CN108537280A - A kind of bulk commodity charge system based on machine vision - Google Patents

A kind of bulk commodity charge system based on machine vision Download PDF

Info

Publication number
CN108537280A
CN108537280A CN201810327841.1A CN201810327841A CN108537280A CN 108537280 A CN108537280 A CN 108537280A CN 201810327841 A CN201810327841 A CN 201810327841A CN 108537280 A CN108537280 A CN 108537280A
Authority
CN
China
Prior art keywords
module
bulk commodity
machine vision
system based
charge system
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
Application number
CN201810327841.1A
Other languages
Chinese (zh)
Inventor
王云飞
毛雯歆
薛伟洁
张黎燕
孟银娜
严剑冰
张春丽
段朝磊
赵伟伟
朱相帛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Henan Mechanical and Electrical Vocational College
Original Assignee
Henan Mechanical and Electrical Vocational College
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Henan Mechanical and Electrical Vocational College filed Critical Henan Mechanical and Electrical Vocational College
Priority to CN201810327841.1A priority Critical patent/CN108537280A/en
Publication of CN108537280A publication Critical patent/CN108537280A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/24Classification techniques
    • G06F18/241Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2413Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
    • G06F18/24147Distances to closest patterns, e.g. nearest neighbour classification
    • GPHYSICS
    • G01MEASURING; TESTING
    • G01GWEIGHING
    • G01G19/00Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups
    • G01G19/40Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups with provisions for indicating, recording, or computing price or other quantities dependent on the weight
    • G01G19/413Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups with provisions for indicating, recording, or computing price or other quantities dependent on the weight using electromechanical or electronic computing means
    • G01G19/414Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups with provisions for indicating, recording, or computing price or other quantities dependent on the weight using electromechanical or electronic computing means using electronic computing means only
    • G01G19/415Weighing apparatus or methods adapted for special purposes not provided for in the preceding groups with provisions for indicating, recording, or computing price or other quantities dependent on the weight using electromechanical or electronic computing means using electronic computing means only combined with recording means
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/40Extraction of image or video features
    • G06V10/44Local 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
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00Arrangements for image or video recognition or understanding
    • G06V10/40Extraction of image or video features
    • G06V10/48Extraction of image or video features by mapping characteristic values of the pattern into a parameter space, e.g. Hough transformation

Abstract

A kind of bulk commodity charge system based on machine vision:Including photographing module;Image processing module;Identification module;Communication module;Weighing module;Charging module;Output module.The beneficial effects of the invention are as follows:It is identified based on closest template matching algorithm, Database is convenient, only needs single sample.Bulk commodity charge system based on machine vision, reduces the step of being manually entered type of merchandize, instead Machine Vision Recognition type of merchandize and weight, and is sent to charging module according to communication protocol, completes charging.For businessman, reduce human cost and customer's queuing time;For staff, reduce cumbersome uninteresting labour;For consumer, consumption time has been saved, has optimized consumption experience.

