Crystal Oscillator Detection Dataset

In the industrial sector, the quality control of frequency control components, such as crystal oscillators, faces significant challenges due to the increasing complexity of defects and the need for rapid inspection to ensure operational efficiency. Existing solutions often rely on manual inspection, which can lead to human errors and inconsistencies. This dataset aims to address the need for automated detection of defects in crystal oscillators, providing a reliable source of labeled images for training machine learning models. The dataset was collected using high-resolution cameras in controlled lighting environments to ensure visibility of defects. Quality control measures included multi-round labeling by trained annotators, consistency checks, and expert reviews to ensure high accuracy. The data is organized in JPG format, with images structured in folders categorized by defect type.