A Survey on Food Computing (1808.07202v5)

Abstract: Food is very essential for human life and it is fundamental to the human experience. Food-related study may support multifarious applications and services, such as guiding the human behavior, improving the human health and understanding the culinary culture. With the rapid development of social networks, mobile networks, and Internet of Things (IoT), people commonly upload, share, and record food images, recipes, cooking videos, and food diaries, leading to large-scale food data. Large-scale food data offers rich knowledge about food and can help tackle many central issues of human society. Therefore, it is time to group several disparate issues related to food computing. Food computing acquires and analyzes heterogenous food data from disparate sources for perception, recognition, retrieval, recommendation, and monitoring of food. In food computing, computational approaches are applied to address food related issues in medicine, biology, gastronomy and agronomy. Both large-scale food data and recent breakthroughs in computer science are transforming the way we analyze food data. Therefore, vast amounts of work has been conducted in the food area, targeting different food-oriented tasks and applications. However, there are very few systematic reviews, which shape this area well and provide a comprehensive and in-depth summary of current efforts or detail open problems in this area. In this paper, we formalize food computing and present such a comprehensive overview of various emerging concepts, methods, and tasks. We summarize key challenges and future directions ahead for food computing. This is the first comprehensive survey that targets the study of computing technology for the food area and also offers a collection of research studies and technologies to benefit researchers and practitioners working in different food-related fields.

• The paper provides a comprehensive review of food computing, detailing methods for data acquisition, analysis, and major computational tasks.
• It outlines advanced techniques such as CNN-based food recognition, cross-modal retrieval, and personalized recommendation systems.
• It identifies challenges like data heterogeneity and proposes future directions including large-scale datasets and multimodal knowledge graphs.

Overview of "A Survey on Food Computing"

The paper "A Survey on Food Computing" by Weiqing Min et al. presents a comprehensive examination of food computing, an emergent interdisciplinary field leveraging computational approaches to analyze large-scale food data. This research area synthesizes methods from computer science and other domains to address food-related issues pertinent to health, culture, and agriculture. The paper encapsulates the facets of food computing including data acquisition, analysis, major tasks, and broad applications while highlighting challenges and suggesting future research directions.

Food computing is predicated on the aggregation and examination of heterogeneous food data sourced from social media, Internet of Things (IoT) devices, recipe websites, and others. This data facilitates the development of applications such as dietary management, cultural analysis, and culinary science innovations. The paper acknowledges the infancy of systematic reviews in this field and thus provides an in-depth and organized outline of present concepts, methodologies, and tasks.

Key Topics and Methodologies

1. Food Data Acquisition and Analysis: The paper outlines the profusion of data available due to modern digital platforms. This data ranges from recipes and food images to cooking videos and health attributes. Diverse data sources include social media, such as Instagram for visual data, recipe-sharing websites like Allrecipes for textual and structured data, and IoT devices for location and sensor-based information.
2. Principal Tasks in Food Computing:
   • Perception and Recognition: The intrinsic challenges of food recognition, such as the deformable and complex nature of food items, require sophisticated computer vision techniques. The utilization of Convolutional Neural Networks (CNNs) has shown promise in single-label and multi-label food recognition.
   • Retrieval: Given a food image, systems can retrieve corresponding recipes or related images utilizing cross-modal retrieval techniques. This area leverages feature extraction and learning methods like deep learning models.
   • Recommendation Systems: These systems, which span nutritional aspects and cultural relevance, necessitate integrating user preferences, contextual information, and content-based approaches to offer personalized recommendations.
   • Prediction and Monitoring: Predictive analysis on social networks offers insights into dietary trends and public health implications, correlating food choices with societal health metrics.
3. Applications: The paper documents the application of food computing in health monitoring, cultural paper, agriculture, and food science. For example, systems for monitoring nutrient intake from food images aid in managing dietary habits. Furthermore, analyzing culinary norms through recipes and social media provides cultural insights.

Challenges and Future Directions

The discussed challenges include the difficulty of accurate food recognition due to the fine-grained and multimodal nature of food data. Another challenge lies in the integration of diverse data sources and achieving context-aware, personalized health recommendations. The paper proposes the development of a large-scale food dataset akin to ImageNet, the enhancement of recognition systems with deep learning, and the establishment of multimodal knowledge graphs. Such advances would not only augment food computing capabilities but also extend to use in smart home systems, restaurants, and personalized health services.

In summation, this survey lays the groundwork for future research in food computing by delineating current methodologies and applications while emphasizing the untapped potential in enhancing human health, understanding cultural identities, and fostering innovations in food science and technology.