Using Vision Inspection Systems for Tortilla Quality Control

At-line, in-line, and over-line vision inspection technologies are built to offer critical measurements quicker and more consistently than manual measurements, while also allowing for the measurement and quantification of product attributes that are nearly impossible to calculate manually (e.g., volume, surface area, etc.).

The use of these systems, such as the Sightline vision inspection system from KPM Analytics, eradicates the need for manual data entry and charting, resulting in more reliable and repeatable quality assurance measurements. The advantages include automatic rejection of defective or out-of-spec products, fast and convenient product sampling, automated reporting and more data for less effort.

Color Analysis

  • The average color of top
  • The average color of the bottom (toast/dark marks ignored)

Anomaly Detection

  • Holes, tears, folds, tails, bites
  • Irregular edges, foreign objects
  • Burn marks and dark spots 

Inspecting Tortilla for Quality Control

Image Credit: KPM Analytics

Toast Marks

  • Total number
  • Color analysis
  • Area/coverage

2D Geometry

  • Roundness/shape verification
  • Minimum, Maximum, Average diameter
  • Area measurements

Contour Defects

  • Curling
  • Edge roughness
  • Tails, bites, folds
  • Blowout detection 

Inspecting Tortilla for Quality Control

Image Credit: KPM Analytics

Easy detection of holes and transparent areas.

Easy detection of holes and transparent areas. Image Credit: KPM Analytics

KPM Analytics vision inspection technology can quantify virtually any food product, either directly during the production process (Over-Line/In-Line) or with a Benchtop Inspection System (Off-Line).

A few of the measurements available, notably for tortilla bread, are listed below.

Table 1. Overhead 2D Analysis. Source: KPM Analytics

. .
Min/Max Diameter The minimum and maximum diameters of the object as measured through the center of the object.
Average Diameter The average of 180 diameters of the object as measured every one degree through the center of the object.
Shape Roundness/Ovality. The comparison measurement of the product to a proper circle.
Toast Marks Identified based on user-defined color specifications. Determine total number, % of area affected (distribution), voids, largest or smallest toast mark, and color information.
Hole Analysis Identification of holes, the area of each hole and the location of the holes.
Surface Area The overall area of the object. Used to find doubles and small products.
Folds/Straight Segments The length and locations of straight segments/folds anywhere on the perimeter of the product.
Edge Roughness The maximum standard deviation of contiguous radii around the circumference of the object.
Contour Defects Detection of shape deviations, mainly in the form of tears, bites and tails.
Product Color The average color of the product with all marks ignored for the calculation.

 

(*bottom analysis is optional)

Table 2. Package Analysis. Source: KPM Analytics

. .
Heat Seal Inspection of the seal area for abnormal areas based on color and size. Analysis of heat seal pattern for integrity and abnormalities.
Code Verification Readability and verification of bar codes, date codes, lot codes, etc.
Regions of Interest Color analysis of specific regions of the package. Used to determine presence of product, proper placement of label, package color anomalies, etc.
Text Verification Validate specific text elements, such as product names, compliance with regulated statements, etc.

 

Actual geometry data extracted from live tortilla production run, displayed on the included HMI monitor at the line.

Actual geometry data extracted from live tortilla production run displayed on the included HMI monitor at the line. Image Credit: KPM Analytics

Example of unwanted fold found during a production run.

Example of unwanted fold found during a production run. Image Credit: KPM Analytics

Toast marks identified by user-defined color specifications.

Toast marks identified by user-defined color specifications. Image Credit: KPM Analytics

Thermal inspection of the package seal.

Thermal inspection of the package seal. Image Credit: KPM Analytics

This information has been sourced, reviewed and adapted from materials provided by KPM Analytics.

For more information on this source, please visit KPM Analytics.

Citations

Please use one of the following formats to cite this article in your essay, paper or report:

  • APA

    KPM Analytics. (2022, April 26). Using Vision Inspection Systems for Tortilla Quality Control. AZoOptics. Retrieved on June 27, 2022 from https://www.azooptics.com/Article.aspx?ArticleID=2203.

  • MLA

    KPM Analytics. "Using Vision Inspection Systems for Tortilla Quality Control". AZoOptics. 27 June 2022. <https://www.azooptics.com/Article.aspx?ArticleID=2203>.

  • Chicago

    KPM Analytics. "Using Vision Inspection Systems for Tortilla Quality Control". AZoOptics. https://www.azooptics.com/Article.aspx?ArticleID=2203. (accessed June 27, 2022).

  • Harvard

    KPM Analytics. 2022. Using Vision Inspection Systems for Tortilla Quality Control. AZoOptics, viewed 27 June 2022, https://www.azooptics.com/Article.aspx?ArticleID=2203.

Ask A Question

Do you have a question you'd like to ask regarding this article?

Leave your feedback
Your comment type
Submit