CN112085118A - Big data classification statistical method based on image recognition technology - Google Patents
Big data classification statistical method based on image recognition technology Download PDFInfo
- Publication number
- CN112085118A CN112085118A CN202010980872.4A CN202010980872A CN112085118A CN 112085118 A CN112085118 A CN 112085118A CN 202010980872 A CN202010980872 A CN 202010980872A CN 112085118 A CN112085118 A CN 112085118A
- Authority
- CN
- China
- Prior art keywords
- image recognition
- image
- classification statistical
- recognition system
- big data
- 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
- 238000007619 statistical method Methods 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 18
- 230000006872 improvement Effects 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 7
- 238000007781 pre-processing Methods 0.000 claims description 18
- 230000004297 night vision Effects 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 10
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 238000013135 deep learning Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 6
- 238000009499 grossing Methods 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 6
- 230000007246 mechanism Effects 0.000 abstract description 2
- 230000001737 promoting effect Effects 0.000 abstract description 2
- 241000287828 Gallus gallus Species 0.000 description 11
- 235000013330 chicken meat Nutrition 0.000 description 11
- 230000008569 process Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention belongs to the technical field of image recognition, and particularly relates to a big data classification statistical method based on an image recognition technology, which comprises the following specific steps: s1: establishing an image recognition system: establishing an image recognition system according to the use requirement, and performing recognition training on the image recognition system, so that the image recognition system can meet the recognition requirement on the target object and can output the recognition result; s2: image recognition and acquisition results: outputting the result of the image recognition based on the recognition result of step S1; s3: carrying out classified statistics on the image recognition results; s4: the feedback improvement of the identification accuracy is realized, an autonomous learning improvement mechanism is provided, the method is suitable for different use conditions, and the identification accuracy is continuously improved in a learning improvement mode; through electronic information's identification mode, the mode efficiency of relative manual identification is showing and is promoting, and through the mode of constantly studying, and the accuracy is higher.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to a big data classification statistical method based on an image recognition technology.
Background
Image recognition refers to a technique of processing, analyzing and understanding an image with a computer to recognize various different modes of objects and objects. Image recognition is an important area of artificial intelligence. The main image recognition methods include an image recognition method based on a neural network, an image recognition method based on a wavelet moment, and the like. In general industrial use, an industrial camera is adopted to shoot pictures, then software is utilized to further identify and process according to the gray level difference of the pictures, and in addition, the technology of classifying remote sensing images in geography is pointed out.
Image recognition is used for fewer data statistics directions, the accuracy of data statistics results is insufficient, improvement is difficult, and overall system upgrading is needed.
Disclosure of Invention
The invention aims to provide a big data classification statistical method based on an image identification technology, and aims to solve the problems that the image identification proposed in the background technology is less in data statistical direction, insufficient in accuracy of data statistical results, difficult to improve and needs to upgrade an integral system.
In order to achieve the purpose, the invention provides the following technical scheme: a big data classification statistical method based on an image recognition technology comprises the following specific steps:
s1: establishing an image recognition system: establishing an image recognition system according to the use requirement, and performing recognition training on the image recognition system, so that the image recognition system can meet the recognition requirement on the target object and can output the recognition result;
s2: image recognition and acquisition results: outputting the result of the image recognition based on the recognition result of step S1;
s3: and (3) carrying out classified statistics on image recognition results: according to the step S2, acquiring the output image recognition result, and performing classification statistics on the output image recognition result according to the recognition result to make a corresponding classification statistical table;
s4: feedback improvement on recognition accuracy: and (4) acquiring the classification statistical table in the step (S3), comparing the classification statistical table with the actual image display condition, screening out the image condition with wrong identification, and taking the image condition with wrong identification as a case for improving the identification of the image identification system.
Preferably, the step of establishing an image recognition system in step S1 includes: the method comprises the steps of establishing an image recognition model, preprocessing an image and extracting features, wherein the image recognition system removes interference information from the image to be recognized through image preprocessing, extracts the features from the preprocessed image information through feature extraction and judges the image.
Preferably, the image recognition system is based on high-definition night vision cameras, and the high-definition night vision cameras are distributed at each image acquisition point.
Preferably, the image preprocessing is image processing that specifically deletes unnecessary information in the original data, and performs smoothing, binarization, and amplitude normalization.
Preferably, the classification statistical table in the step S3 includes a bar chart, a data table, a line chart and a pie chart.
Preferably, the image recognition system is a deep learning image recognition system based on a neural network.
Compared with the prior art, the invention has the beneficial effects that:
1) the system has an autonomous learning improvement mechanism, can be suitable for different use conditions, and continuously improves the identification accuracy through a learning improvement mode;
2) through electronic information's identification mode, the mode efficiency of relative manual identification is showing and is promoting, and through the mode of constantly studying, and the accuracy is higher.
