WO2002032795A1 - Procede et dispositif d'identification de marchandises - Google Patents

Procede et dispositif d'identification de marchandises Download PDF

Info

Publication number
WO2002032795A1
WO2002032795A1 PCT/JP2000/007197 JP0007197W WO0232795A1 WO 2002032795 A1 WO2002032795 A1 WO 2002032795A1 JP 0007197 W JP0007197 W JP 0007197W WO 0232795 A1 WO0232795 A1 WO 0232795A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
information
image data
imaging means
baggage
Prior art date
Application number
PCT/JP2000/007197
Other languages
English (en)
Japanese (ja)
Inventor
Tomoaki Hachiya
Yasunobu Harada
Yuuichi Komazawa
Original Assignee
Technowave, Ltd.
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 Technowave, Ltd. filed Critical Technowave, Ltd.
Priority to PCT/JP2000/007197 priority Critical patent/WO2002032795A1/fr
Publication of WO2002032795A1 publication Critical patent/WO2002032795A1/fr

Links

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
    • B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
    • B07C3/00—Sorting according to destination
    • B07C3/10—Apparatus characterised by the means used for detection ofthe destination
    • B07C3/14—Apparatus characterised by the means used for detection ofthe destination using light-responsive detecting means
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
    • B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
    • B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
    • B07C5/34—Sorting according to other particular properties
    • B07C5/3412—Sorting according to other particular properties according to a code applied to the object which indicates a property of the object, e.g. quality class, contents or incorrect indication
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition
    • G06V30/14—Image acquisition
    • G06V30/1444—Selective acquisition, locating or processing of specific regions, e.g. highlighted text, fiducial marks or predetermined fields
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition

