CN105828026A - Reading fatigue intelligent detection system based on educational psychology and reading fatigue intelligent detection method thereof - Google Patents
Reading fatigue intelligent detection system based on educational psychology and reading fatigue intelligent detection method thereof Download PDFInfo
- Publication number
- CN105828026A CN105828026A CN201610098302.6A CN201610098302A CN105828026A CN 105828026 A CN105828026 A CN 105828026A CN 201610098302 A CN201610098302 A CN 201610098302A CN 105828026 A CN105828026 A CN 105828026A
- Authority
- CN
- China
- Prior art keywords
- video
- module
- face
- fatigue
- reading fatigue
- 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
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- 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
Abstract
The invention relates to the technical field of fatigue detection, and particularly relates to a reading fatigue intelligent detection system based on the educational psychology. The system comprises a vision detection system, a fuzzy neural network system and a microcomputer system. The vision detection system and the fuzzy neural network system are connected with the microcomputer system. The fuzzy neural network system comprises a DSP processor which is connected with a CPLD and an FPGA. The CPLD and the FPGA are respectively connected with a video A/D and a video D/A. The video A/D inputs video information through an infrared CCD and a common CCD. The video A/D converter transmits image data to the DSP processor and the video D/A. The video D/A performs image outputting. The DSP processor is connected with a result display and alarm mechanism. The vision detection system comprises an image processing module which is connected with an image acquisition module, a power supply management module, an emulator, a voice prompting module and an expanded storage module.
Description
Technical field
The present invention relates to fatigue detecting technology field, be specifically related to a kind of reading fatigue intelligent checking system based on pedagogical psychology and method.
Background technology
E-learning is the same with other activities of people, all can cause physical and mental consumption, thus show health and emotional state psychological nervous or tired out." learning fatigue " is the key concept in psychology and pedagogy.Generally speaking, learning fatigue refers to, due to long continuous learning, create indolent and listless at aspects such as physiology and psychology, cause the learning efficiency to decline, even up to can not continue the situation of study.
Learning fatigue has many forms.Learning fatigue mainly can divide into the physiological fatigue i.e. fatigue of health and the psychological fatigue i.e. fatigue of brain.Some fatigue phenomenon can by main body perception, also some learning fatigue phenomenon not by main body perception by other people perception.The observation of other people the external behavior by learning learner, draws the conclusion of " learner entrance learning fatigue ".Under normal circumstances, physical fatigue is easily discovered；But psychological fatigue is often difficult to be discovered, causing learner memory and intelligential weaken, attention is difficult to concentrate, and reaction is slowed down etc..
At present, at fatigue driving detection field, some scholars attempt using sensing technology, signal detection and acquisition technique or human facial expression recognition technology, carry out the identification of driver fatigue state, prediction and tired intervention, the predominantly detection of physiological fatigue.
In e-learning field, some scholars attempt, from the angle improving design of Internet course teaching, to promote the affective interaction under Network Study Environment, can reduce learner to a certain extent and enter the probability of learning fatigue；Some scholars utilize the chat tools such as multimedia technology, BBS even QQ to promote the affective interaction in Network Study Environment, serve and certain prevent learning fatigue effect.These researchs focus primarily upon identification or the detection of physiological fatigue, are not concerned with the complexity of learning fatigue, and it comprises physiological fatigue and the fatigue of two kinds of levels of psychological fatigue, and research learning fatigue state being carried out to initiative recognition and intervention is the rarest.
Existing from design of Internet course teaching, utilize the chat tools such as multimedia technology, BBS even QQ to promote the method for affective interaction Network Study Environment, simply prevent learning fatigue from one-sided reinforcement affective interaction, still whether fatigue state can not be entered by initiative recognition learner, do not distinguish discussion physiological fatigue and psychological fatigue, there is no intervening measure yet.
The most domestic fatigue detecting mostly uses single fatigue characteristic to carry out tired identification, is seldom organically combined by multiple fatigue characteristics, and this makes misclassification rate high.
