Silencer Detection Dataset

The current industrial sector faces challenges in maintaining high-quality exhaust systems, particularly in detecting faults in silencers. Existing solutions often rely on manual inspections, which are time-consuming and prone to human error. This dataset aims to address the need for automated detection and noise analysis, providing a foundation for developing machine learning models that can improve accuracy and efficiency in silencer condition assessment. The dataset comprises images captured using high-resolution cameras in controlled environments, ensuring consistent lighting and background conditions. Quality control is enforced through multi-round annotations, consistency checks, and expert reviews. The data is organized in JPG format, with structured metadata for easy access and analysis. The dataset includes 15,000 images, each annotated with specific conditions and noise levels, facilitating detailed analysis and model training.