CN112668645A - Classification method for finely sorting apples based on human physiological cognitive characteristics - Google Patents
Classification method for finely sorting apples based on human physiological cognitive characteristics Download PDFInfo
- Publication number
- CN112668645A CN112668645A CN202011581252.XA CN202011581252A CN112668645A CN 112668645 A CN112668645 A CN 112668645A CN 202011581252 A CN202011581252 A CN 202011581252A CN 112668645 A CN112668645 A CN 112668645A
- Authority
- CN
- China
- Prior art keywords
- brain
- apple
- human
- activity
- decision boundary
- 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
- 238000000034 method Methods 0.000 title claims abstract description 25
- 235000021016 apples Nutrition 0.000 title claims abstract description 18
- 230000001149 cognitive effect Effects 0.000 title claims abstract description 7
- 244000141359 Malus pumila Species 0.000 title 1
- 241000220225 Malus Species 0.000 claims abstract description 41
- 210000004556 brain Anatomy 0.000 claims abstract description 20
- 230000000694 effects Effects 0.000 claims abstract description 18
- 238000012706 support-vector machine Methods 0.000 claims abstract description 16
- 238000002610 neuroimaging Methods 0.000 claims abstract description 11
- 230000008569 process Effects 0.000 claims abstract description 9
- 238000012545 processing Methods 0.000 claims abstract description 8
- 230000001788 irregular Effects 0.000 claims abstract description 4
- 230000007177 brain activity Effects 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 8
- 230000000638 stimulation Effects 0.000 claims description 7
- 210000003710 cerebral cortex Anatomy 0.000 claims description 5
- 230000000007 visual effect Effects 0.000 claims description 5
- 238000005481 NMR spectroscopy Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000008092 positive effect Effects 0.000 claims description 2
- 235000013399 edible fruits Nutrition 0.000 abstract description 3
- 230000019771 cognition Effects 0.000 description 5
- 230000000875 corresponding effect Effects 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 230000005284 excitation Effects 0.000 description 3
- 238000002599 functional magnetic resonance imaging Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 210000002569 neuron Anatomy 0.000 description 3
- 230000002596 correlated effect Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000002964 excitative effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000013421 nuclear magnetic resonance imaging Methods 0.000 description 1
- 239000002420 orchard Substances 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
Images
Landscapes
- Image Analysis (AREA)
Abstract
A classification method for carrying out refined grade sorting on apples based on human physiological cognitive characteristics comprises the following steps: step 1: acquiring brain imaging data when a person watches and identifies the apple; step 2: processing brain imaging data to obtain an active activity factor alpha of an apple with a red color, a big size and a regular shape; and step 3: directly using pictures with red color, large size, regular shape, cyan color, small size and irregular shape to train the algorithm of the support vector machine, and adjusting a decision boundary by using a penalty function HL; and 4, step 4: the influence of the active activity factors in the human brain recognition in the step 2 is brought into the decision boundary adjusting process in the step 3, and the punishment strength is increased when the judgment is wrong, so that the decision boundary is further optimized and adjusted; and 5: and classifying the sample by using a trained classifier. The invention is suitable for the condition that the manual sorting cost is higher when the fruit grower sells apples with different qualities in a grading way.
Description
Technical Field
The invention relates to a classification method for finely sorting apples based on human physiological cognition characteristics, wherein the physiological cognition is considered as brain activity characteristics for identifying and judging human brains, and the classification method is suitable for the condition that manual sorting cost is high when apple dealers sell apples of different qualities in a grading manner.
Background
In order to ensure maximum profit in the orchard and different demands of consumers, fruit growers need to sort apples of different colors, sizes and shapes when picking apples. Fruit growers need invest into a large amount of manpower, material resources and time cost in the face of waiting in a large number to sort the apple, often have certain subjective factor through artifical screening mode letter sorting in addition, and different letter sorting personnel can carry out different letter sorting modes to the apple, cause the apple to sort the confusion at last, and the size is different. In addition, the existing assembly line sorting method mainly aims at the fact that the size of apples is taken as a main classification characteristic, so that the apples with uniform size contain the phenomena of obvious shape and color difference, and the phenomena have certain negative effects in the marketing process.