Summary of the invention
For problem above, the invention provides a kind of reading fatigue intelligent checking system based on pedagogical psychology and method, use vision detection system, the combination of Fuzzy Neural Network System, by multiple damage parameters are extracted, driver fatigue situation is detected, there is preferable effect, use contactless, the PERCLOS fatigue detection method of passive vision, image processing techniques is used to extract the fatigue characteristic of eye for the image obtained, eyes damage will not be caused, the problem in technical background can be effectively solved.
To achieve these goals, the technical solution used in the present invention is as follows: a kind of reading fatigue intelligent checking system based on pedagogical psychology, including vision detection system, Fuzzy Neural Network System and microsystem, described vision detection system, Fuzzy Neural Network System are connected to microsystem；Described Fuzzy Neural Network System includes dsp processor, described dsp processor connects CPLD and FPGA, described CPLD and FPGA is connected to video a/d and video d/a, described video a/d passes through infrared CCD and common CCD input video information, view data is transmitted to dsp processor and video d/a by described video a/d converter, described video d/a carries out image output, and described dsp processor connects has result to show and alarm mechanism；Described vision detection system includes image processing module, and described image processing module connects image capture module, power management module, emulator, voice reminder module and extension storage module.
Further, described dsp processor uses TMS320DM642CPU.
Further, described image processing module uses TMS230DM643CPU.
Further, described image capture module is by CCD camera input video information, it is converted into BT by TVP5150 Video Decoder, transmitting the VPSS front end to TMS230DM643CPU after the standard digital video signal digital signal of 656 forms, described TVP5150 is configured by the iic bus of standard.
Further, the expansion of described extension storage module includes the SDRAM memory of 256Mb and the flash storage of 128Mb.
Further, described power management module uses+5V single supply.
Further, described voice reminder module is made up of ACI33 stereophonic encoder and speaker, and described ACI33 stereophonic encoder is connected with TMS230DM643CPU and speaker.
Additionally the present invention have also been devised a kind of reading fatigue intelligent detecting method based on pedagogical psychology, identical information source is obtained by vision detection system and Fuzzy Neural Network System, face is detected by CCD, after face being detected, integrated integral projecting method based on Mask location eyes are carried out at human face region, with the ratio 80% shared by the time of eyes closed in 1min for tired separation, obtain several 1 minute interior proportional curve；And comprehensively analyzed by microsystem.
Further, the process that realizes of Face datection is: utilize the cluster of the colour of skin to split the area of skin color obtaining in image, then White lnterfere fritter is removed by morphology opening operation, finally detect the structural feature locating human face of face, reject non-face area of skin color by Face datection, reduce the scope of search eyes.
Further, the processing procedure of described Mask integrated integral projecting method is to generate Mask by the bianry image of face, and is projected the longitudinal register carrying out eyes by level comprehensive, by vertical comprehensive projection, removes top eyes the window's position.
Beneficial effects of the present invention:
The present invention uses the combination of vision detection system, Fuzzy Neural Network System, by multiple damage parameters are extracted, driver fatigue situation is detected, there is preferable effect, use contactless, the PERCLOS fatigue detection method of passive vision, use image processing techniques to extract the fatigue characteristic of eye for the image obtained, eyes will not be caused damage.
Accompanying drawing explanation
Fig. 1 is Fuzzy Neural Network System structural representation of the present invention.
Fig. 2 is vision detection system structural representation of the present invention.
Fig. 3 is the schematic diagram that in the embodiment of the present invention, Fuzzy Neural Network System carries out tired identification.
Detailed description of the invention
In order to make the purpose of the present invention, technical scheme and advantage clearer, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
Embodiment: as depicted in figs. 1 and 2, a kind of reading fatigue intelligent checking system based on pedagogical psychology, including vision detection system, Fuzzy Neural Network System and microsystem, described vision detection system, Fuzzy Neural Network System are connected to microsystem；Described Fuzzy Neural Network System includes dsp processor, described dsp processor connects CPLD and FPGA, described CPLD and FPGA is connected to video a/d and video d/a, described video a/d passes through infrared CCD and common CCD input video information, view data is transmitted to dsp processor and video d/a by described video a/d converter, described video d/a carries out image output, and described dsp processor connects has result to show and alarm mechanism；Described vision detection system includes image processing module, and described image processing module connects image capture module, power management module, emulator, voice reminder module and extension storage module.
