CN110084883A - A method of it inducing brain activity and rebuilds face-image - Google Patents
A method of it inducing brain activity and rebuilds face-image Download PDFInfo
- Publication number
- CN110084883A CN110084883A CN201910298267.6A CN201910298267A CN110084883A CN 110084883 A CN110084883 A CN 110084883A CN 201910298267 A CN201910298267 A CN 201910298267A CN 110084883 A CN110084883 A CN 110084883A
- Authority
- CN
- China
- Prior art keywords
- image
- face
- brain activity
- function
- eigenface
- 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
- 230000007177 brain activity Effects 0.000 title claims abstract description 29
- 238000000034 method Methods 0.000 title claims abstract description 22
- 230000001939 inductive effect Effects 0.000 title claims description 7
- 239000011159 matrix material Substances 0.000 claims abstract description 18
- 238000012360 testing method Methods 0.000 claims abstract description 14
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000012937 correction Methods 0.000 claims abstract description 4
- 230000004886 head movement Effects 0.000 claims abstract description 4
- 238000010606 normalization Methods 0.000 claims abstract description 4
- 210000000887 face Anatomy 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 2
- 230000006698 induction Effects 0.000 abstract description 3
- 238000002599 functional magnetic resonance imaging Methods 0.000 abstract 1
- 210000005036 nerve Anatomy 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000003710 cerebral cortex Anatomy 0.000 description 1
- 230000001054 cortical effect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000002610 neuroimaging Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- 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
- G06V40/168—Feature extraction; Face representation
-
- 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
- G06V40/193—Preprocessing; Feature extraction
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Human Computer Interaction (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computer Graphics (AREA)
- Software Systems (AREA)
- Geometry (AREA)
- Ophthalmology & Optometry (AREA)
- Magnetic Resonance Imaging Apparatus (AREA)
Abstract
The invention discloses a kind of method that face-image is rebuild in induction brain activity, the method for the present invention are as follows: the face-image that n describes different faces is carried out PCA and obtains eigenface；After selecting test image, tester to carry out high resolution scanning using functional MRI when watching test image from face face-image, function image, structural images are obtained using the T2* weighting 2D gradin-echo with the repetition time；Slice timing, head movement correction are successively carried out to function image；Structural images are recorded on preprocessing function image；Then fused function image is normalized；Function image after normalization is re-sampled to 3 cubic millimeters of voxels；Brain activity is mapped to eigenface using partial least-square regression method, exports the prediction matrix of brain activity；The weight matrix defined and the prediction matrix of brain activity are when by generating eigenface come reconstruction image.The present invention can be efficiently used for realizing the reconstruction to tester's test image.
Description
Technical field
The present invention relates to a kind of methods that face-image is rebuild in induction brain activity, belong to information technology field.
Background technique
Nearest neuroimaging progress comes out visual experience from brain activity mode reconstruction.Although nerve weight
It is different to build complexity aspect in, but they are almost completely dependent on the view that vision inputs between early vision cortical activity
Nethike embrane mapping.However, subjective conscious information is not yet used as the more advanced cortical region of the main foundation of nerve reconstructive.
Summary of the invention
The present invention provides a kind of method that face-image is rebuild in induction brain activity, for passing through this method to tester
The image of test is rebuild.
The technical scheme is that a kind of method for inducing brain activity and rebuilding face-image, the method step is such as
Under:
It is special to be carried out PCA acquisition by S1, the face-image for collecting n description different faces for the face-image that n describes different faces
Levy face；
S2, it selects to want test image from the face face-image in step S1, tester utilizes function when watching test image
After energy magnetic resonance carries out high resolution scanning, the T2* weighting 2D gradin-echo with the repetition time is used to obtain
Image, structural images；Slice timing, head movement correction are successively carried out to function image, obtain preprocessing function image；It will knot
Composition picture is recorded on preprocessing function image, obtains fused function image；Then fused function image is carried out
Normalized, the function image after being normalized；Function image after normalization is re-sampled to 3 cubic millimeters of bodies
Element；Wherein, the specific beta value of each voxel is brain activity；
S3, the brain activity that step S2 is recorded is mapped to eigenface using partial least-square regression method, exports brain activity
Prediction matrix；
S4, the brain activity that the weight matrix that defines and step S3 are obtained when generating eigenface by step S1 prediction matrix come
Reconstruction image Xpred:
Xpred=Wtrain*Ypred
Wherein, WTrain is the weight matrix defined when generating eigenface by step S1, and Ypred is obtained by step S3
The prediction matrix of brain activity, Xpred indicate the test image rebuild.
The size of n face-image is the same in the step S1, and there are eyes and mouth feature in face-image.
The high-resolution refers to 1.0 × 1.0 × 1.0mm.
