Visual Cultural Biases in Food Classification

Zhang, Qing; Elsweiler, David; Trattner, Christoph

doi:10.3390/foods9060823

Cited by 11 publications

(8 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhang and Luo (2018) extract composition attributes of food images from Yelp to predict restaurant survival. Zhang et al (2020) use a combination of food image attributes and deep learning generated representations to capture visual cultural bias in food classification. However, studies using food images in hospitality research are still limited.…”

Section: Related Literaturementioning

confidence: 99%

Camera eats first: exploring food aesthetics portrayed on social media using deep learning

Gambetti

Han²

2022

IJCHM

View full text Add to dashboard Cite

Purpose The purpose of this paper is to explore and examine discrepancies of food aesthetics portrayed on social media across different types of restaurants using a large-scale data set of food images. Design/methodology/approach A neural food aesthetic assessment model using computer vision and deep learning techniques is proposed, applied and evaluated on the food images data set. In addition, a set of photographic attributes drawn from food services and cognitive science research, including color, composition and figure–ground relationship attributes is implemented and compared with aesthetic scores for each food image. Findings This study finds that restaurants with different rating levels, cuisine types and chain status have different aesthetic scores. Moreover, the authors study the difference in the aesthetic scores between two groups of image posters: customers and restaurant owners, showing that the latter group tends to post more aesthetically appealing food images about the restaurant on social media than the former. Practical implications Restaurant owners may consider performing more proactive social media marketing strategies by posting high-quality food images. Likewise, social media platforms should incentivize their users to share high-quality food images. Originality/value The main contribution of this paper is to provide a novel methodological framework to assess the aesthetics of food images. Instead of relying on a multitude of standard attributes stemming from food photography, this method yields a unique one-take-all score, which is more straightforward to understand and more accessible to correlate with other target variables.

show abstract

Section: Related Literaturementioning

confidence: 99%

Camera eats first: exploring food aesthetics portrayed on social media using deep learning

Gambetti

Han²

2022

IJCHM

View full text Add to dashboard Cite

show abstract

“…For example, industry might afford higher budgets for recruiting data subjects, but individuals may lack the domain-specific information of professionals working in, for example, marine biology (relevant to fishery datasets); nor did dataset authors report how identity characteristics might impact the perspectives of annotators, such as how local or regional culture might influence perspectives on beauty. Instead, they assumed that there are inherently neutral practices to strive for, disregarding the rich scholarly history discussing how all human decisions are inherently value-laden [115,118,122].…”

Section: Impartiality Over Positionalitymentioning

confidence: 99%

Do Datasets Have Politics? Disciplinary Values in Computer Vision Dataset Development

Scheuerman

Hanna

Denton

2021

Proc. ACM Hum.-Comput. Interact.

131

View full text Add to dashboard Cite

Data is a crucial component of machine learning. The field is reliant on data to train, validate, and test models. With increased technical capabilities, machine learning research has boomed in both academic and industry settings, and one major focus has been on computer vision. Computer vision is a popular domain of machine learning increasingly pertinent to real-world applications, from facial recognition in policing to object detection for autonomous vehicles. Given computer vision's propensity to shape machine learning research and impact human life, we seek to understand disciplinary practices around dataset documentation-how data is collected, curated, annotated, and packaged into datasets for computer vision researchers and practitioners to use for model tuning and development. Specifically, we examine what dataset documentation communicates about the underlying values of vision data and the larger practices and goals of computer vision as a field. To conduct this study, we collected a corpus of about 500 computer vision datasets, from which we sampled 114 dataset publications across different vision tasks. Through both a structured and thematic content analysis, we document a number of values around accepted data practices, what makes desirable data, and the treatment of humans in the dataset construction process. We discuss how computer vision datasets authors value efficiency at the expense of care; universality at the expense of contextuality; impartiality at the expense of positionality; and model work at the expense of data work. Many of the silenced values we identify sit in opposition with social computing practices. We conclude with suggestions on how to better incorporate silenced values into the dataset creation and curation process. CCS Concepts: • Human-centered computing → Collaborative and social computing; • Computing methodologies → Artificial intelligence.

show abstract

“…An interesting study applying machine learning techniques to predict the preferred recipes using low-level image features and recipe meta-data as predictors was presented by Elsweiler et al to improve the selection of recipes towards healthier [ 14 , 15 ].…”

Section: Introductionmentioning

confidence: 99%

Photograph Based Evaluation of Consumer Expectation on Healthiness, Fullness, and Acceptance of Sandwiches as Convenience Food

García-Segovía

Pagán-Moreno

Tárrega

et al. 2021

Foods

View full text Add to dashboard Cite

Sandwiches are the most common “casual-food” consumed by all age groups in Spain. Due to the importance of visual appearance to promote unplanned or impulse buying, foodservice and hospitality companies focus on improving the visual impression of their food menus to create an expectation that satisfies both sensory and hedonic consumer experiences. To provide a list of attributes about the visual appearance of sandwiches, 25 students were recruited from a university and were invited to participate in two nominal group technique (NGT) sessions. To understand whether a sandwiches’ appearance can influence the expectation of consumers, 259 participants completed an online survey specially designed from the results of the NGT sessions. Data were analyzed using conjoint, internal preference mapping and cluster analysis; the interaction effect by gender was also studied. The conjoint results indicate that visual perception about the filling (vegetal or pork based) plays the most key role overall in consumer expectation. When consumers choose vegetables as the filling, the consumers’ perceived sandwiches as healthier, but the pork filling was perceived as more attractive and satiating. Interaction effect by gender was observed in filling when females perceived pork filling as less healthy than vegetable. By acceptance, consumers were segmented into three groups. The first cluster (n = 80) selected the pork filling. The smaller group (cluster 3, n = 36) prioritized the vegetal filling, and the most numerous cluster 2 (n = 140) liked sandwiches with multigrain bread. These results may help companies to build tailor-made marketing strategies to satisfy consumer segments.

show abstract

Visual Cultural Biases in Food Classification

Cited by 11 publications

References 44 publications

Camera eats first: exploring food aesthetics portrayed on social media using deep learning

Camera eats first: exploring food aesthetics portrayed on social media using deep learning

Do Datasets Have Politics? Disciplinary Values in Computer Vision Dataset Development

Photograph Based Evaluation of Consumer Expectation on Healthiness, Fullness, and Acceptance of Sandwiches as Convenience Food

Contact Info

Product

Resources

About