Identification system

• US 5,725,253 A
• Filed: 08/05/1996
• Issued: 03/10/1998
• Est. Priority Date: 10/09/1991
• Status: Expired due to Fees

• Current Assignee: Kiwisoft Programs Limited
• Original Assignee: Kiwisoft Programs Limited
• Inventors: Salive, Rachel Keene, Slade, Kevin George, Salive, Harold Terrence
• Primary Examiner(s): HAN, FRANCES CHIN
• Application Number:
  US08/691,823
• Time in Patent Office: 582 Days
• Field of Search: 283/74, 283/70, 283/75, 283/81, 283/67, 235/462, 235/375
• US Class Current: 283/67
• CPC Class Codes: G06K 19/06131 the marking comprising a target pattern, e.g. for indicating the center of the bar code or for helping a bar code reader to properly orient the scanner or to retrieve the bar code inside of an image
• CPC Class Codes: G06K 7/10722 Photodetector array or CCD scanning
• CPC Class Codes: G06K 7/10861 sensing of data fields affixed to objects or articles, e.g. coded labels postal sorting B07C3/14, conveying articles B65G47/48
• CPC Class Codes: G06K 7/1439 including a method step for retrieval of the optical code
• CPC Class Codes: G09F 3/0297 including a machine-readable marking, e.g. a bar code digitally marked record carriers in general G06K19/00
• CPC Class Codes: G09F 3/205 specially adapted for electric cables, pipes or the like

Abstract

An identification system involves the labeling then tracking of grouped items such as logs, shipping containers, or packets of mail and reporting the current location of identified items during transport, processing, and storage. Machine-readable labels are provided, adapted for recognition and reading from within a cluttered scene. These labels have bordering indicia--used for locating purposes--distinguishable from inner informative indicia. Bordering indicia include either a series of small substantially similar marks like filled or hollow ovals, or one circle, or part of a circle, or a sequence of locating symbols or characters. Informative indicia include dots, bars, rings, or regional text characters. Multiple coding methods and spatial (e.g. Latin Square) replication of indicia are used to minimize errors. A machine-vision image decoder comprises a high-resolution camera adapted for field use and a remote image processing computer to analyze the image and make reports listing or showing items within the image as identified by labels.

Claims

1. An identification system for identifying each of a plurality of items, comprising:

a plurality of machine-readable labels, each of said labels being capable of being applied to one of the items and comprising a substrate carrying contrasting indicia on at least one surface,

said contrasting indicia including at least one distinctive marking which defines a frame of reference for an area containing an adjoining information-holding field, said information-holding field containing a plurality of information-carrying indicia, and wherein at least one of (a) said distinctive marking, (b) said information carrying indicia, and (c) further indicia on the substrate, comprises orientation indicia indicating an orientation of the label,

machine vision equipment to view an image containing a plurality of the items with the labels applied thereto, conversion means to convert the image to machine readable form, and processing means to process the thus-converted image.

2. An identification system as claimed in claim 1, in which said distinctive marking is selected from the group consisting of at least one arcuate marking, a plurality of alphanumeric characters, a plurality of ovals, a plurality of triangles, a plurality of marks, and a combination thereof.

3. An identification system as claimed in claim 2, in which said distinctive marking comprises a plurality of indicia forming at least one distinctive sequence arranged in an enclosing shape.

4. An identification system as claimed in claim 1, in which the orientation indicia comprise at least one compact indicium having an appearance distinct from those used in the distinctive marking.

5. An identification system as claimed in claim 2, wherein said information-holding field contains an array of replicated said information-carrying indicia selected from the group consisting of alphanumeric characters, distinctive symbols, marks and multiple code sets.

6. An identification system as claimed in claim 5, wherein said information bearing indicia are replicated within the array in the form of an at least partial Latin Square.

7. A method of identifying each of a plurality of items at a site, comprising the steps of:

labelling each of the items with a machine-readable label, said label carrying contrasting indicia compatible with machine vision equipment, wherein said indicia include at least one distinctive marking which constitutes a frame of reference defining an area containing an adjoining information-holding field, and said information-holding field contains information-carrying indicia relevant to its respective item, recording at least one image containing a plurality of the labelled items at the site, converting the at least one image into a computer-compatible form, applying machine vision algorithms to detect the presence and position of each distinctive marking within each image, computing the location of each adjoining information-holding field, assessing the rotational orientation of each label by means of orientation-indicating indicia contained in at least one of the distinctive marking, the information-carrying indicia or further indicia, and detecting and decoding the information-carrying indicia to identify each of the items.

8. A method as claimed in claim 7, further wherein said information-holding field of each said label contains an array of information-carrying indicia which is replicated in the form of an at least partial Latin Square, and using the replicated information to verify and, if required, to correct the decoded information from the information-holding field.

9. A method of identifying each of a plurality of items at a site, comprising the steps of:

labelling each of said items with a substantially unique machine-readable label, said label carrying a data matrix data field readable by machine vision reading equipment, said data matrix data field containing information-carrying indicia, and an area of the field of view able to be read by said machine vision reading equipment containing a plurality of said labels,

recording at least one image of the area of the field of view able to be read by said machine vision reading equipment, converting the image into a computer-compatible form, applying machine vision algorithms to detect the presence and position of each distinct data field within the image, and

decoding the information-carrying indicia in each data field in order to identify each of the items.

10. A method of identifying as claimed in claim 9, wherein each said label has an area which is substantially less than the field of view area.

11. A method of identifying as claimed in claim 10, wherein a plurality of said labels are positioned in the field of view area.

12. A method of identifying as claimed in claim 11, wherein said plurality of labels comprises at least five labels.