When an image appears in the visual range of a person, the type (color, shape, and distance of position) of the object contained in the image is used as a visual stimulus, different areas of the cerebral cortex receive the stimulus to generate different degrees of excitement, and judgment is made according to the strong excitement signal. That is, when the stimulation information reaches the cerebral cortex, the neurons in the corresponding region are activated to generate excitation, the irrelevant neurons do not generate or generate weak excitation, and the similarity of the nerves is associated with a certain dimension (shape, color, smell, etc.) of the stimulation. These excitations are manifested in the mri image in that the more strongly correlated regions are more prominent in the red region of the fMRI image, and the less correlated regions are more prominent in the blue region. When the neural activation mode presents the same effect as the cognitive dimension in the form of voxels, the type of stimulation can be inferred according to the region where the excitatory neurons are located, although the type to which the stimulation belongs is unclear, so that the classification decision of the user is facilitated.
The brain imaging of the experimenter who recognizes the size, shape and color of the apple can be tracked through the nuclear magnetic resonance imaging technology, and the experimenter makes a judgment on the characteristics (the size, the shape and the color) of the observed apple at the same time in the process. Semantic analysis, data processing and feature extraction are carried out on pictures obtained by brain imaging to obtain data which are used as training set data of a support vector machine, the support vector machine is assisted to adjust decision boundaries by modifying a loss function, and information in new pictures is identified. Therefore, training and learning are carried out through the acquired brain imaging, and the physiological cognition characteristic of human recognition and judgment is applied to apple sorting.
The existing apple sorting method has manual sorting and basic industrial assembly line sorting modes, the manual sorting mode is low in efficiency and high in cost, and the industrial assembly line sorting mode is not fine enough, so that the shape and color of the finally sorted apples are obviously differentiated.
Disclosure of Invention
The invention aims to overcome the defects of the existing method and introduces a classification method for finely sorting apples based on human physiological cognitive characteristics.
The invention can ensure the refinement of apple classification grade on the premise of reducing the cost of manpower and material resources as much as possible, provides a method for applying the brain activity characteristics of the human brain for identification and judgment to the training process of the existing support vector machine algorithm, and provides a new application idea for people to the identification and classification situation.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a classification method for carrying out grade fine sorting on apples by a brain activity characteristic help support vector machine algorithm based on human brain recognition and judgment comprises the following steps:
step 1: acquiring brain imaging data when a person watches and identifies the apple: brain activity when the experimenter classified and judged the apple was read by the nuclear magnetic resonance technology, and the correlation between the brain activity and the corresponding visual stimulus (the characteristics of the apple being identified) was recorded. Analyzing and processing the brain moving images to obtain image data when the cerebral cortex is identified and judged;
step 2: processing brain imaging data to obtain an active activity factor alpha of the apple which is red in color, large in size and regular in shape: preprocessing the image data obtained in the step 1, and extracting the activity characteristics of the brain when the stimulation type is identified as an active activity factor alpha;
and step 3: directly using pictures with red color, large size, regular shape, cyan color, small size and irregular shape to train the algorithm of the support vector machine, and adjusting a decision boundary by using a penalty function HL;
and 4, step 4: the influence of the active activity factors in the human brain recognition in the step 2 is brought into the decision boundary adjusting process in the step 3, and the punishment strength is increased when the judgment is wrong, so that the decision boundary is further optimized and adjusted;
and 5: and classifying the sample by using a trained classifier.
The invention provides a new idea for a classification method faced by a machine learning algorithm, which utilizes the brain activity characteristics of human brain for identification and judgment to help the support vector machine algorithm to improve the classification precision under the training condition of small samples.
The support vector machine algorithm can extract the features in the pictures and identify the information in the new pictures, so that the pictures with a large number of known labels can be trained and then classified; fMRI measurement data is injected into the training process of the support vector machine recognition learning algorithm from the human brain activity of an object watching an image, and penalty strength corresponding to the active activity factor is added when judgment is wrong.
