Automated Surface Inspection

Automated optical inspection (AOI)

Automated optical inspection systems

automated optical inspection

Shelton Vision provides the fabric and textile industries with Automated Optical Inspection (AOI) systems and solutions.

The significant advantage offered by all proven computer inspection systems lies in the consistency of operation and applied standard, allied to the speed at which they
can operate. They give the user  access to  inspection data in real time at a point in the production cycle that can minimise costs, waste and customer rejections by lowering overall defect rates.

A range of different machine vision processes and application are applied, increasing accuracy and improved quality through out the production line.

Automated defect detection

Our WebSPECTOR detection system tackles defect-finding tasks where the feature being looked for is not known but simply differs from what should be there. WebSPECTOR is a self-learning system that identifies defects that otherwise would be forwarded on to the customer.

The automatic optical inspection system runs 9 different defect detection algorithms simultaneously. The detected faults are used to operate a tagging system, marking the faults for processes further down the production line.

Classification of textile faults

The camera images, after processing, identify all features that differ from the normal view. The features extraction utilises up to 48 algorithms, due to the diverse and sometimes subtle nature of textile faults. The features from each camera plane are then combined to ensure that no feature is reported twice, resulting in a better understanding of each fault.

This process outputs 56 independent properties for each fault, which are analysed in a classification stage to see what type of fault it is. This provides a basis for acceptance or rejection of the fault. The fault criteria are subsequently adjustable, so that the final declaration of a feature as a fault can be framed as a particular set of values. These values can vary, depending on the intended customer, or grade of the product.

Detectable defect grading

The defect type and severity grade is recorded in real time, allowing images to be stored and the corresponding data can be used to adapt the cutting plan. Here are some, but not all, of the defects that can be detected:

  • Abrasion
  • Black Spot
  • Broken Pick
  • Coating Line
  • Colour Variation
  • Contamination
  • Contamination Yarn
  • Delamination
  • Dirty Marks
  • Dyeing stop
  • Foreign Fibre
  • Fused Fibre
  • Hair
  • Impression
  • Longitudinal crease mark
  • Misprint
  • Mixed Yarn
  • Neps
  • Non-woven black spots
  • Non-woven contamination
  • Non-woven contamination
  • Non-woven defects
  • Non-woven stain
  • Impression
  • Paper contamination
  • Pigment line
  • Reed mark
  • Repeating weft defects
  • Shade change
  • Snag

Surface inspection defect detection

In this video you can see how the defect detection system uses a signal to noise (S/N) ratio to detect the defect.  The video displays each defect with its corresponding graph. The large peak indicates a fault compared to the much smaller peaks of the background texture. The ratio between fault peak and largest background peak gives the signal to noise ratio (S/N).

Benefits of AOI

The benefits of automatic optical inspection systems can be reaped in both a fabric production environment as well as in fabric processing and fabric make up (garmenting, upholstery, automotive trim) operations. Increased accuracy, improved quality and decreased labour costs are some of the other advantages.

Follow Shelton Vision on Twitter, LinkedIn and Vimeo.