CN110059595A - A kind of adaptive algorithm for image recognition - Google Patents
A kind of adaptive algorithm for image recognition Download PDFInfo
- Publication number
- CN110059595A CN110059595A CN201910264244.3A CN201910264244A CN110059595A CN 110059595 A CN110059595 A CN 110059595A CN 201910264244 A CN201910264244 A CN 201910264244A CN 110059595 A CN110059595 A CN 110059595A
- Authority
- CN
- China
- Prior art keywords
- image
- algorithm
- data
- population
- analysis
- 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
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 43
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 20
- 238000004364 calculation method Methods 0.000 claims abstract description 11
- 230000002068 genetic effect Effects 0.000 claims abstract description 11
- 238000004458 analytical method Methods 0.000 claims abstract description 10
- 238000007405 data analysis Methods 0.000 claims abstract description 7
- 238000000513 principal component analysis Methods 0.000 claims abstract description 5
- 238000005452 bending Methods 0.000 claims description 6
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 230000006978 adaptation Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 3
- 230000035772 mutation Effects 0.000 abstract description 2
- 230000000007 visual effect Effects 0.000 abstract description 2
- 238000013473 artificial intelligence Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000000034 method Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000012706 support-vector machine Methods 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/73—Deblurring; Sharpening
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Genetics & Genomics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Physiology (AREA)
- Multimedia (AREA)
- Biomedical Technology (AREA)
- Image Analysis (AREA)
Abstract
A kind of adaptive algorithm for image recognition of the present invention belongs to intelligent image identification field.The following steps are included: step 1: acquisition image;Step 2: the image of acquisition is pre-processed;Step 3: will the pretreated image of progress described in the step 2, handled again, the image size that makes that treated is identical;Under a kind of adaptive algorithm effect for image recognition of the present invention, this algorithm carries out data analysis to image using principal component analysis, finds optimal characteristics, has unwanted visual characteristic removal for extra;Then benefit is generated algorithmically by initial population, and algorithm makes population be evenly distributed on domain, to promote whole search speed, improves using to genetic algorithm;Intersection and mutation probability according to fitness value adaptive change ensure population diversity, promote Searching efficiency and discrimination;Manual analysis and big data analysis comparing calculation are finally carried out, image object classification is carried out.
Description
Technical field
A kind of adaptive algorithm for image recognition of the present invention belongs to intelligent image identification field.
Background technique
The important component indispensable as following intelligent clothing monitoring system or artificial intelligence module, artificial intelligence
Energy image identification system has become the research hotspot of domestic and international developer.For electric business product identification system, most it is difficult to resolve
The electric business commodity that are how to be effectively treated certainly identify in real time and the problem of detection difficult.Artificial intelligence and corresponding machine learning
The research and development of algorithm provides new resolving ideas for the above problem, with linear discriminant analysis, neural network, subspace
Analysis, support vector machines, numerous machine learning algorithms that random forest is representative have been attempted and have identified applied to electric business commodity
In system.Result of study shows that all kinds of machine learning algorithms can greatly improve the discrimination of merchandise marks, but can also exist
The defects of computation complexity is high, live effect is poor, parameter setting solution is immature, the type of merchandise is limited is practical application
Bring no small obstruction.
Summary of the invention
In view of the above-mentioned problems, the invention discloses a kind of adaptive algorithms for image recognition.
The object of the present invention is achieved like this:
A kind of adaptive algorithm for image recognition, comprising the following steps:
Step 1: acquisition image;
Step 2: the image of acquisition is pre-processed;
Step 3: will the pretreated image of progress described in the step 2, handled again, the image size phase that makes that treated
Together;
Step 4: by size identical image described in the step 3, being carried out edge Edge contrast, operated using Binary Conversion,
By edgeization handle image, be converted into can digitized processing analysis image;
Step 5: image after will be processed described in the step 4 constructs 8 not bending moment formula using second-order moment around mean, together
When calculate image not bending moment;
Step 6: image after will be processed described in the step 5 carries out principal component analysis, forms new feature space;
Step 7: being combined using neural network algorithm and genetic algorithm, generates initial population;
Step 8: ideal adaptation angle value is calculated according to genetic algorithm calculation formula;
Step 9: by the step 8, calculated excellent individual carries out reservation operations;
Step 10: according to the step 7 algorithm calculation method, judge to stop output data;
Step 11: according to the step 10 output data, optimal characteristics data in image are selected, it is empty to form new data characteristics
Between;
Step 12: the data obtained to the step 11 carry out manual analysis and big data analysis comparing calculation, carry out figure
As target classification.
A kind of adaptive algorithm for image recognition, contribution rate is to percent 98 in the step 6.Described
A kind of adaptive algorithm for image recognition, the genetic algorithm are further comprising the steps of:
Step a, it is maximum to fitness value in population to record;
Step b, is calculated again, is obtained data greater than preceding population data, is replaced former data with big individual data items;Step c,
The current the smallest individual maximum individual replacement of fitness value of fitness value;
Step d guarantees that optimum individual is not destroyed.