Definitions

  • the present invention relates to a package recognition device for identifying information such as characters and graphics described on a package surface for a package flowing on a distribution conveyor or the like.
  • the present invention has been made to solve the above problems, and has as its object to use a dedicated reading description, to temporarily stop the system, to share image data,
  • the purpose of the present invention is to provide a device capable of recognizing a package by reading information on characters and figures written on a surface. Disclosure of the invention
  • An apparatus for identifying baggage surface information of a baggage moving along a flow path wherein first imaging means arranged on the upstream side of the flow path,
  • Second imaging means arranged on the downstream side, First image processing means for processing image data of the baggage surface captured from the first imaging means;
  • Second image processing means for processing image data of the baggage surface captured from the second imaging means
  • An apparatus having first image processing means and information transmission means between the second image processing means,
  • the first imaging means captures the baggage surface and captures it as image data
  • the first image processing means determines an area in which information to be recognized is described in the image data of the baggage surface captured from the first imaging means, and transmits the position information of the area to the information transmitting means.
  • the second imaging means transmits the same luggage surface as the one imaged by the first imaging means again and captures it as image data.
  • the second image processing means performs baggage surface information recognition processing based on the image data of the baggage surface captured from the second imaging means based on the position information of the area. Device.
  • the most significant feature of the present invention is that the same package surface is imaged twice or more for the cargo flowing through the flow path in a distribution system or the like, and in the processing of the second and subsequent captured images, the analysis result of the previous imaging is obtained. The point is to use it.
  • the present invention has been made based on the idea of performing recognition processing on information narrowed down by processing. According to this, since each image processing means only needs to perform a limited process, the amount of each process can be reduced.
  • the luggage surface For example, first, image the luggage surface once, and then roughly grasp where the information (such as characters (including numbers) or figures) to be recognized is drawn on the luggage surface.
  • the analysis for the recognition is performed only for the position where the character or the graphic to be recognized is determined to be drawn using the position information.
  • a publicly-known image recognition technique may be appropriately used as a method for extracting a position where a character or a figure is described on the imaged surface of the package.
  • a known character / graphic recognition technology may be appropriately used as a method for recognizing a character / graphic described at the position.
  • processing using a plurality of processing means can be performed without transferring a large amount of data or sharing the data with a plurality of CPUs. Since only limited information such as position information is transmitted from the first image processing means to the second image processing means, much less information is transmitted than when the captured image information itself is transmitted. Transmission is sufficient and delay problems are less likely to occur. As described above, data obtained by re-imaging can be used instead of data transfer, etc. in a system in which an object moves on a flow path, such as a distribution system, on a flow path such as a belt conveyor.
  • the number of imaging means and image processing means is not limited to two, and may be three or more. Image data may be read for each image processing unit.
  • the transmission of the position information from the first image processing unit to the second image processing unit may be performed before or after the acquisition of the image information by the second imaging unit.
  • the communication does not need to be performed directly, and it is sufficient that the communication is finally secured.
  • a first luggage detection sensor for generating a signal to be a trigger for imaging by the first imaging means
  • a second luggage detecting sensor for generating a signal to be a trigger for imaging by the second imaging means
  • an object of the present invention is to provide a baggage detection sensor corresponding to each imaging unit, and to perform imaging at the same timing after detecting that a baggage has flowed.
  • the invention described in claim 3 is:
  • the physical distribution system includes a physical information processing device that performs information processing for physical distribution control using information from the identification device.
  • a physical information processing device that performs information processing for physical distribution control using information from the identification device.
  • various kinds of information of the target luggage can be obtained.
  • an information processing device such as a computer that supervises distribution control
  • advanced information such as branching and distribution of luggage can be obtained.
  • a logistics system with functions can be realized.
  • This is a method for identifying the baggage surface information in a physical distribution conveyor.
  • This invention is an invention of a method for identifying packages in a distribution system based on the same idea as the invention described in claim 1.
  • FIG. 1 (a) and 1 (b) are schematic perspective views showing a system configuration and an operation process of a character identification device according to the present invention.
  • FIG. 2 is a perspective view of the baggage subject to the same character identification.
  • FIGS. 3 (a) and 3 (b) are flow charts showing operation procedures of the first and second image reading devices.
  • FIGS. 4 (a) to (d) are explanatory diagrams showing the processing procedure of the first image processing unit.
  • FIGS. 5 (a) and 5 (b) are explanatory diagrams showing a processing procedure subsequent to FIG.
  • FIGS. 6 (a;) and (b) are explanatory diagrams showing the processing procedure of the second image processing unit. Explanation of reference numerals