The beneficial effects of the present invention are: the present invention is analyzed using PCA for multiple facial images, the spy obtained for analysis
It is more excellent to levy face effect, it can be efficiently used for realizing to tester's test image in conjunction with partial least-square regression method
It rebuilds.
Detailed description of the invention
Fig. 1 is schematic process flow diagram of the present invention.
Specific embodiment
Embodiment 1: as shown in Figure 1, a kind of method for inducing brain activity and rebuilding face-image, the method step is such as
Under:
It is special to be carried out PCA acquisition by S1, the face-image for collecting n description different faces for the face-image that n describes different faces
Levy face；Wherein, the size of n face-image is the same, and there are eyes and mouth feature in face-image；
S2, test image is selected from the face face-image in step S1, tester utilizes function magnetic when watching test image
Resonance carry out high resolution scanning after, using with the repetition time T2* weighting 2D gradin-echo obtain function image,
Structural images；Slice timing, head movement correction are successively carried out to function image, obtain preprocessing function image；By structure chart
As being recorded on preprocessing function image, fused function image is obtained；Then normalizing is carried out to fused function image
Change processing, the function image after being normalized；Function image after normalization is re-sampled to 3 cubic millimeters of voxels；Its
In, each specific beta value of voxel is brain activity；The high-resolution refers to 1.0 × 1.0 × 1.0mm；
S3, the brain activity that step S2 is recorded is mapped to eigenface using partial least-square regression method, exports brain activity
Prediction matrix；
S4, the brain activity that the weight matrix that defines and step S3 are obtained when generating eigenface by step S1 prediction matrix come
Reconstruction image Xpred:
Xpred=Wtrain*Ypred
Wherein, WTrain is the weight matrix defined when generating eigenface by step S1, and Ypred is obtained by step S3
The prediction matrix of brain activity, Xpred indicate the test image rebuild.
Above in conjunction with attached drawing, the embodiment of the present invention is explained in detail, but the present invention is not limited to above-mentioned
Embodiment within the knowledge of a person skilled in the art can also be before not departing from present inventive concept
Put that various changes can be made.
Claims (3)
1. a kind of method for inducing brain activity and rebuilding face-image, it is characterised in that: the method comprises the following steps:
It is special to be carried out PCA acquisition by S1, the face-image for collecting n description different faces for the face-image that n describes different faces
Levy face；
S2, test image is selected from the face face-image in step S1, tester utilizes function magnetic when watching test image
Resonance carry out high resolution scanning after, using with the repetition time T2* weighting 2D gradin-echo obtain function image,
Structural images；Slice timing, head movement correction are successively carried out to function image, obtain preprocessing function image；By structure chart
As being recorded on preprocessing function image, fused function image is obtained；Then normalizing is carried out to fused function image
Change processing, the function image after being normalized；Function image after normalization is re-sampled to 3 cubic millimeters of voxels；Its
In, each specific beta value of voxel is brain activity；
S3, the brain activity that step S2 is recorded is mapped to eigenface using partial least-square regression method, exports brain activity
Prediction matrix；
S4, the brain activity that the weight matrix that defines and step S3 are obtained when generating eigenface by step S1 prediction matrix come
Reconstruction image Xpred:
Xpred=Wtrain*Ypred
Wherein, WTrain is the weight matrix defined when generating eigenface by step S1, and Ypred is obtained by step S3
The prediction matrix of brain activity, Xpred indicate the test image rebuild.
2. the method according to claim 1 for inducing brain activity and rebuilding face-image, it is characterised in that: the step S1
The size of middle n face-image is the same, and there are eyes and mouth feature in face-image.