Drawings
FIG. 1 is a flow chart of a class statistics method of the present invention;
FIG. 2 is a flow chart of the recognition process of the image recognition system according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In the description of the present invention, it is to be understood that the terms "upper", "lower", "front", "rear", "left", "right", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, are merely for convenience in describing the present invention and simplifying the description, and do not indicate or imply that the device or element being referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus, should not be construed as limiting the present invention.
Referring to fig. 1-2, the present invention provides a technical solution: a big data classification statistical method based on an image recognition technology comprises the following specific steps:
s1: establishing an image recognition system: the method comprises the following steps of establishing an image recognition system according to use requirements, wherein the image recognition system is a deep learning image recognition system based on a neural network, recognizing and training the image recognition system to enable the image recognition system to meet the recognition of a target object and output a recognition result, and the step of establishing the image recognition system comprises the following steps: the method comprises the steps of establishing an image recognition model, image preprocessing and feature extraction, wherein the image recognition system removes interference information from an image to be recognized through image preprocessing, extracts features from the preprocessed image information through the feature extraction and judges the image, the image recognition system is based on high-definition night vision cameras, the high-definition night vision cameras are distributed at each image acquisition point, and the image preprocessing specifically comprises the steps of deleting useless information in original data, and performing image processing of smoothing, binaryzation and amplitude normalization;
s2: image recognition and acquisition results: outputting the result of the image recognition based on the recognition result of step S1;
s3: and (3) carrying out classified statistics on image recognition results: according to the step S2, acquiring the output image recognition result, and performing classification statistics on the output image recognition result according to the recognition result to make a corresponding classification statistical table, wherein the classification statistical table comprises a histogram, a data table, a line graph and a pie graph;
s4: feedback improvement on recognition accuracy: and (4) acquiring the classification statistical table in the step (S3), comparing the classification statistical table with the actual image display condition, screening out the image condition with wrong identification, and taking the image condition with wrong identification as a case for improving the identification of the image identification system.
Example 1:
image recognition is used for scenic spot people counting:
the big data classification statistical method based on the image recognition technology comprises the following specific steps:
s1: establishing an image recognition system: the method comprises the steps of establishing an image recognition system according to use requirements, wherein the image recognition system is a deep learning image recognition system based on a neural network, recognizing and training the image recognition system, taking a person as a recognition object, and recognizing the person by the image recognition system so as to acquire the information of the recognized person, so that the image recognition system can recognize a target object and output a recognition result, and the step of establishing the image recognition system comprises the following steps: the method comprises the steps of establishing an image recognition model, image preprocessing and feature extraction, wherein the image recognition system removes interference information from an image to be recognized through image preprocessing, extracts features from the preprocessed image information through the feature extraction and judges the image, the image recognition system is based on high-definition night vision cameras, the high-definition night vision cameras are distributed at all image acquisition points, the high-definition night vision cameras are installed at all intersections of each scenic spot and identify faces of tourists on the road, and the image preprocessing specifically comprises the steps of deleting useless information in original data and performing image processing of smoothing, binaryzation and amplitude normalization;
s2: image recognition and acquisition results: outputting the result of image recognition according to the recognition result of the step S1, and recording each tourist once after one scenic spot recognition on the same day when the recognition result occurs twice;
s3: and (3) carrying out classified statistics on image recognition results: according to the step S2, obtaining the output image recognition result, and performing classification statistics on the output image recognition result according to the recognition result to make a corresponding classification statistical table, where the classification statistical table includes a histogram, a data table, a line graph and a pie graph, the number of tourists on each sight spot is the number index of the classification statistical table, and the larger the number of records in the classification statistical table, the larger the number of tourists in the sight spot;
s4: feedback improvement on recognition accuracy: and (4) acquiring the classification statistical table in the step (S3), comparing the classification statistical table with the actual image display condition, screening out the image condition with wrong identification, and taking the image condition with wrong identification as a case for improving the identification of the image identification system.
