A study on synthetic diamond quality evaluation using an enhanced YOLOv8n-based algorithm named YOLOv8n_adamas

Abstract In response to the requirements for synthetic diamond quality evaluation in industrial applications, this study proposes an enhanced algorithm titled YOLOv8n_adamas, derived from an improved variant of the YOLOv8n neural network. To overcome the limitations in feature extraction and recognition of synthetic diamond images using the YOLOv8n model, the backbone architecture was redesigned by referring to ConvNextV2 structure, thereby enhancing the feature extraction capacity of the YOLOv8n backbone. An attention-based dynamic detection head was integrated into the original model, replacing the conventional detection head, leading to an improvement in the model's object detection sensitivity. Experimental results demonstrate that, compared to the baseline YOLOv8n network, the YOLOv8n_adamas algorithm achieves a 3.4% increase in precision, a 3.4% rise in recall, and respective improvements of 2.5% and 1.6% in mean precision at confidence levels of 0.5 and 0.95. Consequently, the accuracy of synthetic diamond quality evaluations has been significantly boosted.