MyPhotos: a system for home photo management and processing
Proceedings of the tenth ACM international conference on Multimedia
Detecting image orientation based on low-level visual content
Computer Vision and Image Understanding
IEEE Transactions on Pattern Analysis and Machine Intelligence
Automatic image orientation determination with natural image statistics
Proceedings of the 13th annual ACM international conference on Multimedia
Semi-automatic video annotation based on active learning with multiple complementary predictors
Proceedings of the 7th ACM SIGMM international workshop on Multimedia information retrieval
Sunset scene classification using simulated image recomposition
ICME '03 Proceedings of the 2003 International Conference on Multimedia and Expo - Volume 2
Semantic Modeling of Natural Scenes for Content-Based Image Retrieval
International Journal of Computer Vision
Smart album: photo filtering by effect detections
ACM SIGGRAPH 2008 posters
What's up CAPTCHA?: a CAPTCHA based on image orientation
Proceedings of the 18th international conference on World wide web
Orientation detection of major Indian scripts
Proceedings of the International Workshop on Multilingual OCR
Error bounds of decision templates and support vector machines in decision fusion
International Journal of Knowledge Engineering and Soft Data Paradigms
Hierarchical System for Content Based Categorization and Orientation of Consumer Images
PReMI '09 Proceedings of the 3rd International Conference on Pattern Recognition and Machine Intelligence
A Bayesian network-based framework for semantic image understanding
Pattern Recognition
Sketcha: a captcha based on line drawings of 3D models
Proceedings of the 19th international conference on World wide web
An algorithm for the automatic estimation of image orientation
MLDM'12 Proceedings of the 8th international conference on Machine Learning and Data Mining in Pattern Recognition
Hi-index | 0.00 |
Accurate and automatic image orientation detection isof great importance in image libraries. In this paper, wepresent automatic image orientation detect on algorithmsby adopting both the illuminance (structural) andchrominance (color) low-level content features. Thestatistical learning Support Vector Machines (SVMs) areused n our approach as the classifiers. The differentsources of the extracted mage features, as well as thebinary classification nature of SVM, require our system tobe able to integrate the outputs from multiple classifiers.Both static combiner (averaging) and trainable combiner(also based on SVMs) are proposed and evaluated n thiswork. In addition, two rejection options (regular and re-enforced ambiguity rejections)are employed to improveorientation detect on accuracy by sieving out mages withlow confidence values during the classification. A numberof experiments on a database of more than 14,000 mageswere performed to validate our approaches.