Example 2:
image recognition is used for traffic flow statistics:
the big data classification statistical method based on the image recognition technology comprises the following specific steps:
s1: establishing an image recognition system: the method comprises the following steps of establishing an image recognition system according to use requirements, wherein the image recognition system is a deep learning image recognition system based on a neural network, recognizing and training the image recognition system, taking a license plate of a vehicle as a recognition object, and recognizing the license plate by the image recognition system so as to acquire the information of the recognized vehicle, so that the image recognition system can recognize a target object and output a recognition result, and the step of establishing the image recognition system comprises the following steps: the method comprises the steps of establishing an image recognition model, image preprocessing and feature extraction, wherein the image recognition system removes interference information from an image to be recognized through image preprocessing, extracts features from the preprocessed image information through the feature extraction and judges the image, the image recognition system is based on a high-definition night vision camera, the high-definition night vision camera is installed at a road junction to be collected, the high-definition night vision camera recognizes license plates of vehicles on the road, the image preprocessing specifically comprises the steps of deleting useless information in original data, and performing image processing of smoothing, binaryzation and amplitude normalization;
s2: image recognition and acquisition results: outputting the result of image recognition according to the recognition result of the step S1, and setting a time period, wherein if the time period is 2h, the number of vehicles passing through the road in 2h is a counting number;
s3: and (3) carrying out classified statistics on image recognition results: according to the step S2, acquiring the output image recognition result, and performing classification statistics on the output image recognition result according to the recognition result to make a corresponding classification statistical table, where the classification statistical table includes a bar chart, a data table, a line chart and a pie chart, the number of vehicles in the time period of the road is the number index of the classification statistical table, and the greater the number of records in the classification statistical table, the greater the number of vehicles in the time period of the road;
s4: feedback improvement on recognition accuracy: and (4) acquiring the classification statistical table in the step (S3), comparing the classification statistical table with the actual image display condition, screening out the image condition with wrong identification, and taking the image condition with wrong identification as a case for improving the identification of the image identification system.
Example 3:
image recognition is used for growth state statistics of the bred chickens:
the big data classification statistical method based on the image recognition technology comprises the following specific steps:
s1: establishing an image recognition system: the method comprises the following steps of establishing an image recognition system according to use requirements, wherein the image recognition system is a deep learning image recognition system based on a neural network, recognizing and training the image recognition system, taking the bred chicken as a recognition object, recognizing the bred chicken by the image recognition system, and regarding the walking state of the bred chicken (the bred chicken walks forcedly and slowly and is regarded as a diseased state), so that the image recognition system can recognize a target object and output a recognition result, wherein the step of establishing the image recognition system comprises the following steps: the method comprises the steps of establishing an image recognition model, image preprocessing and feature extraction, wherein the image recognition system removes interference information from an image to be recognized through image preprocessing, extracts features and judges the image from the preprocessed image information through feature extraction, is based on a high-definition night vision camera which is arranged in a breeding base in a matrix shape, and specifically, the image preprocessing is to delete useless information in original data and perform image processing of smoothing, binaryzation and amplitude normalization;
s2: image recognition and acquisition results: outputting the result of image recognition according to the recognition result of the step S1, and recording the time when the bred chickens are in various states (if the bred chickens are sick, the time interval from the first time when the bred chickens are shot to be in the sick state to the last time when the bred chickens are shot to be in the sick state; if the bred chickens are normal, no record is made);
s3: and (3) carrying out classified statistics on image recognition results: according to the step S2, acquiring the output image recognition result, performing classification statistics on the output image recognition result according to the recognition result, and making a corresponding classification statistical table, wherein the classification statistical table comprises a histogram, a data table, a line graph and a pie graph, and the time of the diseased state of the bred chickens is recorded, and the longer the time is, the greater the risk is;
s4: feedback improvement on recognition accuracy: and (4) acquiring the classification statistical table in the step (S3), comparing the classification statistical table with the actual image display condition, screening out the image condition with wrong identification, and taking the image condition with wrong identification as a case for improving the identification of the image identification system.
While there have been shown and described the fundamental principles and essential features of the invention and advantages thereof, it will be apparent to those skilled in the art that the invention is not limited to the details of the foregoing exemplary embodiments, but is capable of other specific forms without departing from the spirit or essential characteristics thereof; the present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein, and any reference signs in the claims are not intended to be construed as limiting the claim concerned.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (6)
1. A big data classification statistical method based on image recognition technology is characterized in that: the big data classification statistical method based on the image recognition technology comprises the following specific steps:
s1: establishing an image recognition system: establishing an image recognition system according to the use requirement, and performing recognition training on the image recognition system, so that the image recognition system can meet the recognition requirement on the target object and can output the recognition result;
s2: image recognition and acquisition results: outputting the result of the image recognition based on the recognition result of step S1;
s3: and (3) carrying out classified statistics on image recognition results: according to the step S2, acquiring the output image recognition result, and performing classification statistics on the output image recognition result according to the recognition result to make a corresponding classification statistical table;
s4: feedback improvement on recognition accuracy: and (4) acquiring the classification statistical table in the step (S3), comparing the classification statistical table with the actual image display condition, screening out the image condition with wrong identification, and taking the image condition with wrong identification as a case for improving the identification of the image identification system.
