Modern people live in an environment with ubiquitous food cues, including food advertisements, videos, and smells. Do these food cues change people\'s eating behavior? Since diet plays a crucial role in maintaining health, it has been researched for decades. As convenient alternatives for real food, food images are widely used in diet research. To date, researchers from Germany, Spain, and other countries have established food photo databases; however, these food pictures are not completely suitable for Chinese studies because of the ingredients and characteristics of Chinese food. The main goal of this research is to create a library of Chinese food images and to provide as complete a data reference as possible for future studies that use food images as experimental material. After standardized processing, we selected 508 common Chinese food pictures with high familiarity and recognizability and attached detailed classifications concerning taste, macronutrients, calories, and participants\' emotional responses to the pictures. Additionally, with food pictures as material, we conducted research on how people make dietary decisions in order to identify the variables that may affect a person\'s food choices. The effects of individual perceived healthiness and palatability, gender, BMI, family income, and levels of emotional and restricted eating were examined using eating decisions based on healthiness and palatability as dependent variables. The results showed that people with low household incomes are more likely to be influenced by food taste in their dietary decision-making process, while individuals with high household incomes are more likely to consider the healthy aspects of food. Moreover, parental BMI affects what children consume, with children who have parents with higher BMIs being more prone to overlook the healthiness value of food.

Obesity is a modern public health problem. Social media images can capture eating behavior and the potential implications to health, but research for identifying the healthiness level of the food image is relatively under-explored. This study presents a deep learning architecture that transfers features from a 152 residual layer network (ResNet) for predicting the level of healthiness of food images that were built using images from the Google images search engine gathered in 2020. Features learned from the ResNet 152 were transferred to a second network to train on the dataset. The trained SoftMax layer was stacked on top of the layers transferred from ResNet 152 to build our deep learning model. We then evaluate the performance of the model using Twitter images in order to better understand the generalizability of the methods. The results show that the model is able to predict the images into their respective classes, including Definitively Healthy, Healthy, Unhealthy and Definitively Unhealthy at an F1-score of 78.8%. This finding shows promising results for classifying social media images by healthiness, which could contribute to maintaining a balanced diet at the individual level and also understanding general food consumption trends of the public.

Deep learning models can recognize the food item in an image and derive their nutrition information, including calories, macronutrients (carbohydrates, fats, and proteins), and micronutrients (vitamins and minerals). This technology has yet to be implemented for the nutrition assessment of restaurant food. In this paper, we crowdsource 15,908 food images of 470 restaurants in the Greater Hartford region on Tripadvisor and Google Place. These food images are loaded into a proprietary deep learning model (Calorie Mama) for nutrition assessment. We employ manual coding to validate the model accuracy based on the Food and Nutrient Database for Dietary Studies. The derived nutrition information is visualized at both the restaurant level and the census tract level. The deep learning model achieves 75.1% accuracy when compared with manual coding. It has more accurate labels for ethnic foods but cannot identify portion sizes, certain food items (e.g., specialty burgers and salads), and multiple food items in an image. The restaurant nutrition (RN) index is further proposed based on the derived nutrition information. By identifying the nutrition information of restaurant food through crowdsourced food images and a deep learning model, the study provides a pilot approach for large-scale nutrition assessment of the community food environment.

We have prototyped a KANSEI multimedia display (KMMD) that is able to release scent through the screen in order to realize collaboration between images and scents. Two types of \"sukiyaki\" food videos were presented to subjects using this device, and a method for objectively evaluating the realistic sensation of the food videos was examined using biological reaction measurements. The sukiyaki scent was added to one type of video to improve appetite. Viewers\' saliva flow rate, line of sight, pupil diameter, autonomic nerve activity, and cerebral blood flow were measured at the same time, and changes in these measured values were analyzed. As a result, the scent was effective in improving the sensation, as if the food was present in front of the eyes and increasing the saliva flow rate. Additionally, in a realistic scene, it was found that the line of sight follows the performer\'s eating behavior as if the viewers themselves are eating. The sympathetic nervous system temporarily increases, mydriasis occurs, and the frontal lobe is activated. Furthermore, the possibility of objective evaluation of realistic sensations was demonstrated by the correlation between appetite, accompanied by salivary sensation, and the biological reaction measurement results.

With commercialization of deep learning (DL) models, daily precision dietary record based on images from smartphones becomes possible. This study took advantage of DL techniques on visual recognition tasks and proposed a suite of big-data-driven DL models regressing from food images to their nutrient estimation. We established and publicized the first food image database from the Chinese market, named ChinaMartFood-109. It contained 10,921 images with 23 nutrient contents, covering 18 main food groups. Inception V3 was optimized using other state-of-the-art deep convolutional neural networks, achieving up to 78 % and 94 % for top-1 and top-5 accuracy, respectively. Besides, this research compared three nutrient estimation algorithms and achieved the best regression coefficient (R2) by normalization + AM compared with arithmetic mean and harmonic mean, validating applicability in practice as well as theory. These encouraging results provide further evidence supporting artificial intelligence in the field of food analysis.