  • FIG. 1 shows an apparatus configuration in a case where the present invention is applied to a character reading apparatus printed or affixed to a side surface of a package flowing on a conveyor line.
  • Reference numeral 1 denotes a belt conveyor on which goods are sequentially circulated.
  • Figures (a) and (b) show temporal changes.
  • the baggage W is, for example, a corrugated pole in which the corresponding product is packed.
  • the baggage W is, for example, a corrugated pole in which the corresponding product is packed.
  • the trade name, product name, product character, etc. of the goods packed inside area A
  • the product number area B
  • the description of the contents Area C
  • the date of manufacture Area D
  • the sticking of the bar code Area E
  • a first image reading device 2 and a second image reading device 3 are arranged on a side surface of the conveyor 1 at a predetermined distance downstream of the reading device 2. I have.
  • the first image reading device 2 includes a CCD camera 4 as a first imaging unit, an image processing unit 6 as a first image processing unit connected thereto, and a sensor 8 as a first baggage detecting unit. Inclusive. Regarding the second image reading device 3, It includes a CCD camera 5 as a second imaging means, an image processing unit 7 as a second image processing means connected thereto, and a sensor 9 as a second baggage detecting means. The two image processing units 6 and 7 are connected by a communication cable 10 as information transmission means. The second image processing unit 7 transmits the processed data to the upper device 12.
  • the upper device 12 is a logistics information processing device that is configured by a computer device and controls the logistics of the logistics system including the conveyor 1. As a result, it is possible to control the sorting, branching, merging, and the like of packages at a position downstream of the conveyor 1.
  • a screen (not shown) is fixedly installed as a background at a position opposite to the image reading devices 2 and 3 with the conveyor 1 interposed therebetween.
  • FIG. 3 (a) shows a processing procedure of the first image reading device 2.
  • the luggage detecting sensor 8 constantly monitors the passage of the luggage W, and the luggage sensor 8 emits a signal when the luggage passes through the sensitive range of the sensor 8.
  • the CCD camera 4 captures an image of the side of the package W (SA302, Fig. 1 (a)).
  • This image is captured by the image processing unit 6 (SA303), image processing is performed to extract and specify an area for character recognition (SA304), and area position data for the specified area is stored in the second image.
  • FIG. 3 (b) shows a processing procedure of the second image reading device 3.
  • the second image reading device monitors whether or not the area position data has been received from the image processing unit 6 of the first image reading device (SB301). It is loaded into the control unit 7 (SB302). During this time, the baggage W is flowing on the conveyor 1, so the second image reading device constantly monitors the passage of the baggage W by the baggage detection sensor 9 (SB303). Then, upon detecting the passage of the same package W, the CCD camera 5 takes an image of the package W (SB304, FIG. 1 (b)), and then the image processing unit 7 sets the block designated by the position data.
  • FIG. 4 the processing contents of the first image processing unit 6 are shown in FIG. 4 and FIG.
  • Fig. 4 (a) assuming that the total number of pixels for one screen of the actually captured image is 640 dots in the horizontal direction and 480 dots in the vertical direction, ), A reduced image of 640 11 X 48 O Zn at a predetermined thinning rate n.
  • the first image processing unit 6 only needs to extract a specific area where characters in the image are drawn as a group or a block and extract only its outline. Processing speed Because
  • the image processing unit 6 extracts the outline of the entire portion where the characters and the like of the thinned image are drawn, and then, as shown in FIG. Performs valuation.
  • the black and white is the same, but it is actually a black and white inverted image.
  • the area where the characters are described is grouped, the blocks are calculated, and the coordinates are calculated.
  • Specified as This process detects the corner coordinates Pl, P2, P3, and P4 of the rectangular area and reads the area enclosed by the coordinates, as shown partially enlarged in the figure. It is a taking area.
  • the image processing area in the second image processing unit 7 is determined, and this area position information is transmitted to the second image processing unit 7 via the connection cable 10. Transfer to.
  • the second baggage detection sensor 9 detects the passing baggage W after a predetermined time delay
  • the second CCD camera 5 takes an image of the same baggage W, and the image content is converted to the second image processing unit. It is taken in 7.
  • the contents of this processing are as follows: contours are extracted, binarized, and connected components are extracted from image data in a specified area in the read data. Then, when the aspect ratio of the contour of the obtained data is constant, it is determined to be an alphanumeric character, and is recognized as character data by a pattern matching method or another character recognition method.
  • the character data is transferred to the host device 12.
  • a system for recognizing and identifying only characters is exemplified, so that areas B, C, and D, that is, the product number, NET, and date of manufacture are recognized as characters, and areas A and E are used. If it is determined that the recognized image in the outline is not a character, the recognition operation in the outline is stopped.
  • the host device 12 In other words, of the image data, only the product number, NET, and date of manufacture are transferred to the host device 12 as information forming a pair with the corresponding package W.
  • a branch line etc. can be provided downstream of the belt conveyor 1 to automatically sort the package according to the product number, NET, date of manufacture, etc. described on the package surface. I can do it.
  • the cargo identification device in the physical distribution system when identifying the cargo in the compare system or the like, the moving cargo is not stopped temporarily, but simply and quickly. Recognition of letters on luggage Can perform intelligence processing