2. The big data classification statistical method based on the image recognition technology as claimed in claim 1, wherein: the step of establishing the image recognition system in step S1 includes: the method comprises the steps of establishing an image recognition model, preprocessing an image and extracting features, wherein the image recognition system removes interference information from the image to be recognized through image preprocessing, extracts the features from the preprocessed image information through feature extraction and judges the image.
3. The big data classification statistical method based on the image recognition technology as claimed in claim 2, wherein: the image recognition system is based on high-definition night vision cameras which are distributed at each image acquisition point.
4. The big data classification statistical method based on the image recognition technology as claimed in claim 2, wherein: the image preprocessing is specifically image processing of deleting useless information in the original data, smoothing, binarization and amplitude normalization.
5. The big data classification statistical method based on the image recognition technology as claimed in claim 1, wherein: the classification statistical table in the step S3 includes a histogram, a data table, a line graph and a pie chart.
6. The big data classification statistical method based on the image recognition technology as claimed in claim 2, wherein: the image recognition system is a deep learning image recognition system based on a neural network.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010980872.4A CN112085118A (en) | 2020-09-17 | 2020-09-17 | Big data classification statistical method based on image recognition technology |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010980872.4A CN112085118A (en) | 2020-09-17 | 2020-09-17 | Big data classification statistical method based on image recognition technology |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112085118A true CN112085118A (en) | 2020-12-15 |
Family
ID=73736544
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010980872.4A Pending CN112085118A (en) | 2020-09-17 | 2020-09-17 | Big data classification statistical method based on image recognition technology |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112085118A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114581376A (en) * | 2022-01-31 | 2022-06-03 | 南通摩瑞纺织有限公司 | Automatic sorting method and system for textile silkworm cocoons based on image recognition |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106503747A (en) * | 2016-10-28 | 2017-03-15 | 西安夫子电子科技研究院有限公司 | A kind of image recognition statistical analysis system |
WO2019000653A1 (en) * | 2017-06-30 | 2019-01-03 | 清华大学深圳研究生院 | Image target identification method and apparatus |
-
2020
- 2020-09-17 CN CN202010980872.4A patent/CN112085118A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106503747A (en) * | 2016-10-28 | 2017-03-15 | 西安夫子电子科技研究院有限公司 | A kind of image recognition statistical analysis system |
WO2019000653A1 (en) * | 2017-06-30 | 2019-01-03 | 清华大学深圳研究生院 | Image target identification method and apparatus |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114581376A (en) * | 2022-01-31 | 2022-06-03 | 南通摩瑞纺织有限公司 | Automatic sorting method and system for textile silkworm cocoons based on image recognition |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103208185B (en) | A kind of vehicle detection at night method and system based on car light identification | |
US20170286780A1 (en) | Method and system for calculating passenger crowdedness degree | |
CN104091176B (en) | Portrait comparison application technology in video | |
CN104239867B (en) | License plate locating method and system | |
CN104166841A (en) | Rapid detection identification method for specified pedestrian or vehicle in video monitoring network | |
CN104978567B (en) | Vehicle checking method based on scene classification | |
CN105354548A (en) | Surveillance video pedestrian re-recognition method based on ImageNet retrieval | |
CN110660222A (en) | Intelligent environment-friendly electronic snapshot system for black smoke vehicle on road | |
CN106295558A (en) | A kind of pig Behavior rhythm analyzes method | |
CN106169071A (en) | A kind of Work attendance method based on dynamic human face and chest card recognition and system | |
CN111274886B (en) | Deep learning-based pedestrian red light running illegal behavior analysis method and system | |
CN108830254B (en) | Fine-grained vehicle type detection and identification method based on data balance strategy and intensive attention network | |
CN111310592B (en) | Detection method based on scene analysis and deep learning | |
CN109635726B (en) | Landslide identification method based on combination of symmetric deep network and multi-scale pooling | |
CN111723773A (en) | Remnant detection method, device, electronic equipment and readable storage medium | |
CN115830490A (en) | Multi-target tracking and behavior statistical method for herd health pigs | |
CN111950499A (en) | Method for detecting vehicle-mounted personnel statistical information | |
CN107784273B (en) | Classroom seat distribution prediction method based on student social relationship model | |
CN115424217A (en) | AI vision-based intelligent vehicle identification method and device and electronic equipment | |
Thomas et al. | Smart car parking system using convolutional neural network | |
CN113673527B (en) | License plate recognition method and system | |
TWI696958B (en) | Image adaptive feature extraction method and its application | |
CN112085118A (en) | Big data classification statistical method based on image recognition technology | |
CN117079195A (en) | Wild animal identification method and system based on image video | |
CN107194352A (en) | A kind of pedestrian counting method of video monitoring, apparatus and system |
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 |