Low level features for image appeal measurement

Obrador, Pere; Moroney, Nathan

doi:10.1117/12.806140

Cited by 9 publications

(18 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, similar to e.g., [12] we extract several image aesthetic appeal features (e.g., image colorfulness, aspect ratio) and consider image popularity indicators as well (i.e., view count and number of comments). For consistency reasons, we adopt notation from related work, where image aesthetic appeal features are considered to be those that influence aesthetic rating of an image [11]- [13].…”

Section: Approach Overview and Rationalementioning

confidence: 99%

Learning Crowdsourced User Preferences for Visual Summarization of Image Collections

Rudinac

Larson

Hanjalic

2013

IEEE Trans. Multimedia

View full text Add to dashboard Cite

In this paper we propose a novel approach to selecting images suitable for inclusion in the visual summaries. The approach is grounded in insights about how people summarize image collections. We utilize the Amazon Mechanical Turk crowdsourcing platform to obtain a large number of manually created visual summaries as well as information about criteria for image inclusion in the summary. Based on these large-scale user tests, we propose an automatic image selection approach, which jointly utilizes the analysis of image content, context, popularity, visual aesthetic appeal as well as the sentiment derived from the comments posted on the images. In our approach we do not describe images based on their properties only, but also in the context of semantically related images, which improves robustness and effectively enables propagation of sentiment, aesthetic appeal as well as various inherent attributes associated with a particular group of images. We discuss the phenomenon of a low inter-user agreement, which makes an automatic evaluation of visual summaries a challenging task and propose a solution inspired by the text summarization and machine translation communities. The experiments performed on a collection of geo-referenced Flickr images demonstrate the effectiveness of our image selection approach.Index Terms-Crowdsourcing, image aesthetic appeal, image content and context, image set evaluation, learning to rank, sentiment analysis, social media, user-informed visual summarization.

show abstract

Section: Approach Overview and Rationalementioning

confidence: 99%

Learning Crowdsourced User Preferences for Visual Summarization of Image Collections

Rudinac

Larson

Hanjalic

2013

IEEE Trans. Multimedia

View full text Add to dashboard Cite

show abstract

“…In this work, we take a similar approach to [24] where the representative images within a specific event cluster will be selected based on their aesthetic value [16], and images within a cluster will be ranked based on their aesthetic value as given in [23]. This algorithm measures aesthetics of an image ci, i.e., A(ci), on a region by region basis, and takes into account sharpness, contrast, colorfulness and exposure.…”

Section: A Face Aestheticsmentioning

confidence: 99%

“…However, in the case of image selection it makes more sense ranking the images within a cluster rather than classifying them. Hence, we use a regression-based computational image aesthetics algorithm based on [23]. Our system also includes regressionbased computational face aesthetics algorithm, since it has been shown that different image categories would benefit from different aesthetic metrics [22], and the best high level categorization regarding aesthetics is usually obtained by partitioning the set into people and non-people photos 5 [5].…”

Section: Aestheticsmentioning

confidence: 99%

“…Unfortunately, these type of approaches would favor a character over another based on their looks, which would go against the storytelling principles described above. In order to avoid this kind of bias, we have used a normalized face aesthetic measure (A f ) that takes into account normalized face sharpness, combined with the relative size of the face with respect to the overall image size [23], and smile detection [33]. This face aesthetic measure turns out to be very effective when comparing aesthetics of the same character 's face, i.e., within the same character 's face cluster.…”

Section: A Face Aestheticsmentioning

confidence: 99%

See 1 more Smart Citation

Supporting personal photo storytelling for social albums

Obrador

Oliveira

Oliver

2010

Proceedings of the 18th ACM International Conference on Multimedia

Self Cite

View full text Add to dashboard Cite

Information overload is one of today's major concerns. As high-resolution digital cameras become increasingly pervasive, unprecedented amounts of social media are being uploaded to online social networks on a daily basis. In order to support users on selecting the best photos to create an online photo album, attention has been devoted to the development of automatic approaches for photo storytelling. In this paper, we present a novel photo collection summarization system that learns some of the users' social context by analyzing their online photo albums, and includes storytelling principles and face and image aesthetic ranking in order to assist users in creating new photo albums to be shared online. In an in-depth user study conducted with 12 subjects, the proposed system was validated as a first step in the photo album creation process, helping users reduce workload to accomplish such a task. Our findings suggest that a human audio/video professional with cinematographic skills does not perform better than our proposed system.

show abstract

“…9. Combined Aesthetics: Combination of attributes 5-8 into a single metric, computed similar to [11].…”

Section: Modeling Image Appealmentioning

confidence: 99%

Modeling Image Appeal Based on Crowd Preferences for Automated Person-Centric Collage Creation

Vonikakis

Subramanian

Arnfred

2014

Proceedings of the 2014 International ACM Workshop on Crowdsourcing for Multimedia

View full text Add to dashboard Cite

This paper attempts to model Image Appeal of photos portraying people, with the objective of automatically ranking and selecting the most appealing ones for the creation of interesting person-centric collages/collections. To understand the notion of image appeal, we employed crowdsourcing, using 350 workers who were asked to select a representative subset of images from five different person-centric album themes (involving a man, woman, couple, girl and baby). The albums were previously balanced with respect to nine different image attributes using Binary Integer Programming. The crowdsourcing study revealed identifiable patterns in the photo selection process, with more appealing photos securing more hits than less appealing ones. We then employed nine low-level image features and Support Vector Regressors to model photo selection statistics-the best model explained 63% of the selection patterns, and our analyses also confirmed the role of context in influencing Image Appeal. Finally, Image Appeal predictions on unseen photos are presented to demonstrate the promise of our approach.

show abstract

Low level features for image appeal measurement

Cited by 9 publications

References 18 publications

Learning Crowdsourced User Preferences for Visual Summarization of Image Collections

Learning Crowdsourced User Preferences for Visual Summarization of Image Collections

Supporting personal photo storytelling for social albums

Modeling Image Appeal Based on Crowd Preferences for Automated Person-Centric Collage Creation

Contact Info

Product

Resources

About