DataProphet INSPECT is a cutting-edge machine vision system used to enhance the effectiveness of human quality control operators. Unlike other inspection solutions, it does not use template matching to detect defects but instead relies on proven machine learning algorithms to flag manufacturing defects.

Our solution for quality control in manufacturing is more efficient and consistent than the human eye. Through Artificial Intelligence (AI), DataProphet INSPECT improves continually and can locate and classify defects on components that the computer system has never seen before.

DataProphet INSPECT combines consistent quality control with traceability by performing OCR on the surface of castings.
> 99% Accuracy
upon OCR of castings serial numbers
> 99% Accuracy
upon presence or absence of components classification in assembly

Why it works

The use of a multi-camera system enables images to be taken at different angles and within a short period of time allowed by the semi-continuous process. These images are preprocessed by DataProphet’s solution before being ingested by DataProphet’s state-of-the-art, object detection models which make use of convolutional neural networks (CNN) to determine the location, edges and type of any defects. This approach proves particularly robust for any given operating environment.

After training, DataProphet’s model is applied locally upon new images. The model works by finding anchor points for the defects before determining the bounding box for, and classifying each defect. The consistent frame of reference created by the assembly enables a grid to be overlayed. The grid location of the defects are then recorded for further analysis, along with the appropriate metadata such as item number and type. In the unlikely event that a defect is not detected, a customized user interface enables clients to label the defect such that the system can learn and detect the same or similar defects in the future.

Considerations for computer vision quality control in manufacturing Paper

With ever faster computers and the rise of industrial use of machine learning techniques, probabilistic approaches utilising convolutional neural networks to determine outcomes is fast becoming the technology of choice.