The utility model has the advantages that
Under a kind of adaptive algorithm effect for image recognition of the present invention, this algorithm carries out image using principal component analysis
Data analysis, finds optimal characteristics, has unwanted visual characteristic removal for extra;Then benefit is generated algorithmically by initial population, and algorithm makes to plant
Group is evenly distributed on domain, to promote whole search speed, improves using to genetic algorithm;Certainly according to fitness value
The intersection and mutation probability for adapting to variation ensure population diversity, promote Searching efficiency and discrimination;Finally carry out manual analysis
With big data analysis comparing calculation, image object classification is carried out.
Specific embodiment
The specific embodiment of the invention is described in further detail below.
Specific embodiment one
The present embodiment is a kind of specific embodiment of the adaptive algorithm for image recognition of the present invention.
A kind of adaptive algorithm for image recognition, comprising the following steps:
Step 1: acquisition image;
Step 2: the image of acquisition is pre-processed;
Step 3: will the pretreated image of progress described in the step 2, handled again, the image size phase that makes that treated
Together;
Step 4: by size identical image described in the step 3, being carried out edge Edge contrast, operated using Binary Conversion,
By edgeization handle image, be converted into can digitized processing analysis image;
Step 5: image after will be processed described in the step 4 constructs 8 not bending moment formula using second-order moment around mean, together
When calculate image not bending moment;
Step 6: image after will be processed described in the step 5 carries out principal component analysis, forms new feature space;
Step 7: being combined using neural network algorithm and genetic algorithm, generates initial population;
Step 8: ideal adaptation angle value is calculated according to genetic algorithm calculation formula;
Step 9: by the step 8, calculated excellent individual carries out reservation operations;
Step 10: according to the step 7 algorithm calculation method, judge to stop output data;
Step 11: according to the step 10 output data, optimal characteristics data in image are selected, it is empty to form new data characteristics
Between;
Step 12: the data obtained to the step 11 carry out manual analysis and big data analysis comparing calculation, carry out figure
As target classification.
Specific embodiment two
The present embodiment is the specific embodiment that the present invention cures a kind of adaptive algorithm for image recognition.
A kind of adaptive algorithm for image recognition, contribution rate is to percent 98 in the step 6.
Specific embodiment three
The present embodiment is the specific embodiment that the present invention cures a kind of adaptive algorithm for image recognition.
A kind of adaptive algorithm for image recognition, the genetic algorithm are further comprising the steps of:
Step a, it is maximum to fitness value in population to record;
Step b, is calculated again, is obtained data greater than preceding population data, is replaced former data with big individual data items;Step c,
The current the smallest individual maximum individual replacement of fitness value of fitness value;
Step d guarantees that optimum individual is not destroyed.
Finally, it should be noted that these are only the preferred embodiment of the present invention, it is not intended to restrict the invention, although reference
Invention is explained in detail for previous embodiment, for those skilled in the art, still can be to aforementioned
Technical solution documented by each embodiment is modified or equivalent replacement of some of the technical features.
Claims (3)
1. a kind of adaptive algorithm for image recognition, which comprises the following steps:
Step 1: acquisition image;
Step 2: the image of acquisition is pre-processed;
Step 3: will the pretreated image of progress described in the step 2, handled again, the image size phase that makes that treated
Together;
Step 4: by size identical image described in the step 3, being carried out edge Edge contrast, operated using Binary Conversion,
By edgeization handle image, be converted into can digitized processing analysis image;
Step 5: image after will be processed described in the step 4 constructs 8 not bending moment formula using second-order moment around mean, together
When calculate image not bending moment;
Step 6: image after will be processed described in the step 5 carries out principal component analysis, forms new feature space;
Step 7: being combined using neural network algorithm and genetic algorithm, generates initial population;
Step 8: ideal adaptation angle value is calculated according to genetic algorithm calculation formula;
Step 9: by the step 8, calculated excellent individual carries out reservation operations;
Step 10: according to the step 7 algorithm calculation method, judge to stop output data;
Step 11: according to the step 10 output data, optimal characteristics data in image are selected, it is empty to form new data characteristics
Between;
Step 12: the data obtained to the step 11 carry out manual analysis and big data analysis comparing calculation, carry out figure
As target classification.
2. a kind of adaptive algorithm for image recognition according to claim 1, which is characterized in that in the step 6
Contribution rate is to percent 98.
