CN109190691A - The method of waste drinking bottles and pop can Classification and Identification based on deep neural network - Google Patents
The method of waste drinking bottles and pop can Classification and Identification based on deep neural network Download PDFInfo
- Publication number
- CN109190691A CN109190691A CN201810949861.2A CN201810949861A CN109190691A CN 109190691 A CN109190691 A CN 109190691A CN 201810949861 A CN201810949861 A CN 201810949861A CN 109190691 A CN109190691 A CN 109190691A
- Authority
- CN
- China
- Prior art keywords
- pop
- identification
- classification
- training
- beverage bottle
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Abstract
The present invention relates to the methods of waste drinking bottles and pop can Classification and Identification based on deep neural network, comprising the following steps: S1: shooting image, the image data of acquisition beverage bottle, pop can all angles；S2: image preprocessing；S3: image labeling is carried out using the image data of acquisition, makes training sample set and test sample collection；S4: the depth convolutional neural networks model of several numbers of plies is constructed；S5: the training sample data with mark are inputted into depth convolutional neural networks model, carry out network training；S6: training process automatically extracts feature and classifies；S7: training terminates that the identification model of a beverage bottle, pop can will be exported；S8: utilizing test sample collection, and network training result is obtained the Classification and Identification of beverage bottle, the identification model progress waste drinking bottles of pop can, pop can.The method of waste drinking bottles of the present invention based on deep neural network and pop can Classification and Identification, automatic recognition classification, identification is fast, and accuracy rate is high.
Description
Technical field
The present invention relates to artificial intelligence, are applied to environmental technology field, more particularly, to a kind of waste drinking bottles, pop can
Classifying identification method.
Background technique
Currently, method of the identification of existing beverage bottle, pop can using pattern-recognition.The method master of pattern-recognition
If being directed to beverage bottle, pop can, it is necessary to manually extract certain features of beverage bottle, pop can, and type carries out template one by one
Typing, feature mining is relatively difficult, heavy workload, and beverage bottle for deformation or pop can identification are difficult.Meanwhile if
Realize the identification of all beverage bottles, pop can, then need by all types of beverage bottles of beverage types all on the market,
Pop can all records corresponding template, this is clearly to be difficult to, while will also expend a large amount of manpower and material resources in a short time.And
And beverage that different drink brand manufacturer productions are released is being constantly updated on the market, the type and shape of beverage bottle be not yet
Disconnected update, this just causes difficulty to the method for pattern-recognition, and this difficulty is endless.
Summary of the invention
To solve the problems mentioned in the above background technology, the present invention provides the discarded beverages based on deep neural network
The method of bottle and pop can Classification and Identification, the feature for automatically extracting waste drinking bottles, pop can may be implemented using this method, and
Automatic identification, classification, identification is fast, and accuracy rate is high.
In order to solve the above technical problems, technical solution provided by the invention are as follows:
The method of waste drinking bottles and pop can Classification and Identification based on deep neural network, comprising the following steps:
S1: shooting image, the image data of acquisition beverage bottle, pop can all angles；
S2: image preprocessing；
S3: image labeling is carried out using the image data of acquisition, makes training sample set and test sample collection；
S4: the depth convolutional neural networks model of several numbers of plies is constructed；
S5: the training sample data with mark are inputted into depth convolutional neural networks model, carry out network training；
S6: training process automatically extracts feature and classifies；
S7: training terminates that the identification model of a beverage bottle, pop can will be exported；
S8: utilizing test sample collection, network training result is obtained beverage bottle, the identification model of pop can carries out discarded drink
Expect point of bottle, pop can
Class identification.
It include the operation such as convolution, activation, Chi Hua, normalization, residual error network as improved, described S4.
After using the above structure, the present invention has the advantage that
The present invention may be implemented to automatically extract waste drinking bottles, pop can feature, and automatic recognition classification, and identification is fast, quasi-
True rate is high, not only can improve the correct recognition rata of waste drinking bottles, pop can, while also improving Waste sorting recycle
Working efficiency, any waste drinking bottles, pop can are either deforming or undeformed, can Forecasting recognition go out
Come, discrimination is high, and efficiency is fast.
