SnapChef - AI-powered recipe suggestions - evaluating an Android prototype

Sep 11, 2026

AI-powered technologies are expanding into consumer scenarios, enabling practical solutions for daily needs and sustainability challenges. This paper presents the design, implementation, and evaluation of SnapChef, a recipe recommendation mobile application that uses computer vision for ingredient identification and a large language model to generate recipe suggestions. A System Usability Scale (SUS) assessment on an Android software prototype produced strongly positive user feedback, reflecting high usability satisfaction. Limitations in image recognition accuracy are discussed, along with expectations for continued improvement as the underlying AI matures.

LanguageEnglish

CategoryPresentations

FormatPDF

Pages13

Reading Time5 min

AccessFree to download

Introduction

Food waste context and motivation

AI and model foundations for recommendation

SnapChef: AI-powered Recipe Suggestions⋆ Santiago Ruiz-Rincón* , Ixent Galpin Universidad de Bogotá-Jorge Tadeo Lozano, Bogotá, Colombia Abstract AI-powered technologies are becoming pervasive, and offer endless possibilities for novel consumer applications. This paper describes the comprehensive process of designing, implementing, and evaluating SnapChef, an innovative recipe recommendation application. The results of the System Usability Scale (SUS) study conducted over a software prototype using the Android platform yielded overwhelmingly positive user feedback, indicating a high level of satisfaction with the application’s usability. Despite noted imperfections in image recognition accuracy, we anticipate significant enhancements in this aspect as AI technology continues to evolve and mature over time. These findings underscore the potential for continual improvement and optimization of our application to meet user needs and expectations in the dynamic landscape of AI-driven technologies. Keywords Computer vision, Image recognition, Large Language Models, Artificial Intelligence 1. Introduction Food waste is a major global issue [1] . In the United States, 38% of food produced annually is not consumed, representing a costly issue equivalent to approximately 1.8% of the GDP. [2] . Despite often being overlooked, approximately two-thirds ofthe food discarded in households is due to spoilage before it can be utilized [3] . Food waste may occur in different stages in the supply chain, from production and harvesting, to retail and distribution, to consumer behaviour. It may be a result of overproduction, inefficient storage, transport issues, as well as strict aesthetic standards. Consumer behaviors such as overbuying and improper storage also contribute significantly, as well as date label confusion. Regardless of the reasons for underutilizing our food, it is imperative to address this issue because agriculture is an activity that demands extensive resources, in terms of land, water and labor [4] . Over the last decade we have witnessed a boom of artificial intelligence (AI) technologies. Computer vision has advanced significantly leveraged by deep learning approaches, in particular convolutional neural networks [5, 6] . One the other hand, generative AI also promises a plethora of new applications [7] . For example, generative AI has found novel applications in creating realistic virtual characters for videogames, generating personalized content for marketing campaigns, and designing complex molecules for pharmaceutical research [7] . While still in their infancy, Large Language Models such as GPT- 4 for natural language processing, BERT for understanding context in text, and T5 for text-to-text transformations offer possibilities to apply artificial intelligence to help solve novel problems to bring about positive changes to our society [8] . Despite their potential, these technologies face several challenges due to their recent development; one key consideration is their lack of complete accuracy, which makes them susceptible to errors and incoherent results. However, significant advances in the technology’s responsiveness are expected over time. In this work, we leverage recent trends in AI technologies to address the issue of food wastage that occurs as a result of consumer behavior. We introduce SnapChef, a mobile application that allows users to photograph food ingredients in their kitchen cupboard or fridge and receive a list of recipe recommendations. This process involves two steps: first, computer vision techniques identify the set of food ingredients; second, a Large Language Model generates a list of recipe suggestions based on ICAIW 2024: Workshops at the 7th International Conference on Applied Informatics 2024, October 24 –26, 2024, Viña del Mar, Chile ⋆ We wish to credit ChatGPT for suggesting the name “SnapChef” for our application. * Corresponding author. $ [santiago.ruizr@utade

FAQs

What is SnapChef and what problem does it address?

SnapChef is an AI-powered mobile recipe recommendation application aimed at reducing food waste driven by consumer behavior through ingredient-based recommendations.

How does SnapChef generate recipe suggestions?

It uses computer vision to identify food ingredients from a user photo, then a large language model generates recipe suggestions based on the detected ingredients.

What were the evaluation results of the SnapChef prototype?

System Usability Scale (SUS) results from an Android prototype indicated overwhelmingly positive feedback and a high level of user satisfaction with usability.

Sep 11, 2026

Uploaded by River Wang