3. the method according to claim 1 for inducing brain activity and rebuilding face-image, it is characterised in that: the high-resolution
Rate refers to 1.0 × 1.0 × 1.0mm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910298267.6A CN110084883A (en) | 2019-04-15 | 2019-04-15 | A method of it inducing brain activity and rebuilds face-image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910298267.6A CN110084883A (en) | 2019-04-15 | 2019-04-15 | A method of it inducing brain activity and rebuilds face-image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110084883A true CN110084883A (en) | 2019-08-02 |
Family
ID=67415206
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910298267.6A Pending CN110084883A (en) | 2019-04-15 | 2019-04-15 | A method of it inducing brain activity and rebuilds face-image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110084883A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100249573A1 (en) * | 2009-03-30 | 2010-09-30 | Marks Donald H | Brain function decoding process and system |
| CN102592148A (en) * | 2011-12-29 | 2012-07-18 | 华南师范大学 | Face identification method based on non-negative matrix factorization and a plurality of distance functions |
| GB201300637D0 (en) * | 2013-01-14 | 2013-02-27 | Univ Heriot Watt | An Image Restoration Method |
| CN105335991A (en) * | 2014-06-27 | 2016-02-17 | 联想(北京)有限公司 | Information processing method and electronic device |
| CN105590091A (en) * | 2014-11-06 | 2016-05-18 | Tcl集团股份有限公司 | Face Recognition System And Method |
| CN105975921A (en) * | 2016-04-29 | 2016-09-28 | 厦门大学 | Local feature symbiosis and partial least square method-based pedestrian detection method |
| CN109191505A (en) * | 2018-08-03 | 2019-01-11 | 北京微播视界科技有限公司 | Static state generates the method, apparatus of human face three-dimensional model, electronic equipment |
-
2019
- 2019-04-15 CN CN201910298267.6A patent/CN110084883A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100249573A1 (en) * | 2009-03-30 | 2010-09-30 | Marks Donald H | Brain function decoding process and system |
| CN102592148A (en) * | 2011-12-29 | 2012-07-18 | 华南师范大学 | Face identification method based on non-negative matrix factorization and a plurality of distance functions |
| GB201300637D0 (en) * | 2013-01-14 | 2013-02-27 | Univ Heriot Watt | An Image Restoration Method |
| CN105335991A (en) * | 2014-06-27 | 2016-02-17 | 联想(北京)有限公司 | Information processing method and electronic device |
| CN105590091A (en) * | 2014-11-06 | 2016-05-18 | Tcl集团股份有限公司 | Face Recognition System And Method |
| CN105975921A (en) * | 2016-04-29 | 2016-09-28 | 厦门大学 | Local feature symbiosis and partial least square method-based pedestrian detection method |
| CN109191505A (en) * | 2018-08-03 | 2019-01-11 | 北京微播视界科技有限公司 | Static state generates the method, apparatus of human face three-dimensional model, electronic equipment |
Non-Patent Citations (3)
| Title |
|---|
| ALAN S. COWEN: "Neural portraits of perception: Reconstructing face images from evoked", 《ELSEVIER SCIENCE》 * |
| YUNFA FU: "Imagined Hand Clenching Force and Speed Modulate Brain Activity and Are Classified by NIRS Combined With EEG", 《IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING》 * |
| 霍丽娜: "基于视觉感知与注意机制的图像显著目标检测", 《中国博士学位论文全文数据库》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ozcelik et al. | Reconstruction of perceived images from fmri patterns and semantic brain exploration using instance-conditioned gans | |
| Sujit et al. | Automated image quality evaluation of structural brain MRI using an ensemble of deep learning networks | |
| CN106023194B (en) | Amygdaloid nucleus spectral clustering dividing method based on tranquillization state function connects | |
| Bing et al. | Medical image super resolution using improved generative adversarial networks | |
| Yue et al. | Auto-detection of Alzheimer's disease using deep convolutional neural networks | |
| Gilaie-Dotan et al. | Perceptual shape sensitivity to upright and inverted faces is reflected in neuronal adaptation | |
| Kalarot et al. | Component attention guided face super-resolution network: Cagface | |
| Musel et al. | Coarse-to-fine categorization of visual scenes in scene-selective cortex | |
| Allen et al. | A massive 7T fMRI dataset to bridge cognitive and computational neuroscience | |
| CN112002428B (en) | Whole brain individualized brain function map construction method taking independent component network as reference | |
| CN110246137A (en) | A kind of imaging method, device and storage medium | |
| Jiang et al. | CT image super resolution based on improved SRGAN | |
| Sun et al. | Landmarkgan: Synthesizing faces from landmarks | |
| Huang et al. | Perception-to-image: Reconstructing natural images from the brain activity of visual perception | |
| Goebel et al. | Reading imagined letter shapes from the mind’s eye using real-time 7 tesla fMRI | |
| Kim et al. | Spontaneously emerging patterns in human visual cortex and their functional connectivity are linked to the patterns evoked by visual stimuli | |
| Wang et al. | Brain MR image super-resolution using 3D feature attention network | |
| CN108573512A (en) | A kind of complicated visual pattern reconstructing method based on depth encoding and decoding veneziano model | |
| Zhang et al. | Equivalent processing of facial expression and identity by macaque visual system and task-optimized neural network | |
| Qiao et al. | CorGAN: Context aware recurrent generative adversarial network for medical image generation | |
| CN110084883A (en) | A method of it inducing brain activity and rebuilds face-image | |
| CN104952053B (en) | The facial image super-resolution reconstructing method perceived based on non-linear compression | |
| Eid et al. | RapidVol: Rapid Reconstruction of 3D Ultrasound Volumes from Sensorless 2D Scans | |
| CN111329446B (en) | Visual stimulation system and method for processing spatial frequency of facial pores through brain visual pathway | |
| Yang et al. | Functional diversity of visual cortex improves constraint-free natural image reconstruction from human brain activity |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190802 |