In mass food production and sale, proper stock inventory management is deemed necessary for proper operation. The traditional check-ups include manual inspections of defects and accuracy in labels; they are effective but slow, expensive, and prone to human errors. Advances in artificial intelligence and computer vision made brand segregation ending the subjective and labor-extensive check-ups. They combine OCR and image classification to make these processes faster. They extract text using the EasyOCR tool, including product labels, whereby preprocessing techniques of grayscale conversion or noise removal ensure accuracy even when the picture is rotated or noisy. The context could maximize compliance while minimizing errors. The model is tested on a diverse and vast real-time dataset. Executed, this integrated strategy improves tracking and verification as well as the accuracy of labels, which will enable effective quality control in the production and consumption of food. The classification and identification procedures are often perpetually enhanced by machine learning algorithms, assuring flexibility with regard to new label kinds and packaging designs. Besides contributing to bettering productivity, this automation lessens expenses, which benefits both manufacturers and customers.