Description

A kind of bulk commodity charge system based on machine vision
Technical field
The present invention relates to field of artificial intelligence, specially a kind of bulk commodity charge system based on machine vision.
Background technology
Due to being difficult to directly stamp price tag on bulk commodity, such as apple, rice, bulk commodity meter at present Take, needs to arrange for staff and identify type of merchandize and input computer charging, consumer needs to wait in line, and expends in the extreme Time and efforts.Businessman's human cost is high, and staff is cumbersome, and consumer's time cost is high, experience is poor.With artificial intelligence The every aspect that energy technology enters life can be reduced using Machine Vision Recognition type of merchandize or quantity and be manually entered commodity The step of type, and it is sent to charging module according to communication protocol, export price information completes charging.For businessman, reduce Human cost and customer's queuing time;For staff, reduce cumbersome uninteresting labour;For consumer, saves and disappeared It is time-consuming, optimize consumption experience.
Invention content
To solve the above problems, the present invention provides a kind of bulk commodity charge system based on machine vision.
Technical scheme of the present invention is specially:
A kind of bulk commodity charge system based on machine vision:Including photographing module, pass through camera lens, light source and camera handle The optical image of bulk commodity is converted to digital signal image;Image processing module, to the digital signaling diagram of photographing module shooting As carrying out image segmentation and feature extraction;Identification module is based on closest template matching algorithm, identification image processing module processing Data afterwards identify the species characteristic of bulk commodity, and the species characteristic of commodity are sent to communication module;Communication module pair The information received is sent to Weighing module after carrying out communications protocol conversion;Weighing module obtains the commodity of identification module identification The weight of bulk commodity is weighed after information, and weight information is sent to charging module by communication module;Charging module, Charging is completed according to the type of merchandize unit price of storage and the commodity weight according to the type of the bulk commodity received;Export mould Block, output type of merchandize, unit price, weight and total price information.
Further:The communication module reserves external communication interface.
Further:Also have Merchandise Template property data base, Merchandise Template property data base respectively with identification module and Communication module connects.
Further:Image processing module carries out feature extraction using PCA-SIFT methods.
Further:Identification module, using closest template matching algorithm, identify bulk commodity species characteristic or Quantity.
Further:Image processing module carries out edge detection using Canny detection methods.
Further:Image processing module carries out edge detection using Hough transform detection method.
Compared with prior art, the beneficial effects of the invention are as follows:It is identified based on closest template matching algorithm, data It is convenient that library is established, and only needs single sample.Bulk commodity charge system based on machine vision, reduces and is manually entered type of merchandize The step of, instead Machine Vision Recognition type of merchandize and quantity, and it is sent to charging module according to communication protocol, complete meter Take.For businessman, reduce human cost and customer's queuing time;For staff, reduce cumbersome uninteresting labour;It is right In consumer, consumption time has been saved, has optimized consumption experience.
Description of the drawings
Fig. 1 is that a kind of structure diagram of bulk commodity charge system based on machine vision of the present invention (is suitable for by kind The commodity that class sum number gauge takes).
Fig. 2 is that a kind of structure diagram of bulk commodity charge system based on machine vision of the present invention (is suitable for by kind The commodity of class and weight charging).
Specific implementation mode
Embodiment 1:
A kind of bulk commodity charge system based on machine vision, including photographing module (1), pass through camera lens, light source and phase The optical image of bulk commodity is converted to digital signal image by machine, and image processing module (2) carries out figure to digital signal pattern As segmentation and feature extraction, the wherein use PCA-SIFT methods of feature extraction, identification module (3) is based on closest template With algorithm, identify that the species characteristic or quantity of bulk commodity, communication module (4) are sent to type number information and weigh Module is sent to charging module, charging module the weight information obtained from Weighing module, or type and quantity information (5), charging is completed according to type unit price and weight or quantity, output module (6), output class, unit price, weight or quantity and total Valence information confirms for consumer, completes charging.
Such as the above-mentioned bulk commodity charge system based on machine vision, concrete principle and feature are as follows:
(1) optical image of bulk commodity is converted into digital signaling diagram by photographing module by light source, camera lens and camera Picture:Light source illuminates target, improves brightness so that camera lens collects image with distinct contrast, causes the effect for being conducive to image procossing Fruit.Shots are irradiated the reflected light of commodity by light source, and focus on the photosurface of imaging sensor of camera.Camera CCD (Charge Coupled Device) or CMOS (Complementary Metal Oxide Semiconductor) image Optical image is converted into digital signal image by sensor by opto-electronic conversion, charge storage, electric charge transfer and signal-obtaining, and Send image processing module to.
(2) image processing module carries out image segmentation and feature extraction to digital signal pattern:According to each position of image RGB color and edge, edge detection is detected using Canny or Hough transform detection, divides the image into different regions. According to color and edge bulk commodity and shopping bag and background separation come.Feature extraction is from the region in bulk split In, using PCA-SIFT methods, extract the crucial point feature of bulk commodity.
(3) identification module automatically identifies the species characteristic or number of bulk commodity using closest template matching algorithm Amount:The feature of extraction is matched with the template characteristic of the extensive stock stored in database.Template T (m, n) in feature The subgraph S covered in figureijThe aberration of (m, n) is:
First item is the energy of subgraph in formula, and (i, j) is characterized image vegetarian refreshments coordinate, and (m, n) is template pixel point coordinates. Section 3 is the energy of template, all unrelated with template matches.Section 2 is that template is related each other to subgraph, is changed with (i, j) Become.When template and subgraph match, this is by maximum value.After being normalized, the related coefficient of template matches is obtained:
