Method for scoring and controlling quality of food products in a dynamic production line

• US 9,014,434 B2
• Filed: 11/26/2012
• Issued: 04/21/2015
• Est. Priority Date: 11/26/2012
• Status: Active Grant

• Current Assignee: Frito-Lay North America Incorporated (PepsiCo Incorporated)
• Original Assignee: Frito-Lay North America Incorporated (PepsiCo Incorporated)
• Inventors: Bajema, Rick Wendell, Trick, Kevin Matthew, Warren, David Ray, Wright-Henry, Sheila, Lange, Sonchai, Bourg, Wilfred Marcellien Jr., Fox, Garrett
• Primary Examiner(s): FUJITA, KATRINA R
• Application Number:
  US13/684,994
• Publication Number:
  US 20140147015A1
• Time in Patent Office: 876 Days
• US Class Current: 382/110
• CPC Class Codes: G06T 2207/30128 Food products
• CPC Class Codes: G06T 7/0004 Industrial image inspection

Abstract

A method for scoring and controlling the quality of dynamic food products transitioning in the processing steps is performed using image analysis. An image of a plurality of moving food products on a conveyor system is captured by on-line vision equipment and image analysis is performed on the image via an algorithm that determines the percentage of pixels having varying intensities of colors and applies predetermined preferences to predict consumer dissatisfaction. The entire group of food products of one or more images is given an overall appearance score and each individual food product is also scored such that each may be ranked from least to more acceptable. The ranked food products can then be ejected in the order of worst to better rank to increase the overall quality score of the entire group.

Claims

1. A method for scoring and controlling quality of a plurality of moving food products, the method comprising the steps of:

capturing an image of a plurality of moving food products;

performing image analysis on the image to determine varying intensities of at least one color;

scoring the plurality of moving food products as a group based on a percentage of the color, thereby obtaining an overall calculated group appearance score; and

scoring each individual food product based on image analysis applied to individual food product, thereby obtaining a plurality of individual product scores.

2. The method of claim 1 further comprising the steps of:

ranking each of the individual food products according to individual product score; and

ejecting one or more of the individual food products based on a quality threshold to improve the group appearance score, wherein the individual food product having the worst product score is first ejected.

3. The method of claim 2 wherein the ejecting step comprises sending a signal to downstream sorting equipment to reject an individually scored food product.

4. The method of claim 2 wherein the quality threshold is changed based in part on the group appearance score.

5. The method of claim 1 wherein the capturing step comprises sequentially capturing a plurality of images of the plurality of moving food products and combining the plurality of images together prior to perform the image analysis.

6. The method of claim 1 wherein the image is captured in the visible spectrum.

7. The method of claim 1 wherein the image is captured in the near infrared spectrum.

8. The method of claim 1 wherein the image is captured in the ultraviolet spectrum.

9. The method of claim 1 wherein the image is captured using fluorescence between ultraviolet and visible spectrum.

10. The method of claim 1 wherein the image is captured using fluorescence between visible and near infrared spectrum.

11. The method of claim 1 wherein the image analysis comprises pixelating the image into a plurality of pixels and classifying each pixel into the at least two colors for the subsequent scoring step.

12. The method of claim 11 further comprising classifying each pixel into two or more subclasses representing different levels of intensity of each color.

13. The method of claim 11 wherein the pixels comprise varying intensities of red, green, and blue.

14. The method of claim 11 wherein classifying the pixels further comprises determining a plurality of background pixels.

15. An apparatus for the monitoring defects in a dynamic food production system comprising:

an image capturing device; and

a central processing unit having an algorithm programmed therein, wherein a basis of the algorithm comprises preference threshold quantified based on visual perceptions of colored defects within food products and an overall calculated group appearance score, wherein said colored defects are predetermined colorings in the visible spectrum.

16. The apparatus of claim 15 wherein the basis further comprises a ratio between an area comprising a defect and an area of a food piece.

17. The apparatus of claim 15 wherein the basis further comprises determining a color intensity value for each pixel.

18. The apparatus of claim 15 wherein the imaging capturing device is a camera.

19. The apparatus of claim 15 wherein the computing device is further operable to pixelate an image captured by the image capturing device.

20. The apparatus of claim 15 further comprising a sorter wherein the sorter is in communication with the computing device.