About this Research Topic
Accurately assessing food intake is essential for understanding the effect of diet on health and disease and evaluating the efficacy of dietary interventions. However, accurate assessment of energy (kcal) intake, diet quality, meal timing, and the day-to-day variability of eating behavior remains a major challenge. Traditional dietary assessment methods (e.g., paper-based food records) are frequently used, despite being burdensome to complete and analyze. In addition, traditional assessment methods don’t allow for real-time or near real-time feedback on dietary intake, which is important for healthy behavior change. Consequently, there has been a shift to developing new technologies for assessing dietary intake (e.g., computer vision for volume estimation and food identification). The field of technology-based dietary assessment with real-time or near real-time feedback dietary feedback is growing rapidly in research and commercial settings. Therefore, there is an ongoing need to report on the validity and effectiveness of this technology.
The goal of this Research Topic is to present emerging methods for measuring food intake behavior in laboratory and free-living conditions. To more reliably track food intake behavior, these methods include mobile apps and remote captors of behavior, and are ideally validated against gold-standard methods.
This Research Topic will present readers with updated research on technology-based dietary assessment tools with real-time or near real-time feedback capabilities. This includes methods papers, validity studies, pilot studies, systematic reviews, and behavior change techniques. All papers submitted should clearly detail the nutrient database used for the dietary assessment method, including for both the experimental and gold standard method. We encourage submissions from academia, not for profit organizations, government agencies, and industry, and submission from a wide range of disciplines including nutrition, engineering, computer science, and so forth.
Example topics that could be considered include:
• Image-based food recognition
• Image-based ingredients recognition
• Image datasets for machine learning in healthy nutrition
• Personalization of healthy nutrition using image cues
• Image-based recommenders in healthy nutrition
• Image-based methods in food industry
• Imaging and computer vision for raw food diet applications
• Image-based methods in assessing raw fruits and vegetables in the field and in the market
• Image-based methods in assessing dried fruits and vegetables
• Computer vision in vegetable and fruit produce
• Computer vision in organic farming applications
• Image-based sorting in food processing chains
• Image-based methods for blood sugar-related food identification and planning
• Diabetes diets and image based methods in food recognition
• Quality control in food chains based on imaging technologies
• Computer vision for food quality assurance
• Tomographic approaches in food properties analysis
• Multi/Hyper-spectral imaging in food identification and quality assessment
• Tracking and tracing of foods using image-based methods
• Imaging and gamification in building healthy nutrition habits
Articles covering dietary assessment techniques that do not provide automated or semi-automated feedback in real-time or near real-time will not be considered for this Research Topic. For example, articles covering food records where images need to be analyzed on the back end by a trained professional before the nutrition feedback is presented to the user.
The goal of this Research Topic is to present emerging methods for measuring food intake behavior in laboratory and free-living conditions. To more reliably track food intake behavior, these methods include mobile apps and remote captors of behavior, and are ideally validated against gold-standard methods.
This Research Topic will present readers with updated research on technology-based dietary assessment tools with real-time or near real-time feedback capabilities. This includes methods papers, validity studies, pilot studies, systematic reviews, and behavior change techniques. All papers submitted should clearly detail the nutrient database used for the dietary assessment method, including for both the experimental and gold standard method. We encourage submissions from academia, not for profit organizations, government agencies, and industry, and submission from a wide range of disciplines including nutrition, engineering, computer science, and so forth.
Example topics that could be considered include:
• Image-based food recognition
• Image-based ingredients recognition
• Image datasets for machine learning in healthy nutrition
• Personalization of healthy nutrition using image cues
• Image-based recommenders in healthy nutrition
• Image-based methods in food industry
• Imaging and computer vision for raw food diet applications
• Image-based methods in assessing raw fruits and vegetables in the field and in the market
• Image-based methods in assessing dried fruits and vegetables
• Computer vision in vegetable and fruit produce
• Computer vision in organic farming applications
• Image-based sorting in food processing chains
• Image-based methods for blood sugar-related food identification and planning
• Diabetes diets and image based methods in food recognition
• Quality control in food chains based on imaging technologies
• Computer vision for food quality assurance
• Tomographic approaches in food properties analysis
• Multi/Hyper-spectral imaging in food identification and quality assessment
• Tracking and tracing of foods using image-based methods
• Imaging and gamification in building healthy nutrition habits
Articles covering dietary assessment techniques that do not provide automated or semi-automated feedback in real-time or near real-time will not be considered for this Research Topic. For example, articles covering food records where images need to be analyzed on the back end by a trained professional before the nutrition feedback is presented to the user.
Keywords: computer vision, machine learning, artificial intelligence, image processing, food image, food recognition, image-based, Nutrition AI, mobile food record, dietary assessment, just-in-time
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