Detailed description of the invention
Fig. 1 is the method for the present invention flow diagram；
Fig. 2 is the depth convolutional neural networks hierarchical structure schematic diagram that the present invention constructs；
Fig. 3 is the Inception-ResNet residual error network in the depth convolutional neural networks hierarchical structure that the present invention constructs
Module diagram；
Fig. 4 is the Inception-Reduction mould in the depth convolutional neural networks ginseng hierarchical structure that the present invention constructs
Block schematic diagram；
Fig. 5 is depth convolutional neural networks operating principle schematic diagram of the present invention；
Fig. 6 is inventive network training process schematic diagram；
Specific embodiment
Present invention will be described in further detail below with reference to the accompanying drawings.
In conjunction with attached drawing 1,2,3,4,5,6, the side of waste drinking bottles and pop can Classification and Identification based on deep neural network
Method, comprising the following steps:
S1: shooting image acquires the image data of various waste drinking bottles, pop can；
S2: image preprocessing achievees the purpose that norm image and expands data volume；
S3: the beverage bottle that the band of 9000 various forms marks, pop can picture are chosen as training dataset；
S4: the operation such as building depth convolutional neural networks model, including convolution, activation, Chi Hua, normalization, residual error network；
S5: the picture of tape label is inputted into depth convolutional neural networks, is trained；
S6: training process carries out automatically extracting feature and classify to beverage bottle, the pop can of various forms；
S7: training terminates that a beverage bottle will be exported, (identification model is depth convolutional Neural net to the identification model of pop can
The feature weight that network obtains after training)；
S8: network training result is obtained into point of beverage bottle, the identification model progress waste drinking bottles of pop can, pop can
Class identification.
The present invention and its embodiments have been described above, this description is no restricted, shown in the drawings
Only one of embodiments of the present invention, actual structure is not limited to this.All in all if the ordinary skill of this field
Personnel are enlightened by it, without departing from the spirit of the invention, are not inventively designed and the technical solution phase
As frame mode and embodiment, be within the scope of protection of the invention.
Claims (2)
1. the method for waste drinking bottles and pop can Classification and Identification based on deep neural network, which is characterized in that including following
Step:
S1: shooting image, the image data of acquisition beverage bottle, pop can all angles；
S2: image preprocessing；
S3: image labeling is carried out using the image data of acquisition, makes training sample set and test sample collection；
S4: the depth convolutional neural networks model of several numbers of plies is constructed；
S5: the training sample data with mark are inputted into depth convolutional neural networks model, carry out network training；
S6: training process automatically extracts feature and classifies；
S7: training terminates that the identification model of a beverage bottle, pop can will be exported；
S8: utilizing test sample collection, network training result is obtained beverage bottle, the identification model of pop can carries out discarded beverage
The Classification and Identification of bottle, pop can.
2. the method for the waste drinking bottles according to claim 1 based on deep neural network and pop can Classification and Identification,
It is characterized by: the S4 includes convolution, activation, pond and normalization operation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810949861.2A CN109190691A (en) | 2018-08-20 | 2018-08-20 | The method of waste drinking bottles and pop can Classification and Identification based on deep neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810949861.2A CN109190691A (en) | 2018-08-20 | 2018-08-20 | The method of waste drinking bottles and pop can Classification and Identification based on deep neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109190691A true CN109190691A (en) | 2019-01-11 |
Family
ID=64918482
