Commercial Kitchen Hygiene Violation Detection Image Dataset

The current retail food and beverage industry faces challenges such as low efficiency, high labor costs, and missed or false inspections in hygiene supervision. Existing solutions mostly rely on manual checks and lack automation, making real-time monitoring and wider coverage difficult. This dataset aims to provide high-quality image data to support the development of intelligent detection systems, improving the accuracy and efficiency of kitchen hygiene inspections. Data is collected using high-definition cameras in various types of commercial kitchen environments. Multiple rounds of labeling and consistency checks ensure data quality, with the annotation team consisting of experienced food safety experts. Data preprocessing includes denoising, enhancement, and format conversion, with data stored in JPG format and organized by scene and violation type. The dataset features high annotation accuracy and consistency, an innovative multi-level annotation method, and potential application value in real-time hygiene violation detection, effectively improving detection accuracy by over 20%. Compared to other datasets, it covers a richer variety of kitchen scenes and violation types, providing a diverse data foundation for algorithm models and has broad industry applicability.