Further, described dsp processor uses TMS320DM642CPU.
Further, described image processing module uses TMS230DM643CPU.
Further, described image capture module is by CCD camera input video information, it is converted into BT by TVP5150 Video Decoder, transmitting the VPSS front end to TMS230DM643CPU after the standard digital video signal digital signal of 656 forms, described TVP5150 is configured by the iic bus of standard.
Further, the expansion of described extension storage module includes the SDRAM memory of 256Mb and the flash storage of 128Mb.
Further, described power management module uses+5V single supply.
Further, described voice reminder module is made up of ACI33 stereophonic encoder and speaker, and described ACI33 stereophonic encoder is connected with TMS230DM643CPU and speaker.
Additionally the present invention have also been devised a kind of reading fatigue intelligent detecting method based on pedagogical psychology, identical information source is obtained by vision detection system and Fuzzy Neural Network System, face is detected by CCD, after face being detected, integrated integral projecting method based on Mask location eyes are carried out at human face region, with the ratio 80% shared by the time of eyes closed in 1min for tired separation, obtain several 1 minute interior proportional curve；And comprehensively analyzed by microsystem.
Further, the process that realizes of Face datection is: utilize the cluster of the colour of skin to split the area of skin color obtaining in image, then White lnterfere fritter is removed by morphology opening operation, finally detect the structural feature locating human face of face, reject non-face area of skin color by Face datection, reduce the scope of search eyes.
Further, the processing procedure of described Mask integrated integral projecting method is to generate Mask by the bianry image of face, and is projected the longitudinal register carrying out eyes by level comprehensive, by vertical comprehensive projection, removes top eyes the window's position.
TMS230DM643 of the present invention is the good digital Media Processor for multi-media processing of the up-to-date release of TI company, possesses advantage in image processing method face.From the point of view of the requirement of real-time meeting driving fatigue detecting system, people nictation the most per minute 10～15 times, along with the number of times increasing nictation of degree of fatigue also can raise.To catch the closing course of eyes well, sampling to video image must reach more than 10 frames per second, this just requires that system must complete the whole process to a two field picture in 100ms, the main clock frequency of TMS230DM643 is 600MHz, there is the operational performance of 4800MIPS, it is possible to meet the requirement of real time processed images well.
TMS230DM643 sets up on the basis of C64x+ core, in conjunction with the system structure of enhancement mode DSP core Yu up-to-date video processing subsystem, uses third generation high performance very long coding line structure VelociTI.C64x+ nuclear phase improves 20% than C64 core cycle performance, and code size reduces 20%～30%, further increases the execution efficiency of code.And C64x+ core have can the high-speed controller of flexible operating, superior parallel data processing ability, the general register of 64 32 word lengths and 8 function calculating unit the most independent, the operating guidance of 8 function calculating unit that user can provide specially according to TI company, improves it and processes video and the performance of image.TMS230DM643 is based on third generation high performance very long coding line structure VelociTI and hardware floating so that it is is at best able to parallel processing 8 instruction an instruction cycle, further increases processing speed.The built-in video processing subsystem of TMS230DM643, there are two configurable Video processing front ends and process rear end, the video/image form that system needs can be obtained neatly such that it is able to realize the seamless link between Video Decoder, imageing sensor etc. by reasonably configuration.Meanwhile, TMS230DM643 is also integrated with abundant ancillary equipment and interface, provides convenience condition for building driving fatigue detecting system.
