Lymperis Perakis published his master thesis as a paper:

Classifying figures and illustrations in electronics datasheets: A comparative evaluation of recent computer vision models on a custom collection of 4000 technical documents

We report findings from a comparative evaluation of several recent object detection models applied to a domain-specific use case in technical document analysis and graphics recognition. More specifically, we apply models from the EfficientDet and YOLO model families to detect and classify figures in electronics datasheets according to a custom classification scheme. We identify YOLOv7-D6 as the most accurate model in our study and show that it can successfully solve this task. We highlight an iterative approach to figure annotation in document page images for creating a comprehensive and balanced custom dataset for our use case. In our experiments, the object detection models show impressive performance levels on par with state-of-the-art results from the literature and related studies.

the paper can be accessed here: https://dl.gi.de/items/7b242ead-e083-4867-b8a4-1600662f628d

Congrats to Lymperis Perakis and the whole team!