Landscape photo classification mechanism for context-aware photography support system

This paper presents landscape photo classification mechanisms to enhance our proposed photography support system named Phorec. The system utilizes big data in social photo stock services and online historical weather database to recommend relevant photos based on user's natural contexts, including location, time, and weather condition. In order to help user take better photos, important information, such as camera setting, time, and location, is displayed with the photo selected by the user. Since the aim of Phorec is to support not only photographers but also general users as a travel assistant, we mainly focus on the landscape photos. From the huge collected data, landscape photos classification is required to extract the landscape photos from the uncategorized photos. In this paper, some possible landscape classification techniques are investigated and evaluated with our collected dataset. In addition to the straightforward tag analysis and Exif analysis method, we propose a unique method that utilizes a common face recognition technique for excluding non-landscape photos. Experimental results show that our proposed people-exclusion method works well for excluding non-landscape photos from the collected various photo.

[1]  Dewen Hu,et al.  Scene classification using a multi-resolution bag-of-features model , 2013, Pattern Recognit..

[2]  Barry Smyth,et al.  The social camera: a case-study in contextual image recommendation , 2011, IUI '11.

[3]  Sameer Singh,et al.  Indoor vs. outdoor scene classification in digital photographs , 2005, Pattern Recognit..

[4]  Jiebo Luo,et al.  Photo classification by integrating image content and camera metadata , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[5]  Anil K. Jain,et al.  On image classification: city images vs. landscapes , 1998, Pattern Recognit..

[6]  Barbara Scifo,et al.  The Sociocultural Forms of Mobile Personal Photographs in a Cross-Media Ecology: Reflections Starting from the Young Italian Experience , 2009 .

[7]  Changsheng Xu,et al.  Tag-aware image classification via Nested Deep Belief nets , 2013, 2013 IEEE International Conference on Multimedia and Expo (ICME).

[8]  Daniel P. Huttenlocher,et al.  Landmark classification in large-scale image collections , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[9]  Martin Szummer,et al.  Indoor-outdoor image classification , 1998, Proceedings 1998 IEEE International Workshop on Content-Based Access of Image and Video Database.

[10]  Jean H. Meeus,et al.  Astronomical Algorithms , 1991 .

[11]  Matthijs C. Dorst.  Distinctive Image Features from Scale-Invariant Keypoints , 2011 .

[12]  Gang Wang,et al.  Building text features for object image classification , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[13]  Cordelia Schmid,et al.  Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).