When template and just the same subgraph, coefficient R (i, j)=1.After all search being completed in searched figure S, Find out the maximum value Rmax (i, j) of R, corresponding subgraph Sij(m, n) is to match target, and type is determined with this.And big Mr. Yu The quantity of one threshold value as matches the quantity of target.
(4) communication module carries out data communication protocol conversion, type and quantity to identification module, charging module data Information is sent to charging module:By network interface or serial ports (including USB port), the type of bulk commodity is compiled according to communication protocol Number, quantity information be sent to charging module.By reserved external communication interface, Merchandise Template property data base is updated It is read out with to identification module, charging module, Weighing module data.
(5) charging module completes charging according to type unit price and weight or quantity:Total price=unit price × weight, Huo Zhezong Valence=unit price 1 × quantity 1+ unit price 2 × quantity 2+ 3 × quantity of unit price 3+ ....
(6) output module, output class, unit price, weight or quantity and total price information confirm for consumer, complete charging: Pass through printing device printing or display screen display of commodity label bar code and type, unit price, weight or quantity and total price information.
Embodiment 2:
A kind of bulk commodity charge system based on machine vision, can also increase Weighing module, Weighing module is identified The weight of bulk commodity is weighed after the type of merchandize information of module identification, and weight information is sent to charging module.
Weighing module is communicated by communication module and identification module, charging module.
Communication module, symmetrical weight module data carry out data communication protocol conversion, type number information are sent to and is weighed Module, the weight information obtained from Weighing module, by network interface or serial ports (including USB port), according to communication protocol in bulk The type number of commodity, weight information are sent to charging module.
Specific work process:
As shown in Figure 1, when being settled accounts with chafing dish restaurant, for the bamboo stick by type and quantity charging, after consumer completes feed, Waiter tiles bamboo stick and be intensively placed on certain on dining table starts billing operation with mobile phone open charge system.Through Light source, i.e. mobile phone flashlight irradiate, lens focus, and the camera in camera module is converted to bamboo stick and appendicular shadow signal Digital signal image, and it is sent to image processing module.Image processing module is according to the RGB color and edge of bamboo stick, edge inspection It surveys and is detected using Hough transform, divide the image into different regions, and isolate the region where bamboo stick.Using PCA- SIFT methods extract product features.Identification module by with each template matches in bulk commodity database, confirm bamboo stick Type and quantity, and type number information and quantity information are sent to by communication module by charging module, charging module according to Information transfers the unit price of food representated by various bamboo sticks, and according to quantity information, according to formula:Total price=unit price 1 × number 1+ unit price 2 × quantity 2+ unit price 3 × quantity 3+ ... are measured, total price is calculated.Output module shows various bamboos on mobile phone screen Label represent unit price, quantity and the total price information of food.After consumer watches confirmation, charging is completed.
As shown in Fig. 2, by taking supermarket's certain apple for sale as an example, after consumer chooses, it is placed on charge system region, is passed through Light source irradiates, lens focus, and the appendicular shadow signal of apple and periphery is converted to digital signal by the camera in camera module Image, and it is sent to image processing module.Image processing module presses commodity, residual leaf, the plastic shopping bag and background for filling commodity According to the RGB color and edge at each position, edge detection is detected using Canny, divides the image into different regions.And it isolates Region where commodity.Product features are extracted using PCA-SIFT methods.Identification module by in bulk commodity database Each template matches calculate the matching related coefficient 0.99 with certain apple template, are maximum value.Confirm that selected commodity are certain Kind apple, and type number information is sent to communication module.Communication module and Weighing module are through network interface or serial ports (including USB Mouthful) interaction, the weight information of apple is obtained, information and weight information are then sent to charging module, charging module root The unit price of certain apple is transferred according to information, and calculates total price according to weight information.The printing device of output module prints The label bar code and type of certain apple of label, unit price, weight and total price information are affixed on shopping and take after consumer confirms, complete At charging.
As shown in Fig. 2, by taking supermarket's certain rice for sale as an example, after consumer chooses, it is placed on charge system region, is passed through Light source irradiates, lens focus, and the appendicular shadow signal of rice and periphery is converted to digital signal by the camera in camera module Image, and it is sent to image processing module.Image processing module presses commodity, residual leaf, the plastic shopping bag and background for filling commodity According to the RGB color and edge at each position, edge detection is detected using Canny, divides the image into different regions.And it isolates Region where commodity.Product features are extracted using PCA-SIFT methods.Identification module by in bulk commodity database Each template matches calculate the matching related coefficient 0.97 with certain rice template, are maximum value.Confirm that selected commodity are certain Kind rice, and type number information is sent to communication module.Communication module and Weighing module are through network interface or serial ports (including USB Mouthful) interaction, the weight information of rice is obtained, information and weight information are then sent to charging module, charging module root The unit price of certain rice is transferred according to information, and calculates total price according to weight information.The printing device of output module prints The label bar code and type of certain rice of label, unit price, weight and total price information are affixed on shopping and take after consumer confirms, complete At charging.
The present invention reduces type of merchandize is manually entered, instead Machine Vision Recognition type of merchandize or quantity, And charging module is sent to by communication protocol, complete charging.For businessman, reduce human cost and customer's queuing time; For staff, reduce cumbersome uninteresting labour;For consumer, consumption time has been saved, has optimized consumption experience.Quotient Family, staff, consumer have nothing in common with each other the benefit of degree, and charging process is more intelligent, is a kind of very promising charging System.
What has been described above is only a preferred embodiment of the present invention, it is noted that for those skilled in the art, Under the premise of not departing from general idea of the present invention, several changes and improvements can also be made, these should also be considered as the present invention's Protection domain.

