Process for evaluating data from textile fabrics

• US 6,987,867 B1
• Filed: 08/14/1998
• Issued: 01/17/2006
• Est. Priority Date: 09/15/1997
• Status: Expired due to Fees

• Current Assignee: Uster Technologies AG (Toyota Motor Corporation)
• Original Assignee: Uster Technologies AG (Toyota Motor Corporation)
• Inventors: Uhlmann, Jürg, Meier, Rudolf
• Primary Examiner(s): Johns, Andrew W.
• Assistant Examiner(s): NAKHJAVAN, SHERVIN K
• Application Number:
  US09/508,430
• Time in Patent Office: 2,713 Days
• Field of Search: 382/111
• US Class Current: 382/111
• CPC Class Codes: G01N 2021/8887 based on image processing techniques
• CPC Class Codes: G01N 21/8983 for testing textile webs, i.e. woven material
• CPC Class Codes: G06T 2207/30124 Fabrics; Textile; Paper
• CPC Class Codes: G06T 7/0006 using a design-rule based approach

Abstract

A process is disclosed for evaluating data obtained from textile fabrics. In order to devise a process which allows data obtained from textile fabrics to be easily compared, assessed in a differentiated manner as to their significance and evaluated, the data are determined in a section (3a,3b) of the surface of the fabric, sorted according to at least two parameters (13,14) and represented in an image (12, 30) as a function of the parameters.

Claims

1. A method for representing faults detected on textile fabrics for purposes of evaluation, comprising the following steps:

receiving data associated with a plurality of faults detected on a swatch of the surface of the fabric;

sorting the data associated with the plurality of detected faults in accordance with at least two parameters, wherein at least one of said two parameters pertains to the size of the detected faults;

representing the received and sorted data associated with the plurality of detected faults in an image having at least two dimensions, wherein one of said dimensions corresponds to said one of said two parameters, and another of said dimensions corresponds to the other of said two parameters.

2. The method of claim 1, wherein said one parameter is the length of a detected fault.

3. The method of claim 2 wherein the other of said two parameters is the intensity of a detected fault.

4. The method of claim 2 wherein the other of said two parameters is the width of a detected fault.

5. The method of claim 1 wherein said one parameter is the area of a detected fault.

6. The method of claim 5 wherein the other of said two parameters is the intensity of a detected fault.

7. The method of claim 1 wherein said one parameter is the number of unit fields in said swatch within which a detected fault is located.

8. The method of claim 7 wherein the other of said two parameters is the intensity of a detected fault.

9. The method of claim 1 wherein said other dimension is divided into a plurality of zones that are respectively associated with different types of faults.

10. The method of claim 1 wherein each of said two dimensions is divided into a plurality of sections to thereby divide said image into a plurality of classes, and the plurality of detected faults are represented as numerical values within the classes with which they are respectively associated.

11. The method of claim 10 wherein the position of a numerical value within a class indicates the value of a parameter for detected faults represented by that number.

12. The method of claim 11 wherein the parameter depicted by the positions of the numerical values is a third parameter different from said two parameters.

13. The method of claim 12 wherein said third parameter is intensity.

14. A method for representing faults detected on textile fabrics for purposes of evaluation, comprising the following steps:

receiving data associated with a plurality of faults detected on a swatch of the surface of the fabric;

sorting the data associated with the plurality of detected faults in accordance with at least two parameters, wherein at least one of said two parameters pertains to the intensity of the detected faults;

representing the received and sorted data associated with the plurality of detected faults in an image having at least two dimensions, wherein one of said dimensions corresponds to said one of said two parameters, and another of said dimensions corresponds to the other of said two parameters.

15. The method of claim 14 wherein one of said dimensions is divided into a plurality of zones that are respectively associated with different types of faults.

16. The method of claim 14 wherein each of said two dimensions is divided into a plurality of sections to thereby divide said image into a plurality of classes, and the plurality of detected faults are represented as numerical values within the classes with which they are respectively associated.

17. The method of claim 16 wherein the position of a numerical value within a class indicates the value of a parameter for detected faults represented by that number.