Automatic inspection system using barcode localization and method thereof

• US 6,382,510 B1
• Filed: 01/24/2000
• Issued: 05/07/2002
• Est. Priority Date: 02/02/1999
• Status: Expired due to Term

• Current Assignee: Transpacific IP Group Limited
• Original Assignee: Industrial Technology Research Institute
• Inventors: Ni, Catherine Wei-fen
• Primary Examiner(s): Lee, Michael G.
• Assistant Examiner(s): WALSH, DANIEL I
• Application Number:
  US09/490,314
• Time in Patent Office: 834 Days
• Field of Search: 235/462.05, 235/462.08, 235/462.09, 235/462.1
• US Class Current: 235/462.08
• CPC Class Codes: G01N 21/8851 Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges G01N21/8806 and G01N21/93 - G01N21/95692 take precedence; optical measurement of dimensions G01B11/00; optical scanning G02B26/10; image transformation G06T3/00; computerised image enhancement G06T5/00; image processing per se for flaw detection G06T7/0002
• CPC Class Codes: G06K 7/14 using light without selection of wavelength, e.g. sensing reflected white light G06K7/10831 - G06K7/1097 take precedence
• CPC Class Codes: G06K 7/1417 2D bar codes
• CPC Class Codes: G06K 7/1443 locating of the code in an image

Abstract

An automatic inspection system using barcode locator and the method thereof which can inspect a colored surface of a three-dimensional object having a barcode. The automatic inspection systems comprises a light source; an image-retrieving device; and an operating and processing device. The image-retrieving device retrieves three-dimensional images of the inspected object from various viewing angles. The three-dimensional images are converted into two-dimensional images, which are then connected to produce a two-dimensional image representing the inspected object by the operating and processing device. The two-dimensional image representing the inspected object is adjusted through the barcode locator. Thereafter, the two-dimensional image is compared with a reference object image previously stored by the operating and processing device to find the defined pre-defects of the inspected object. The automatic inspection system and inspecting method can provide high-speed inspection with a high accuracy for on-line production.

Claims

1. An automatic inspection system using barcode locator, which can inspect a colored surface of a first three-dimensional object having a barcode, comprising:

a light source for uniformly illuminating the first three-dimensional object;

an image-retrieving device for retrieving and analyzing three-dimensional images of the first object at various viewing angles;

an operating and processing device for receiving three-dimensional images from the image retrieving device, segmenting the three-dimensional images, converting the three-dimensional images into two-dimensional images, connecting the two-dimensional images of various viewing angles to obtain a single two-dimensional image representing the first three-dimensional object, using a barcode in the single two-dimensional image to position the single two-dimensional image in a first predefined position and comparing the two-dimensional image with a reference object image previously stored in the operating and processing computer to find defects in the colored surface of the first three-dimensional object.

2. An automatic inspection system as claimed in claim 1 wherein the operating and processing device is a computer that performs the following operations:

a segmenting process for finding the object in an image;

a converting process for connecting the images of various viewing angles to obtain a two-dimensional image representing the inspected object;

an orientation process using a barcode in the single two-dimensional image to position the single two-dimensional image in a first predefined position; and

a comparing process for comparing the two-dimensional image representing the inspected object with a previously stored reference object image to find defects of the inspected object.

3. An automatic inspection system as claimed in claim 1 wherein the light source is an illuminating system that can provide an uniform illumination for a surface of the object.

4. An automatic inspection system as claimed in claim 1 wherein the image-retrieving device comprises a plurality of CCD cameras and a frame grabber.

5. An automatic inspection system as claimed in claim 1 wherein the comparing process comprises the steps of (1) performing a correlation operation for best alignment of the inspected object image to the reference object image;

(ii) obtaining a residual image of the obtained image and the stored image;

(iii) producing binary pixel-values and performing image-negative transforming and closing operations for the residual image; and

(iv) deciding whether the residual image contains pre-defined defects.

6. An automatic inspection system as claimed in claim 4 wherein the light source includes one of two ring-type light tubes and LEDs.

7. An automatic inspection system as claimed in claim 4 wherein the image-retrieving device includes at least three CCD cameras.

8. An automatic inspection method using barcode locator, for inspecting a colored surface of a first three-dimensional object having a barcode, comprising the steps of:

(i) retrieving three-dimensional images of the first three-dimensional object by an image retrieving device, and segmenting the three-dimensional images;

(ii) converting the three-dimensional images into two-dimensional images by an operating and processing computer;

(iii) connecting the two-dimensional images of various viewing angles to obtain a two-dimensional image representing the first three-dimensional object;

(iv) locating the barcode in the two-dimensional image;

(v) adjusting the position of the two-dimensional image so that the barcode is positioned in a first predefined position;

(vi) comparing the positioned two-dimensional image of the first three-dimensional object with a reference object image previously stored in the operating and processing computer to find pre-defined defects in the first three-dimensional object.

9. An automatic inspecting method as claimed in claim 8 wherein, in step (iv), the barcode is located by using edge detection and one-way erosion/dilation operations.

10. An automatic inspecting method as claimed in claim 8 wherein the comparing process of step (vi) comprises the steps of (1) performing a correlation operation for obtaining a best, alignment of the first three-dimensional object image to the reference object image;

(2) obtaining a residual image of the obtained image and the stored image;

(3) producing binary pixel-values and performing image-negative transforming and closing operations for the residual image; and

(4) deciding whether the residual image contains pre-defined defects.