Create an Object Flaw Detector

Detect various irregularities of a product as it moves along a conveyor belt.

Target Operating System Ubuntu* 16.04 LTS
Time to Complete 30 minutes

GitHub* (C++)

What You Will Learn

Use a video source (webcam or video file) to detect anomalies in the objects moving on a conveyor belt, and check for defects in color and orientation of the object.

Gain insight into the following solutions:

  • Computer vision applications for IoT
  • Inference to analyze datasets
  • Industrial IoT market

Use the skills learned in this reference implementation to develop similar IoT solutions.

Learn to build and run an application with these capabilities:

Detect and analyze irregularities.
Monitor for color consistency and flaws.
Read various kinds of bar codes.

How It Works

This application uses video input to track manufactured objects on a conveyor belt and identifies any defects in the objects. Images of defective objects are saved in unique folders depending on the type of defect.

The Intel® Distribution of OpenVINO™ toolkit includes the following OpenCV functions that help detect object flaws.

  • inRange: Creates a mask, analyzes the color of an object, detects color anomalies, and identifies the defective area.
  • findContours: Identifies the contours and orientation of the object from the morphological opening and closing of the mask.
  • cvtColor: Transforms the image from BGR (blue, green, red) format to grayscale to detect and monitor cracks.

dataflow for IoT object flaw detector

Tools We Used