AI-Guided Feature Segmentation Techniques to Model Features from Single Crystal Diamond Growth

TL;DR

This paper presents a deep learning-based semantic segmentation method for real-time feature extraction in single crystal diamond growth, significantly improving accuracy and reducing annotation effort.

Contribution

It introduces a novel deep learning-driven segmentation approach with an active learning annotation framework tailored for diamond growth datasets.

Findings

DeeplabV3plus achieves over 96% accuracy in classifying diamond features.

The annotation process is accelerated with active learning, reducing labeling time and cost.

The method enables precise, real-time monitoring of diamond growth features.

Abstract

Process refinement to consistently produce high-quality material over a large area of the grown crystal, enabling various applications from optics crystals to quantum detectors, has long been a goal for diamond growth. Machine learning offers a promising path toward this goal, but faces challenges such as the complexity of features within datasets, their time-dependency, and the volume of data produced per growth run. Accurate spatial feature extraction from image to image for real-time monitoring of diamond growth is crucial yet complicated due to the low-volume and high feature complexity nature of the datasets. This paper compares various traditional and machine learning-driven approaches for feature extraction in the diamond growth domain, proposing a novel deep learning-driven semantic segmentation approach to isolate and classify accurate pixel masks of geometric features like diamond, pocket holder, and background, along with their derivative features based on shape and size. Using an annotation-focused human-in-the-loop software architecture for training datasets, with modules for selective data labeling using active learning, data augmentations, and model-assisted labeling, our approach achieves effective annotation accuracy and drastically reduces labeling time and cost. Deep learning algorithms prove highly efficient in accurately learning complex representations from datasets with many features. Our top-performing model, based on the DeeplabV3plus architecture, achieves outstanding accuracy in classifying features of interest, with accuracies of 96.31% for pocket holder, 98.60% for diamond top, and 91.64% for diamond side features.