It is difficult to choose recipes that can be prepared using ingredients available at home. Manually identifying available ingredients and performing searches for feasible recipes is cumbersome and error prone. This disclosure describes techniques that enable users to obtain recipe recommendations by capturing available ingredients visually as images and/or videos. With user permission, the visual input is analyzed using computer vision and natural language processing techniques to identify the type and quantity of available ingredients. Matching recipes are determined using a search engine and ranked based on the user’s preferences. The user can filter the list based on various criteria as well as save, label, and/or annotate specific recipes.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Sze, Cliff Chin Ngai; Goldenbroit, Russell; and Jeremko, Elisabeth, "Recipe Recommendations Based on Visual Input of Available Ingredients", Technical Disclosure Commons, (April 10, 2023)