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Image Processing (AREA)
  • Character Discrimination (AREA)

Abstract

L'invention concerne un dispositif comprenant une première unité d'imagerie (4) installée le long d'un passage (1), une seconde unité d'imagerie (5), une première unité de traitement d'image (6) destinée à traiter l'image d'un côté d'un objet capturée par la première unité d'imagerie, une seconde unité de traitement (7) permettant de traiter l'image capturée par la seconde unité d'imagerie, ainsi qu'une unité (10) destinée à transférer des données entre les deux unités de traitement d'image. La première unité de traitement d'image définit la zone comprenant les caractères à reconnaître, puis envoie les informations de position relatives à cette zone vers la seconde unité de traitement d'image. La seconde unité d'imagerie capture une image du même côté de l'objet que la première unité d'imagerie. La seconde unité de traitement d'image traite les informations relatives à la surface de l'objet sur la base des informations de position relatives à la zone définie.
PCT/JP2000/007197 2000-10-17 2000-10-17 Procede et dispositif d'identification de marchandises WO2002032795A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/JP2000/007197 WO2002032795A1 (fr) 2000-10-17 2000-10-17 Procede et dispositif d'identification de marchandises

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2000/007197 WO2002032795A1 (fr) 2000-10-17 2000-10-17 Procede et dispositif d'identification de marchandises

Publications (1)

Publication Number Publication Date
WO2002032795A1 true WO2002032795A1 (fr) 2002-04-25

Family

ID=11736596

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2000/007197 WO2002032795A1 (fr) 2000-10-17 2000-10-17 Procede et dispositif d'identification de marchandises

Country Status (1)

Country Link
WO (1) WO2002032795A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115019300A (zh) * 2022-08-09 2022-09-06 成都运荔枝科技有限公司 用于自动化仓库货物识别的方法

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS5726834B2 (fr) * 1973-12-17 1982-06-07
JPH04503921A (ja) * 1989-12-23 1992-07-16 シーメンス アクチエンゲゼルシヤフト 小包等の分配方法

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS5726834B2 (fr) * 1973-12-17 1982-06-07
JPH04503921A (ja) * 1989-12-23 1992-07-16 シーメンス アクチエンゲゼルシヤフト 小包等の分配方法

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115019300A (zh) * 2022-08-09 2022-09-06 成都运荔枝科技有限公司 用于自动化仓库货物识别的方法

Similar Documents

Publication Publication Date Title
EP1148316A1 (fr) Lecteur d'informations
CN101271514A (zh) 一种快速目标检测和目标输出的图像检测方法及装置
CN112287908B (zh) 一种基于人工智能的安检快速图片识别方法及系统
CN104700058A (zh) 用于旅客行李的检测方法和装置
CN103279756A (zh) 基于集成分类器的车辆检测分析系统及其检测分析方法
CN104821025B (zh) 客流检测方法及其检测系统
CN114049624B (zh) 一种基于机器视觉的船舶舱室智能检测方法及系统
CN206132657U (zh) 一种基于机器视觉的烫金质量智能检测系统
CN111597857B (zh) 一种物流包裹检测方法、装置、设备及可读存储介质
CN108226196A (zh) 一种智能x光机探测系统及探测方法
JP3018949B2 (ja) 文字読取装置およびその方法
CN206292821U (zh) 物品安检判图系统
WO2002032795A1 (fr) Procede et dispositif d'identification de marchandises
JP3917252B2 (ja) 車両のナンバプレート認識装置および車両のナンバプレート認識方法
CN113706497A (zh) 一种违禁品智能识别装置和系统
US20160203385A1 (en) Image processing system for extraction of contextual information and associated methods
Nguyen et al. You always look again: Learning to detect the unseen objects
CN112308848A (zh) 一种废钢货车挡板状态识别方法、系统、电子设备及介质
JP3358142B2 (ja) 物体識別システム
CN115438208A (zh) 一种提升包裹关联准确率的方法及装置
JP3128570B2 (ja) 被搬送物の表示認識方法および表示認識装置
CN115860605A (zh) 一种基于视觉识别的仓储物流检测系统
CN113420851B (zh) 行李监管系统及方法
US20230206606A1 (en) Method and system for training a neural network-implemented sensor system to classify objects in a bulk flow
CN112069841B (zh) X光违禁品包裹跟踪方法及装置

Legal Events

Date Code Title Description
AK Designated states

Kind code of ref document: A1

Designated state(s): CN JP KR US

AL Designated countries for regional patents

Kind code of ref document: A1

Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE

121 Ep: the epo has been informed by wipo that ep was designated in this application
NENP Non-entry into the national phase

Ref country code: JP

122 Ep: pct application non-entry in european phase