Machine Learning and Classification for QA

Hi everyone.

I just started looking into machine learning and classification. For a small project I have different grayscale images showing different shapes that are formed by a collimator. I know want to evaluate how accurate the collimator forms the shapes (allowed tolerance is +-2mm). My idea was to train my model what is in the spects and what is not.

As mentioned, I have just started reading about machine learning, and I don't know where to start. How should my classifiers or training data look like, and which machine learning approach should I choose?

Thanks in advance for any advice!

Kind regards,

Mike

Answer 1

[Image Analyst]

Have you taken the online Deep Learning on-ramp the Mathworks web site offers? That's where I'd start.

[MikeSv]

Hi and thanks for the great advice.

I wasn't aware of this tutorial! Seems like a good starting point. :-)

Regards,

Michael

Answer 2

[vijayabharathi K]

TASKUse the transform function to create a transformed datastore called preprocds. This datastore should apply the scale function to the data referenced by letterds.

[Image Analyst]

How is this an answer to Mike's two year old question? I think you posted this as an Answer when it should have been posted as a new question after you've read the guidelines on the asking form page.