Compared with the prior art, the technical scheme of the invention has the advantages that:
(1) a higher classification can be obtained with only a small number of training samples
(2) The recognition mode of human brain and machine learning are combined, so that the algorithm is closer to human
Drawings
FIG. 1 is a flow chart of the present invention
Detailed Description
The present invention will be described in further detail with reference to examples in order to facilitate the understanding and practice of the invention by those of ordinary skill in the art.
A method for carrying out fine sorting on apples by a support vector machine algorithm based on brain activity characteristics of human brain for identification and judgment comprises the following steps:
step 1: taking brain imaging data when the human brain watches and identifies the apple: brain activity when the experimenter classified and judged the apple was read by the nuclear magnetic resonance technology, and the correlation between the brain activity and the corresponding visual stimulus (the characteristics of the apple being identified) was recorded. Analyzing and processing the brain moving images to obtain image data when the cerebral cortex is identified and judged;
step 2: processing brain imaging data to obtain an active activity factor alpha of the apple which is red in color, large in size and regular in shape: preprocessing the image data obtained in the step 1, and extracting the activity characteristics of the brain when the stimulation type is identified as an active activity factor alpha;
and step 3: directly using pictures with red color, large size, regular shape, cyan color, small size and irregular shape to train the algorithm of the support vector machine, and adjusting a decision boundary by using a penalty function HL;
and 4, step 4: substituting the positive activity factors in the human brain recognition in the step 2 into the decision boundary adjusting process in the step 3, wherein when the judgment is wrong, the punishment is (1-z) alpha, the punishment strength is increased, and the decision boundary is further optimized and adjusted;
and 5: and classifying the apples to be sorted by using a trained support vector machine classifier.
The SVM algorithm and loss function referred to herein are described in Benmei Chen, Sheng Li, Zoe Kourtzi, and Si Wu et al, Behavior-structured Vector Machines for fMRI Data Analysis, 2010.
The active activity factors referred to herein are disclosed in the article "use human blue activity to guide machine learning" published in 2018 by Ruth C.Fong1,3, Walter J.Scheirer2,3& David D.Cox3 et al.
The invention relates to a classification method for finely sorting apples based on human physiological cognition characteristics, wherein the physiological cognition is considered as brain activity characteristics for identifying and judging human brains.
The embodiments described in this specification are merely illustrative of implementations of the inventive concept and the scope of the present invention should not be considered limited to the specific forms set forth in the embodiments but rather by the equivalents thereof as may occur to those skilled in the art upon consideration of the present inventive concept.
Claims (2)
1. A classification method for finely sorting apples based on human physiological cognitive characteristics comprises the following steps:
step 1: taking brain imaging data when the human brain watches and identifies the apple: brain activity when the experimenter classified and judged the apple was read by the nuclear magnetic resonance technology, and the correlation between the brain activity and the corresponding visual stimulus (the characteristics of the apple being identified) was recorded. Analyzing and processing the brain moving images to obtain image data when the cerebral cortex is identified and judged;
step 2: processing brain imaging data to obtain an active activity factor alpha of the apple which is red in color, large in size and regular in shape: preprocessing the image data obtained in the step 1, and extracting the activity characteristics of the brain when the stimulation type is identified as an active activity factor alpha;
and step 3: directly using pictures with red color, large size, regular shape, cyan color, small size and irregular shape to train the algorithm of the support vector machine, and adjusting a decision boundary by using a penalty function HL;
and 4, step 4: substituting the positive activity factors in the human brain recognition in the step 2 into the decision boundary adjusting process in the step 3, wherein when the judgment is wrong, the punishment is (1-z) alpha, the punishment strength is increased, and the decision boundary is further optimized and adjusted;
and 5: and classifying the apples to be sorted by using a trained support vector machine classifier.
