Mold Template Defect Recognition Dataset

In the industrial sector, mold quality inspection is crucial for ensuring product integrity but faces challenges such as inconsistent defect detection and high rates of false negatives. Existing solutions often rely on manual inspection, which is time-consuming and prone to human error, leading to inefficiencies. This dataset aims to address these challenges by providing a comprehensive collection of labeled images that enhance machine learning models for accurate defect recognition in mold templates. Data was collected using high-resolution cameras in controlled industrial environments, ensuring clarity and consistency. Quality control measures included multiple rounds of labeling, consistency checks among annotators, and expert reviews to maintain high accuracy. The images are stored in JPG format, organized in directories by defect type, facilitating easy access and processing.