V.Varun, Y. Sai Pranay, B. Athirath, Mr.CH. Srinath Reddy
Many people enjoy food photography because it highlights the beauty of food. Images of food do not, however, provide any information regarding the method of preparation or the difficulty of the recipe used to create each dish. Convolutional Neural Network (CNN) is used to create an inverse cooking system that creates cooking instructions from food photographs. Without prescribing any order, the system uses a novel architecture to forecast elements and their dependencies. Then, while concurrently taking into account the image and implied ingredients, it provides cooking directions. On the Recipe 1M dataset, the system's performance was carefully assessed, and the results showed that ingredient prediction was more accurate than with earlier techniques. By utilising both the image and the inferred ingredients, the system was also able to generate high-quality recipes. Human review revealed that these recipes were more interesting than those produced by retrieval-based methods.
https://doi.org/10.62226/ijarst20230538
PAGES : 984-987 | 23 VIEWS | 43 DOWNLOADS
V.Varun, Y. Sai Pranay, B. Athirath, Mr.CH. Srinath Reddy | Recipe Generation from Food Images | DOI : https://doi.org/10.62226/ijarst20230538
Journal Frequency: | ISSN 2320-1126, Monthly | |
Paper Submission: | Throughout the month | |
Acceptance Notification: | Within 6 days | |
Subject Areas: | Engineering, Science & Technology | |
Publishing Model: | Open Access | |
Publication Fee: | USD 60 USD 50 | |
Publication Impact Factor: | 6.76 | |
Certificate Delivery: | Digital |