Claims (7)

1. a kind of bulk commodity charge system based on machine vision, it is characterised in that:Including photographing module, pass through camera lens, light The optical image of bulk commodity is converted to digital signal image by source and camera;Image processing module, to photographing module shooting Digital signal image carries out image segmentation and feature extraction;Identification module is based on closest template matching algorithm, identifies at image The data after resume module are managed, identify the species characteristic of bulk commodity, and the species characteristic of commodity is sent to communication module; Communication module is sent to Weighing module after carrying out communications protocol conversion to the information received;Weighing module obtains identification module The weight of bulk commodity is weighed after the type of merchandize information of identification, and weight information is sent to charging mould by communication module Block;Charging module is completed according to the type of the bulk commodity received according to the type of merchandize unit price of storage and the commodity weight Charging;Output module, output type of merchandize, unit price, weight and total price information.
2. a kind of bulk commodity charge system based on machine vision as described in claim 1, it is characterised in that:The communication Module reserves external communication interface.
3. a kind of bulk commodity charge system based on machine vision as described in claim 1, it is characterised in that:Also there is quotient Product template characteristic database, Merchandise Template property data base are connect with identification module and communication module respectively.
4. a kind of bulk commodity charge system based on machine vision as described in claim 1, it is characterised in that:Image procossing Module carries out feature extraction using PCA-SIFT methods.
5. a kind of bulk commodity charge system based on machine vision as described in claim 1, it is characterised in that:Identify mould Block identifies the species characteristic or quantity of bulk commodity using closest template matching algorithm.
6. a kind of bulk commodity charge system based on machine vision as described in claim 1, it is characterised in that:Image procossing Module carries out edge detection using Canny detection methods.
7. a kind of bulk commodity charge system based on machine vision as described in claim 1, it is characterised in that:Image procossing Module carries out edge detection using Hough transform detection method.
CN201810327841.1A 2018-04-12 2018-04-12 A kind of bulk commodity charge system based on machine vision Pending CN108537280A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810327841.1A CN108537280A (en) 2018-04-12 2018-04-12 A kind of bulk commodity charge system based on machine vision

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810327841.1A CN108537280A (en) 2018-04-12 2018-04-12 A kind of bulk commodity charge system based on machine vision

Publications (1)

Publication Number Publication Date
CN108537280A true CN108537280A (en) 2018-09-14

Family

ID=63480225

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810327841.1A Pending CN108537280A (en) 2018-04-12 2018-04-12 A kind of bulk commodity charge system based on machine vision

Country Status (1)

Country Link
CN (1) CN108537280A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111750965A (en) * 2019-03-27 2020-10-09 杭州海康威视数字技术股份有限公司 Commodity self-service charging method, device and system
CN111967942A (en) * 2020-08-20 2020-11-20 渭南双盈未来科技有限公司 Intelligent shopping method
CN112801578A (en) * 2021-01-18 2021-05-14 哈尔滨工业大学 Commodity warehousing and ex-warehouse management system and method applied to individual vendor