The on-chip memory of TMS230DM643 of the present invention is divided into the L2 of L1P, 128KbL1D and the 2Mb of 128Kb, and provides the outside memory interface of 64b.If the resolution selected when gathering image is 576 × 720, the gray level of each image sampling point is 8b, then the memory space shared by a two field picture is about 0.4Mb.The intermediate object program that image obtains in processing procedure is the most, stores a two field picture and relative centre about needs 3Mb, uses table tennis cache way to need to store two two field pictures simultaneously.System extends SDRAM memory and the flash storage of 128Mb of 256Mb by outside memory interface, can fully meet the requirement of system storage.TMS230DM643 controls data transmission by strengthening the direct memory access controller of 64 passages, and data transmission can be carried out between on-chip memory, chip external memory and peripheral hardware, and 64 passage DMA transfer of enhancing can provide the bandwidth duration of more than 2Gbps.
Image capture module of the present invention is made up of CCD camera and TVP5150 Video Decoder.It is analog video signal that CCD camera gathers the driving video image (comprising human face region) of driver, and video formats is generally divided into pal mode and TSC-system formula.Analog video signal transmits the VPSS front end to TMS230DM643 after standard digital video signal (YUV4:2:2) digital signal that TVP5150 is converted into BT.656 form.TVP5150 is configured by the iic bus of standard, and its rate of data signalling reaches as high as 400Kbps.Simultaneously as TMS230DM643 supports the standard digital video signal input of BT.656 form, TVP5150 Yu TMS230DM643 achieves seamless link.
The cluster detection face of the imagery exploitation face complexion that CCD camera is first collected by driving fatigue detection algorithm of the present invention, if continuing 3s to be not detected by face, algorithm is judged as that face lacks.After face being detected, carry out integrated integral projecting method based on Mask location eyes at human face region, it is thus achieved that after eyes window, then extract the closure foundation as PERCLOS evaluation and test fatigue of eyes.If calculated PERCLOS value is more than threshold value, algorithm is judged as driving fatigue, otherwise continues next frame image is carried out same treatment.
PERCLOS algorithm of the present invention is Fu Jiliya university of U.S. Wierwille professor, later Highway Administration of the United States Federal and National Highway Traffic safety management office by simulation experiment Integrated comparative nine kinds of fatigue detecting indexs, consistent recommend using PERCLOS as the feasible method of prediction automobile driver driving fatigue.PERCLOS has three evaluation criterions: P70 standard, P80 standard and EM (EYEMEAS) standard, the experiment of NHTSA shows that P80 standard (time at least closing 80% with eyes accounts for the percentage rate of special time as evaluation index) and degree of fatigue have more preferable dependency.
As shown in Figure 3, Fuzzy Neural Network System of the present invention is 4 the fatigue characteristic parameters extracted to be sent into fuzzy neural network carry out tired identification, the parameter of input has 4, the i.e. ground floor of neutral net has 4 nodes, it exports only one of which, and output valve just represents level of fatigue, and this network is divided into 5 layers, there are 4 input nodes, 1 output node；Ground floor is input layer, and each node of this layer is directly connected with each component xi of input vector, it play by input value X=(x1, x2 ..., xn) T is sent to the effect of next layer, the nodes of this layer is n；The second layer is obfuscation layer, it is used for the degree of membership calculating input sample relative to each fuzzy class, second layer node total number is m1+m2+ ...+mn, one linguistic variable value of each node on behalf, and its effect is the degree of membership calculating each input component for each fuzzy set of this component；Third layer is regular collection layer, one fuzzy rule of each node on behalf, it is used for mating fuzzy rule former piece, calculate the relevance grade of every rule, the node total number of third layer is: m1 m2 ... mn, equal to possible rule sum, in order to comprise all possible rule, being full connection between third layer and the second layer, its node is output as the input variable relevance grade for each rule of whole network；4th layer of effect is to realize normalization to calculate, and its nodes is identical with third layer, is also that each node of the 4th layer is corresponding with certain node of third layer, and its output is to input the summation divided by the output of third layer all nodes；Layer 5 is output layer, it is achieved be that sharpening calculates, layer 5 only one of which node, its each node with the 4th layer has and is connected.
Based on above-mentioned, the present invention uses the combination of vision detection system, Fuzzy Neural Network System, by multiple damage parameters are extracted, driver fatigue situation is detected, there is preferable effect, use contactless, the PERCLOS fatigue detection method of passive vision, use image processing techniques to extract the fatigue characteristic of eye for the image obtained, eyes will not be caused damage.