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810949861.2A Pending CN109190691A (en) | 2018-08-20 | 2018-08-20 | The method of waste drinking bottles and pop can Classification and Identification based on deep neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109190691A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109934255A (en) * | 2019-01-22 | 2019-06-25 | 小黄狗环保科技有限公司 | A kind of Model Fusion method for delivering object Classification and Identification suitable for beverage bottle recycling machine |
| CN110047067A (en) * | 2019-04-02 | 2019-07-23 | 广州大学 | A kind of shoulder detection method for bottle classification |
| CN110866561A (en) * | 2019-11-18 | 2020-03-06 | 佛山市南海区广工大数控装备协同创新研究院 | Plastic bottle color sorting method based on image recognition |
| CN110909660A (en) * | 2019-11-19 | 2020-03-24 | 佛山市南海区广工大数控装备协同创新研究院 | Plastic bottle detection and positioning method based on target detection |
| CN111144480A (en) * | 2019-12-25 | 2020-05-12 | 深圳蓝胖子机器人有限公司 | Visual classification method, system and equipment for recyclable garbage |
| CN111652214A (en) * | 2020-05-26 | 2020-09-11 | 佛山市南海区广工大数控装备协同创新研究院 | Garbage bottle sorting method based on deep learning |
| CN111931557A (en) * | 2020-06-19 | 2020-11-13 | 广州图匠数据科技有限公司 | Specification identification method and device for bottled drink, terminal equipment and readable storage medium |
| CN112418083A (en) * | 2020-11-23 | 2021-02-26 | 深兰人工智能(四川)有限公司 | Bucket classification method and classification device |
| CN112445924A (en) * | 2019-09-04 | 2021-03-05 | 天津职业技术师范大学(中国职业培训指导教师进修中心) | Data mining and transfer learning system based on internet picture resources and method and application thereof |
| CN112591333A (en) * | 2020-12-11 | 2021-04-02 | 江西理工大学 | Automatic garbage classification device and method based on artificial intelligence |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8873813B2 (en) * | 2012-09-17 | 2014-10-28 | Z Advanced Computing, Inc. | Application of Z-webs and Z-factors to analytics, search engine, learning, recognition, natural language, and other utilities |
| CN105320957A (en) * | 2014-07-10 | 2016-02-10 | 腾讯科技（深圳）有限公司 | Classifier training method and device |
| CN106204646A (en) * | 2016-07-01 | 2016-12-07 | 湖南源信光电科技有限公司 | Multiple mobile object tracking based on BP neutral net |
| CN106778902A (en) * | 2017-01-03 | 2017-05-31 | 河北工业大学 | Milk cow individual discrimination method based on depth convolutional neural networks |
| US20180137338A1 (en) * | 2016-11-16 | 2018-05-17 | The Governing Council Of The University Of Toronto | System and method for classifying and segmenting microscopy images with deep multiple instance learning |
| CN108182455A (en) * | 2018-01-18 | 2018-06-19 | 齐鲁工业大学 | A kind of method, apparatus and intelligent garbage bin of the classification of rubbish image intelligent |
| WO2018127498A1 (en) * | 2017-01-05 | 2018-07-12 | Koninklijke Philips N.V. | Ultrasound imaging system with a neural network for image formation and tissue characterization |
-
2018
- 2018-08-20 CN CN201810949861.2A patent/CN109190691A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8873813B2 (en) * | 2012-09-17 | 2014-10-28 | Z Advanced Computing, Inc. | Application of Z-webs and Z-factors to analytics, search engine, learning, recognition, natural language, and other utilities |
| CN105320957A (en) * | 2014-07-10 | 2016-02-10 | 腾讯科技（深圳）有限公司 | Classifier training method and device |
| CN106204646A (en) * | 2016-07-01 | 2016-12-07 | 湖南源信光电科技有限公司 | Multiple mobile object tracking based on BP neutral net |
| US20180137338A1 (en) * | 2016-11-16 | 2018-05-17 | The Governing Council Of The University Of Toronto | System and method for classifying and segmenting microscopy images with deep multiple instance learning |
| CN106778902A (en) * | 2017-01-03 | 2017-05-31 | 河北工业大学 | Milk cow individual discrimination method based on depth convolutional neural networks |
| WO2018127498A1 (en) * | 2017-01-05 | 2018-07-12 | Koninklijke Philips N.V. | Ultrasound imaging system with a neural network for image formation and tissue characterization |
| CN108182455A (en) * | 2018-01-18 | 2018-06-19 | 齐鲁工业大学 | A kind of method, apparatus and intelligent garbage bin of the classification of rubbish image intelligent |
Non-Patent Citations (1)
| Title |
|---|
| 徐勇 等: "基于神经网络的垃圾邮件协同识别研究", 《网络与通信》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109934255A (en) * | 2019-01-22 | 2019-06-25 | 小黄狗环保科技有限公司 | A kind of Model Fusion method for delivering object Classification and Identification suitable for beverage bottle recycling machine |
