Recipe Recommendation Method by Similarity Measure with Food Image Recognition

Abstract

This paper presents a recipe recommendation method by similarity measure with food image recognition. In general, it is difficult for users with little cooking experience to find out what kind of dishes they can make from the ingredients they currently have. Therefore, we propose a system that recommends recipes based on the ingredients in the user's current inventory, thereby increasing the number of dishes in the user's cooking repertoire. This system uses camera images of foodstuffs as input, recognizes the foodstuffs, and searches for recipes. In the experiment, we conducted a questionnaire survey of the recognized food ingredients and a questionnaire survey of recipe suggestions, and the results showed that more than 3/4 of the respondents answered that the recognition results and recipe contents were correct for some of the images. In this way, possible for users to search for recipes with fewer steps.