of facial cosmetic recommendation scheme | |
| CN116862166A (en) | Post matching method, device, equipment and computer storage medium | |
| JP7082333B2 (en) | Question automatic generation program and question automatic generation device | |
| CN114663904A (en) | PDF document layout detection method, device, equipment and medium | |
| Yazdanmehr et al. | Design and Application of a'Textbook Visual Effects' Evaluation Checklist. | |
| CN108847284A (en) | The human-body biological age calculates apparatus and system | |
| CN108197297A (en) | Method for exhibiting data and system | |
| Smith et al. | Improving the communication function of published accounting statements | |
| CN111310709A (en) | Image-text annual newspaper emotion calibration method and system | |
| CN112396897A (en) | Teaching system | |
| CN110458751B (en) | Face replacement method, device and medium based on Guangdong play pictures | |
| JP7147183B2 (en) | Information processing device, information processing system, and program | |
| CN110298236A (en) | A kind of braille automatic distinguishing method for image and system based on deep learning | |
| CN110955727B (en) | Automatic student homework recording system | |
| US20180114093A1 (en) | Data analysis system, method for controlling data analysis system, and recording medium | |
| CN114463816A (en) | Satisfaction determining method and device, processor and electronic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200619 |
|
| RJ01 | Rejection of invention patent application after publication |