3. a kind of adaptive algorithm for image recognition according to claim 1, which is characterized in that the genetic algorithm
It is further comprising the steps of:
Step a, it is maximum to fitness value in population to record;
Step b, is calculated again, is obtained data greater than preceding population data, is replaced former data with big individual data items;
Step c, the current the smallest individual maximum individual replacement of fitness value of fitness value;
Step d guarantees that optimum individual is not destroyed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910264244.3A CN110059595A (en) | 2019-04-03 | 2019-04-03 | A kind of adaptive algorithm for image recognition |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910264244.3A CN110059595A (en) | 2019-04-03 | 2019-04-03 | A kind of adaptive algorithm for image recognition |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110059595A true CN110059595A (en) | 2019-07-26 |
Family
ID=67318280
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910264244.3A Pending CN110059595A (en) | 2019-04-03 | 2019-04-03 | A kind of adaptive algorithm for image recognition |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110059595A (en) |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101465001A (en) * | 2008-12-31 | 2009-06-24 | 昆山锐芯微电子有限公司 | Method for detecting image edge based on Bayer RGB |
CN101706335A (en) * | 2009-11-11 | 2010-05-12 | 华南理工大学 | Wind power forecasting method based on genetic algorithm optimization BP neural network |
CN103942571A (en) * | 2014-03-04 | 2014-07-23 | 西安电子科技大学 | Graphic image sorting method based on genetic programming algorithm |
CN104361352A (en) * | 2014-11-13 | 2015-02-18 | 东北林业大学 | Solid wood panel defect separation method based on compressed sensing |
CN104504442A (en) * | 2014-12-30 | 2015-04-08 | 湖南强智科技发展有限公司 | Neural network optimization method |
US9720934B1 (en) * | 2014-03-13 | 2017-08-01 | A9.Com, Inc. | Object recognition of feature-sparse or texture-limited subject matter |
-
2019
- 2019-04-03 CN CN201910264244.3A patent/CN110059595A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101465001A (en) * | 2008-12-31 | 2009-06-24 | 昆山锐芯微电子有限公司 | Method for detecting image edge based on Bayer RGB |
CN101706335A (en) * | 2009-11-11 | 2010-05-12 | 华南理工大学 | Wind power forecasting method based on genetic algorithm optimization BP neural network |
CN103942571A (en) * | 2014-03-04 | 2014-07-23 | 西安电子科技大学 | Graphic image sorting method based on genetic programming algorithm |
US9720934B1 (en) * | 2014-03-13 | 2017-08-01 | A9.Com, Inc. | Object recognition of feature-sparse or texture-limited subject matter |
CN104361352A (en) * | 2014-11-13 | 2015-02-18 | 东北林业大学 | Solid wood panel defect separation method based on compressed sensing |
CN104504442A (en) * | 2014-12-30 | 2015-04-08 | 湖南强智科技发展有限公司 | Neural network optimization method |
Non-Patent Citations (1)
Title |
---|
张媛 等: "不变矩法分类识别带钢表面的缺陷", 《光电工程》 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Liao et al. | Particle swarm optimization-least squares support vector regression based forecasting model on dissolved gases in oil-filled power transformers | |
CN112383052B (en) | Power grid fault repairing method and device based on power internet of things | |
CN110544177A (en) | Load identification method based on power fingerprint and computer readable storage medium | |
CN109214527B (en) | Early diagnosis and early warning method and system for transformer fault | |
CN110689190A (en) | Power grid load prediction method and device and related equipment | |
CN102142091A (en) | Kernel integration optimizing classification method | |
CN110717610A (en) | Wind power prediction method based on data mining | |
Zhang et al. | A multi-agent genetic algorithm for big optimization problems | |
CN102063626A (en) | Power quality disturbance mode discrimination method | |
Zhang et al. | Intelligent systems for power system dynamic security assessment: Review and classification | |
CN117639452B (en) | Voltage compensation method, device and equipment of inverter and storage medium | |
Wang et al. | Big data analytics for price forecasting in smart grids | |
Abbas et al. | Electric load forecasting using support vector machines optimized by genetic algorithm | |
CN115275990A (en) | Evaluation method and system for broadband oscillation risk of regional power grid | |
Deng et al. | Sales forecasting based on LightGBM | |
Magele et al. | Niching evolution strategies for simultaneously finding global and pareto optimal solutions | |
Chen et al. | An optimization model for process traceability in case-based reasoning based on ontology and the genetic algorithm | |
CN110059595A (en) | A kind of adaptive algorithm for image recognition | |
Sivaranjani et al. | An improvised algorithm for computer vision based cashew grading system using deep CNN | |
CN117151488A (en) | Method, system, storage medium and equipment for expanding cold tide and strong wind weather sample | |
Vidyashanakara et al. | Leaf classification based on GLCM texture and SVM | |
Paardekooper et al. | Designing deep convolutional neural networks using a genetic algorithm for image-based malware classification | |
Zhao et al. | Distribution Network Topology Identification with Graph Transformer Neural Network | |
CN115936389A (en) | Big data technology-based method for matching evaluation experts with evaluation materials | |
Li et al. | Weed identification based on shape features and ant colony optimization algorithm |
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 | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190726 |