Many food decisions are made rapidly and without reflective processing. The ability to determine nutritional information accurately is a precursor of food decisions and is important for a healthy diet and weight management. However, little is known about the cognitive evaluation of food attributes based on visual information in relation to assessing nutritional content. We investigated the accuracy of visual encoding of nutritional information after brief and extended time exposures to food images. The following questions were addressed: (1) how accurately do people estimate energy and macronutrients after brief exposure to food images, and (2) how does estimation accuracy change with time exposure and the type of nutritional information? Participants were first asked to rate the energy density (calories) and macronutrient content (carbohydrates/fat/protein) of different sets of food images under three time conditions (97, 500 or 1000 ms) and then asked to perform the task with no time constraints. We calculated estimation accuracy by computing the correlations between estimated and actual nutritional information for each time exposure and compared estimation accuracy with respect to the type of nutritional information and the exposure time. The estimated and actual energy densities and individual macronutrient content were significantly correlated, even after a brief exposure time (97 ms). The degree of accuracy of the estimations did not differ with additional time exposure, suggesting that <100 ms was sufficient to predict the energy and macronutrients from food images. Additionally, carbohydrate estimates were less accurate than the estimates of other nutritional variables (proteins, fat and calories), regardless of the exposure time. These results revealed rapid and accurate assessment of food attributes based on visual information and the accuracy of visual encoding of nutritional information after brief and extended time exposure to food imagery.

We researched a method to objectively evaluate the presence of food images, for the purpose of applying it to digital signage. In this paper, we defined the presence of food images as a sensation that makes us recognize that food is there, and investigated the relationship between that recognition and the salivary secretion reaction. If saliva secretion can be detected by a non-invasive method, it may be possible to objectively estimate the presence of the viewer from the outside. Two kinds of experiments were conducted. STUDY 1 included presentations of popular cooking images, which portrayed a sense of deliciousness, and evaluated changes in the volume of saliva secretions and cerebral blood flow near the temples. STUDY 2 included comparisons of changes between presenting images only and images with corresponded smells. The images included scenes that introduced foods (i.e., almond pudding cake/bergamot orange) that were relatively simple, so that they did not induce the subjects themselves. As a result, we clarified the cross-modal effects that were closely related to sense of presence and salivation. Moreover, we clarified presentation of images with smells to improve one\'s sense of presence, even though the images were relatively simple.

Emerging data suggest that weight gain is associated with changes in neural response to palatable food tastes and palatable food cues, which may serve to maintain overeating.
We investigated whether weight gain is associated with neural changes in response to tastes of milkshakes varying in fat and sugar content and palatable food images.
We compared changes in neural activity between initially healthy-weight adolescents who gained weight (n = 36) and those showing weight stability (n = 31) over 2-3 y.
Adolescents who gained weight compared with those who remained weight stable showed decreases in activation in the postcentral gyrus, prefrontal cortex, insula, and anterior cingulate cortex, and increases in activation in the parietal lobe, posterior cingulate cortex, and inferior frontal gyrus in response to a high-fat/low-sugar compared with low-fat/low-sugar milkshake. Weight gainers also showed greater decreases in activation in the anterior insula and lateral orbitofrontal cortex in response to a high-fat/high-sugar compared with low-fat/low-sugar milkshake than those who remained weight stable. No group differences emerged in response to a low-fat/high-sugar compared with a low-fat/low-sugar milkshake. Weight gainers compared with those who remained weight stable showed greater decreases in activation in the middle temporal gyrus and increases in cuneus activation in response to appetizing compared with unappetizing food pictures. The significant interactions were partially driven by group differences in baseline responsivity and by opposite changes in neural activation in adolescents who remained weight stable.
Data suggest that weight gain is associated with a decrease in responsivity of regions associated with taste and reward processing to palatable high-fat- and high-fat/high-sugar food tastes. Data also suggest that avoiding weight gain increases taste sensitivity, which may prevent future excessive weight gain.This trial was registered at clinicaltrials.gov as NCT01949636.

Food intake and eating habits have a significant impact on people\'s health. Widespread diseases, such as diabetes and obesity, are directly related to eating habits. Therefore, monitoring diet can be a substantial base for developing methods and services to promote healthy lifestyle and improve personal and national health economy. Studies have demonstrated that manual reporting of food intake is inaccurate and often impractical. Thus, several methods have been proposed to automate the process. This article reviews the most relevant and recent researches on automatic diet monitoring, discussing their strengths and weaknesses. In particular, the article reviews two approaches to this problem, accounting for most of the work in the area. The first approach is based on image analysis and aims at extracting information about food content automatically from food images. The second one relies on wearable sensors and has the detection of eating behaviours as its main goal.

Dietary assessment, while traditionally based on pen-and-paper, is rapidly moving towards automatic approaches. This study describes an Australian automatic food record method and its prototype for dietary assessment via the use of a mobile phone and techniques of image processing and pattern recognition. Common visual features including scale invariant feature transformation (SIFT), local binary patterns (LBP), and colour are used for describing food images. The popular bag-of-words (BoW) model is employed for recognizing the images taken by a mobile phone for dietary assessment. Technical details are provided together with discussions on the issues and future work.