Ranking and classifying attractiveness of photos in folksonomies

Pedro, José San; Siersdorfer, Stefan

doi:10.1145/1526709.1526813

Cited by 88 publications

(90 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, aesthetic pleasing photographs satisfying composition rules are desirable to be selected as an input photograph for transforming it to artistic images, e.g. by using a photograph ranking system [7]. Finally, comparison with the technique by Son et al [8] which is a detail enhancing method similar to our HPUM.…”

Section: Methodsmentioning

confidence: 99%

Hue-Preserving Unsharp-Masking for Color Image Enhancement

Urahama

2014

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

Section: Methodsmentioning

confidence: 99%

Hue-Preserving Unsharp-Masking for Color Image Enhancement

Urahama

2014

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

“…To this end, tags are manually classified into several categories such as Person, Location, Place, Object, Event, and Activity. Analysis of visual and textual image (meta-)data is applied to tackle a variety of problems, such as determining attractiveness [25] or quality [27] of photos, search result diversification [28], and others. Figueiredo et al [26] analyze the quality of textual features available in Web 2.0 systems and their usefulness for classification.…”

Section: International Journal For Research In Applied Science and Engimentioning

confidence: 99%

Survey on Privacy Policy Specification System for User Uploaded Images Over Popular Content Sharing Sites

Hirulkar¹

2017

IJRASET

View full text Add to dashboard Cite

The regular use of social networking websites and application encompasses the collection and retention of personal and very often sensitive information about users. This information needs to remain private and each social network owns a privacy policy that describes in-depth how user's information is managed and published. As there is increasing use of images for sharing through social sites, maintaining privacy has become a major problem. In light of these incidents, the need of tools to aid users control access to their shared content is necessary. This problem can be proposed by using an Privacy Policy Prediction system to help users compose privacy settings for their shared images. To examine the indicators of users privacy preferences one can use the role of social context, image content, and metadata as possible according to information available. Our solution relies on a two-level framework which according to the user's available history on the site, determines the best available privacy policy for the user's images being uploaded. We propose a two-level image classification framework to obtain image categories which may be associated with similar policies. Then, we develop a policy prediction algorithm to automatically generate a policy for each newly uploaded image. This will generate policies that will follow the evolution of user's privacy according to his requirement.

show abstract

“…For instance, appealing images tend to have higher colourfulness, increased contrast and sharpness [52]; we apply image analysis to extract these features. Bag-of-words textual features extracted from the title and tags can also provide information about the image quality and aesthetics.…”

Section: Image Attractivenessmentioning

confidence: 99%