| CN109934255B (en) * | 2019-01-22 | 2023-05-30 | 小黄狗环保科技有限公司 | Model fusion method suitable for classification and identification of delivered objects of beverage bottle recycling machine |
| CN110047067A (en) * | 2019-04-02 | 2019-07-23 | 广州大学 | A kind of shoulder detection method for bottle classification |
| CN110047067B (en) * | 2019-04-02 | 2021-06-22 | 广州大学 | Bottle shoulder detection method for bottle classification |
| CN112445924A (en) * | 2019-09-04 | 2021-03-05 | 天津职业技术师范大学(中国职业培训指导教师进修中心) | Data mining and transfer learning system based on internet picture resources and method and application thereof |
| CN110866561A (en) * | 2019-11-18 | 2020-03-06 | 佛山市南海区广工大数控装备协同创新研究院 | Plastic bottle color sorting method based on image recognition |
| CN110909660A (en) * | 2019-11-19 | 2020-03-24 | 佛山市南海区广工大数控装备协同创新研究院 | Plastic bottle detection and positioning method based on target detection |
| CN111144480A (en) * | 2019-12-25 | 2020-05-12 | 深圳蓝胖子机器人有限公司 | Visual classification method, system and equipment for recyclable garbage |
| CN111652214A (en) * | 2020-05-26 | 2020-09-11 | 佛山市南海区广工大数控装备协同创新研究院 | Garbage bottle sorting method based on deep learning |
| CN111931557A (en) * | 2020-06-19 | 2020-11-13 | 广州图匠数据科技有限公司 | Specification identification method and device for bottled drink, terminal equipment and readable storage medium |
| CN112418083A (en) * | 2020-11-23 | 2021-02-26 | 深兰人工智能(四川)有限公司 | Bucket classification method and classification device |
| CN112591333A (en) * | 2020-12-11 | 2021-04-02 | 江西理工大学 | Automatic garbage classification device and method based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109190691A (en) | The method of waste drinking bottles and pop can Classification and Identification based on deep neural network | |
| CN108765404B (en) | A kind of road damage testing method and device based on deep learning image classification | |
| CN102043945B (en) | License plate character recognition method based on real-time vehicle tracking and binary index classification | |
| CN109064304A (en) | Finance reimbursement bill automated processing system and method | |
| US10679067B2 (en) | Method for detecting violent incident in video based on hypergraph transition | |
| CN103325125A (en) | Moving target tracking method based on improved multi-example learning algorithm | |
| CN103699523A (en) | Product classification method and device | |
| CN101221623B (en) | Object type on-line training and recognizing method and system thereof | |
| CN101980245B (en) | Adaptive template matching-based passenger flow statistical method | |
| CN104021375A (en) | Model identification method based on machine learning | |
| CN102902967A (en) | Method for positioning iris and pupil based on eye structure classification | |
| CN106355180B (en) | A kind of license plate locating method combined based on color with edge feature | |
| CN104636761A (en) | Image semantic annotation method based on hierarchical segmentation | |
| CN109934255A (en) | A kind of Model Fusion method for delivering object Classification and Identification suitable for beverage bottle recycling machine | |
| CN102521561A (en) | Face identification method on basis of multi-scale weber local features and hierarchical decision fusion | |
| CN105095475A (en) | Incomplete attribute tagged pedestrian re-identification method and system based on two-level fusion | |
| CN109492105A (en) | A kind of text sentiment classification method based on multiple features integrated study | |
| CN108829810A (en) | File classification method towards healthy public sentiment | |
| CN109086772A (en) | A kind of recognition methods and system distorting adhesion character picture validation code | |
| CN110674844A (en) | Intelligent container increment learning training method | |
| CN111814687A (en) | Flight support node intelligent identification system | |
| CN109033971A (en) | A kind of efficient pedestrian recognition methods again based on residual error Network Theory | |
| Borianne et al. | Deep Mangoes: from fruit detection to cultivar identification in colour images of mango trees | |
| CN110508510A (en) | A kind of plastic pump defect inspection method, apparatus and system | |
| CN109670019A (en) | Intelligent search method and device based on Technique Using Both Text identification |
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: 20190111 |