International Journal of Academic and Applied Research (IJAAR)   Year: 2023 | Volume: 7 | Issue: 9 | Page No.: 57-70 Application of Deep Learning Methods for Recognizing and Classifying Culinary Dishes in Images Download PDF Iryna Tvoroshenko, Volodymyr Gorokhovatskyi, Oleg Kobylin, Arsenii Tvoroshenko Abstract: The paper deals with the actual tasks of computer vision - recognition and classification of objects in images. Deep learning methods based on neural networks are proposed as an alternative to existing methods. A new approach for effective recognition and classification of culinary dishes in images has been developed, which involves the use of the capabilities of the TensorFlow deep learning library and the features of the Convolutional Neural Network. A software application for recognizing and classifying culinary dishes has been developed. Testing of the proposed tool showed that 7 complete epochs of model training provided 77% accuracy, which is a fairly good result, given that one of the main problems in recognizing culinary dishes is interclass similarity. The prospect of further research is to create subclasses for existing general classes of dishes.