2. The classification method for apple fine sorting based on human physiological cognitive features as claimed in claim 1, wherein: the brain activity characteristics during the recognition and judgment of the human are added into the training process of the support vector machine algorithm, so that the activity characteristics of the human brain directly guide the support vector machine algorithm, and the classifier is helped to improve the training precision.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011581252.XA CN112668645A (en) | 2020-12-28 | 2020-12-28 | Classification method for finely sorting apples based on human physiological cognitive characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011581252.XA CN112668645A (en) | 2020-12-28 | 2020-12-28 | Classification method for finely sorting apples based on human physiological cognitive characteristics |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112668645A true CN112668645A (en) | 2021-04-16 |
Family
ID=75411016
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011581252.XA Pending CN112668645A (en) | 2020-12-28 | 2020-12-28 | Classification method for finely sorting apples based on human physiological cognitive characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112668645A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663414A (en) * | 2012-03-14 | 2012-09-12 | 大连灵动科技发展有限公司 | Cerebrum cognitive status recognition method based on cerebral function imaging |
| CN106682681A (en) * | 2016-08-19 | 2017-05-17 | 江苏电力信息技术有限公司 | Recognition algorithm automatic improvement method based on relevance feedback |
| CN111814825A (en) * | 2020-06-04 | 2020-10-23 | 济南大学 | Apple detection grading method and system based on genetic algorithm optimization support vector machine |
-
2020
- 2020-12-28 CN CN202011581252.XA patent/CN112668645A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663414A (en) * | 2012-03-14 | 2012-09-12 | 大连灵动科技发展有限公司 | Cerebrum cognitive status recognition method based on cerebral function imaging |
| CN106682681A (en) * | 2016-08-19 | 2017-05-17 | 江苏电力信息技术有限公司 | Recognition algorithm automatic improvement method based on relevance feedback |
| CN111814825A (en) * | 2020-06-04 | 2020-10-23 | 济南大学 | Apple detection grading method and system based on genetic algorithm optimization support vector machine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Mohamed et al. | Automated detection of white blood cells cancer diseases | |
| WO2019000653A1 (en) | Image target identification method and apparatus | |
| CN109002851B (en) | Fruit classification method based on image multi-feature fusion and application | |
| CN108776774A (en) | A kind of human facial expression recognition method based on complexity categorization of perception algorithm | |
| CN108256579A (en) | A kind of multi-modal sense of national identity quantization measuring method based on priori | |
| CN104036247A (en) | Facial feature based face racial classification method | |
| CN109934203A (en) | A kind of cost-sensitive increment type face identification method based on comentropy selection | |
| CN109543518A (en) | A kind of human face precise recognition method based on integral projection | |
| Aliyu et al. | Normal and abnormal red blood cell recognition using image processing | |
| CN109009096A (en) | The system and method that a kind of pair of films and television programs objectively evaluate online | |
| CN114937032A (en) | Pathological section color correlation quality evaluation method based on staining separation | |
| CN115034296A (en) | Electroencephalogram cross-tested source domain selection method based on domain similarity | |
| Alzu’bi et al. | Dates fruits classification using SVM | |
| Rameen et al. | Leveraging supervised machine learning techniques for identification of malaria cells using blood smears | |
| KR20200136004A (en) | Method for detecting cells with at least one malformation in a cell sample | |
| Dehmeshki et al. | Classification of disease subgroup and correlation with disease severity using magnetic resonance imaging whole-brain histograms: application to magnetization transfer ratios and multiple sclerosis | |
| KR20010017092A (en) | Method for counting and analyzing morphology of blood cell automatically | |
| CN112668645A (en) | Classification method for finely sorting apples based on human physiological cognitive characteristics | |
| CN106073823A (en) | A kind of intelligent medical supersonic image processing equipment, system and method | |
| CN109409347A (en) | A method of based on facial features localization fatigue driving | |
| CN115330721A (en) | Banana fruit comb plumpness detection method and system based on shape and color information | |
| Srinivasan et al. | Classification of cervix lesions using filter bank-based texture mode | |
| CN114186591A (en) | Method for improving generalization capability of emotion recognition system | |
| CN112274154B (en) | Cross-subject fatigue driving classification method based on electroencephalogram sample weight adjustment | |
| Pathan et al. | Silkworm Egg Counting System Using Image Processing Algorithm-A Review |
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 |