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all any amendment, equivalent and improvement etc. made within the spirit and principles in the present invention, should be included within the scope of the present invention.
Claims (10)
1. a reading fatigue intelligent checking system based on pedagogical psychology, it is characterised in that: include that vision detection system, Fuzzy Neural Network System and microsystem, described vision detection system, Fuzzy Neural Network System are connected to microsystem；
Described Fuzzy Neural Network System includes dsp processor, described dsp processor connects CPLD and FPGA, described CPLD and FPGA is connected to video a/d and video d/a, described video a/d passes through infrared CCD and common CCD input video information, view data is transmitted to dsp processor and video d/a by described video a/d converter, described video d/a carries out image output, and described dsp processor connects has result to show and alarm mechanism；
Described vision detection system includes image processing module, and described image processing module connects image capture module, power management module, emulator, voice reminder module and extension storage module.
A kind of reading fatigue intelligent checking system based on pedagogical psychology the most according to claim 1, it is characterised in that: described dsp processor uses TMS320DM642CPU.
A kind of reading fatigue intelligent checking system based on pedagogical psychology the most according to claim 1, it is characterised in that: described image processing module uses TMS230DM643CPU.
A kind of reading fatigue intelligent checking system based on pedagogical psychology the most according to claim 1, it is characterized in that: described image capture module is by CCD camera input video information, it is converted into BT by TVP5150 Video Decoder, transmitting the VPSS front end to TMS230DM643CPU after the standard digital video signal digital signal of 656 forms, described TVP5150 is configured by the iic bus of standard.
A kind of reading fatigue intelligent checking system based on pedagogical psychology the most according to claim 1, it is characterised in that: the expansion of described extension storage module includes the SDRAM memory of 256Mb and the flash storage of 128Mb.
A kind of reading fatigue intelligent checking system based on pedagogical psychology the most according to claim 1, it is characterised in that: described power management module uses+5V single supply.
A kind of reading fatigue intelligent checking system based on pedagogical psychology the most according to claim 1, it is characterized in that: described voice reminder module is made up of ACI33 stereophonic encoder and speaker, described ACI33 stereophonic encoder is connected with TMS230DM643CPU and speaker.
8. a reading fatigue intelligent detecting method based on pedagogical psychology, it is characterized in that: obtain identical information source by vision detection system and Fuzzy Neural Network System, face is detected by CCD, after face being detected, integrated integral projecting method based on Mask location eyes are carried out at human face region, with the ratio 80% shared by the time of eyes closed in 1min for tired separation, obtain several 1 minute interior proportional curve；And comprehensively analyzed by microsystem.
A kind of reading fatigue intelligent detecting method based on pedagogical psychology the most according to claim 8, it is characterized in that: the process that realizes of Face datection is: utilize the cluster of the colour of skin to split the area of skin color obtaining in image, then White lnterfere fritter is removed by morphology opening operation, finally detect the structural feature locating human face of face, reject non-face area of skin color by Face datection, reduce the scope of search eyes.
