With the technological evolution of digital acquisition and storage technologies, millions of images and video sequences are captured every day and shared in online services. This has resulted in a continuously growing volume of publicly available photos and videos. For instance, Facebook has approximately 100 billion photos stored on its servers, and every minute, more than 48 hours of video are uploaded to YouTube. One way of exploring this huge volume of images and videos is through searching a particular object depicted in such content by making use of object duplicate detection. It can be applied to several image and video retrieval applications, such as tag propagation, augmented reality, video surveillance, mobile visual search, and television channel monitoring. Therefore, there is a need of improving current object duplicate detection algorithms.
We proposed a graph-based approach for 2D and 3D object duplicate detection in still images. A graph model is used to represent the 3D spatial information of the object based on the features extracted from training images so that an explicit and complex 3D object modeling is avoided. Therefore, improved performance can be achieved in comparison to existing methods in terms of both robustness and computational complexity. Different limitations of our approach are analyzed by evaluating performance with respect to the number of training images and calculation of optimal parameters in a number of applications. Furthermore, effectiveness of our object duplicate detection algorithm is measured over different object classes. Our method is shown to be robust in detecting the same objects even when images with objects are taken from very different viewpoints or distances.
- Graph-based approach for 3D object duplicate detection (presented at WIAMIS’09) [paper]
- Analysis of the limits of graph-based object duplicate detection (presented at ISM’09) [paper]
- 3D object duplicate detection for video retrieval (presented at WIAMIS’10) [paper]
- Propagation of geotags based on object duplicate detection (presented at SPIE’10) [paper]
- Omnidirectional object duplicate detection (presented at DSPE’11) [paper]
- Robust duplicate detection of 2D and 3D objects (published in IJMDEM) [paper]