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104240411A (en) * 2014-07-23 2014-12-24 南京工程学院 Intelligent shopping device for supermarket commodities in bulk
EP3118793A1 (en) * 2015-07-15 2017-01-18 Toshiba TEC Kabushiki Kaisha Commodity-sales-data processing apparatus, comodity-sales-data processing method
CN106980885A (en) * 2017-03-17 2017-07-25 杭州竞立智能科技有限公司 A kind of commodity charge system and method
CN106991554A (en) * 2017-03-17 2017-07-28 杭州竞立智能科技有限公司 A kind of commodity management system and method
CN107478315A (en) * 2017-08-28 2017-12-15 云保(佛山)智控科技有限公司 One kind mixing bulk commodity is weighed pricing system automatically
CN107767590A (en) * 2016-08-16 2018-03-06 深圳仪普生科技有限公司 Automatic identification commercialization bar code electronic scale and Automatic identification method

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104240411A (en) * 2014-07-23 2014-12-24 南京工程学院 Intelligent shopping device for supermarket commodities in bulk
EP3118793A1 (en) * 2015-07-15 2017-01-18 Toshiba TEC Kabushiki Kaisha Commodity-sales-data processing apparatus, comodity-sales-data processing method
CN107767590A (en) * 2016-08-16 2018-03-06 深圳仪普生科技有限公司 Automatic identification commercialization bar code electronic scale and Automatic identification method
CN106980885A (en) * 2017-03-17 2017-07-25 杭州竞立智能科技有限公司 A kind of commodity charge system and method
CN106991554A (en) * 2017-03-17 2017-07-28 杭州竞立智能科技有限公司 A kind of commodity management system and method
CN107478315A (en) * 2017-08-28 2017-12-15 云保(佛山)智控科技有限公司 One kind mixing bulk commodity is weighed pricing system automatically

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111750965A (en) * 2019-03-27 2020-10-09 杭州海康威视数字技术股份有限公司 Commodity self-service charging method, device and system
CN111967942A (en) * 2020-08-20 2020-11-20 渭南双盈未来科技有限公司 Intelligent shopping method
CN112801578A (en) * 2021-01-18 2021-05-14 哈尔滨工业大学 Commodity warehousing and ex-warehouse management system and method applied to individual vendor

Similar Documents

Publication Publication Date Title
CN104361698B (en) Self-help intelligent electronic-weighing settlement method and system
CN107084780A (en) A kind of intelligent electronic-scale and corresponding Weighing method
US11461753B2 (en) Automatic vending method and apparatus, and computer-readable storage medium
CN108537280A (en) A kind of bulk commodity charge system based on machine vision
CN103295034B (en) A kind of embedded Books Chaotic Frame checking system based on DSP and method
CN102063616A (en) Automatic identification system and method for commodities based on image feature matching
CN107167221A (en) The agricultural product source tracing method and intelligent electronic-scale of a kind of utilization intelligent electronic-scale
CN107767590A (en) Automatic identification commercialization bar code electronic scale and Automatic identification method
CN104296852A (en) Self-service weighing method and apparatus for fruit and vegetable commodities
US10948338B2 (en) Digital product label generation using modular scale device
CN112466068A (en) Intelligent weighing device and intelligent weighing method based on computer vision technology
CN108663105A (en) A kind of weighing device and corresponding weighing method
CN202720035U (en) Barcode scanning radio frequency identification price computing scale
CN110852733A (en) Intelligent catering settlement system based on RFID fusion dish image matching identification
CN111832590B (en) Article identification method and system
CN107730321A (en) A kind of identification pricing system based on canteen characteristics of image
CN109544791A (en) The automatic vending mode of weighing cubby
CN209216227U (en) Intelligent checkout station
CN109635705A (en) A kind of commodity recognition method and device based on two dimensional code and deep learning
CN214202398U (en) Express delivery intelligence networking security equipment
CN208223620U (en) A kind of intelligent recognition is weighed the electronic scale of Automatic-settlement automatically
CN109345733A (en) The pricing method and system of intelligent scale
CN108520280A (en) A kind of bulk commodity charge system based on machine vision
CN109344926A (en) Processing method, device and the equipment of service receipt information
CN108734458A (en) A kind of supermarket market energy-saving anti-theft automatic identification is weighed settlement method 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
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20180914