A kind of reading fatigue intelligent detecting method based on pedagogical psychology the most according to claim 8, it is characterized in that: the processing procedure of described Mask integrated integral projecting method is to generate Mask by the bianry image of face, and the longitudinal register of eyes is carried out by level comprehensive projection, by vertical comprehensive projection, go to push up eyes the window's position.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610098302.6A CN105828026A (en) | 2016-02-23 | 2016-02-23 | Reading fatigue intelligent detection system based on educational psychology and reading fatigue intelligent detection method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610098302.6A CN105828026A (en) | 2016-02-23 | 2016-02-23 | Reading fatigue intelligent detection system based on educational psychology and reading fatigue intelligent detection method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105828026A true CN105828026A (en) | 2016-08-03 |
Family
ID=56987416
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610098302.6A Pending CN105828026A (en) | 2016-02-23 | 2016-02-23 | Reading fatigue intelligent detection system based on educational psychology and reading fatigue intelligent detection method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105828026A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889955A (en) * | 2019-11-29 | 2020-03-17 | 上海掌门科技有限公司 | Method and equipment for reminding user of rest when user reads |
| CN113721529A (en) * | 2021-09-03 | 2021-11-30 | 成都理工大学 | Data acquisition system based on FPGA |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101746269A (en) * | 2010-01-08 | 2010-06-23 | 东南大学 | Fatigue driving fusion detection method based on soft computing |
| CN104537806A (en) * | 2014-11-11 | 2015-04-22 | 奇瑞汽车股份有限公司 | Camera based real-time driving fatigue detection system |
-
2016
- 2016-02-23 CN CN201610098302.6A patent/CN105828026A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101746269A (en) * | 2010-01-08 | 2010-06-23 | 东南大学 | Fatigue driving fusion detection method based on soft computing |
| CN104537806A (en) * | 2014-11-11 | 2015-04-22 | 奇瑞汽车股份有限公司 | Camera based real-time driving fatigue detection system |
Non-Patent Citations (2)
| Title |
|---|
| 李志春等: "模糊神经网络在驾驶员疲劳检测中的应用", 《江苏大学学报（自然科学版）》 * |
| 赵有灵等: "基于TMS230DM643的驾驶疲劳实时视觉检测系统", 《计算机应用》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889955A (en) * | 2019-11-29 | 2020-03-17 | 上海掌门科技有限公司 | Method and equipment for reminding user of rest when user reads |
| CN113721529A (en) * | 2021-09-03 | 2021-11-30 | 成都理工大学 | Data acquisition system based on FPGA |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liao et al. | Deep facial spatiotemporal network for engagement prediction in online learning | |
| US11967414B2 (en) | Image recognition model training method and apparatus, and image recognition method, apparatus, and system | |
| Javeed et al. | Wearable sensors based exertion recognition using statistical features and random forest for physical healthcare monitoring | |
| Zhang et al. | Intelligent facial emotion recognition and semantic-based topic detection for a humanoid robot | |
| CN108182409A (en) | Biopsy method, device, equipment and storage medium | |
| CN107346629A (en) | A kind of intelligent blind reading method and intelligent blind reader system | |
| Huan et al. | Deep convolutional neural networks for classifying body constitution based on face image | |
| Shen et al. | Assessing learning engagement based on facial expression recognition in MOOC’s scenario | |
| CN104778466B (en) | A kind of image attention method for detecting area for combining a variety of context cues | |
| CN110414607A (en) | Classification method, device, equipment and the medium of capsule endoscope image | |
| Bu | Human motion gesture recognition algorithm in video based on convolutional neural features of training images | |
| CN108875586A (en) | A kind of functional limb rehabilitation training detection method based on depth image Yu skeleton data multiple features fusion | |
| Yahaya et al. | Gesture recognition intermediary robot for abnormality detection in human activities | |
| Jiang et al. | Rdfnet: A fast caries detection method incorporating transformer mechanism | |
| CN116503785A (en) | Natatorium supervision system and natatorium supervision method | |
| Memon | On assisted living of paralyzed persons through real-time eye features tracking and classification using Support Vector Machines | |
| Zhu | Pain expression recognition based on pLSA model | |
| Li et al. | Deep learning and improved HMM training algorithm and its analysis in facial expression recognition of sports athletes | |
| CN105828026A (en) | Reading fatigue intelligent detection system based on educational psychology and reading fatigue intelligent detection method thereof | |
| Sim et al. | Improving the accuracy of erroneous-plan recognition system for Activities of Daily Living | |
| Zhao et al. | Research and development of autism diagnosis information system based on deep convolution neural network and facial expression data | |
| CN116959733A (en) | Medical data analysis method, device, equipment and storage medium | |
| CN103366153A (en) | Semantic cognitive facial feature identification method | |
| CN116994695A (en) | Training method, device, equipment and storage medium of report generation model | |
| Guo et al. | Facial expression recognition: a review |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160803 |