How to avoid false positive

deepjavalibrary / djl

An Engine-Agnostic Deep Learning Framework in Java

https://djl.ai

Apache License 2.0

4.06k stars 648 forks source link

Open ashish143ti opened 2 years ago

ashish143ti commented 2 years ago

Hi Team , I would like to use DJL API for our Automated testing areas to achive visual Testing.

Here we are trying to compare two images where each images contains dynamic test data so how we can handle such false positive scenarios ??

As you mentioned it is built on ML , so can you please confirm it is above pixel to pixel comparison??

lanking520 commented 2 years ago

Can you elaborate more on your scenario? What kind of images you are trying to compare?

For General ML purpose, we build image embedding and use certain Nerual Network to do classification