Techniques for Still Image Scene Classification and Object Detection
In this paper we consider the interaction between different semantic levels in still image scene classification and object detection problems. We present a method where a neural method is used to produce a tentative higher-level semantic scene representation from low-level statistical visual features in a bottom-up fashion. This emergent representation is then used to refine the lower-level object detection results. We evaluate the proposed method with data from Pascal VOC Challenge 2006 image classification and object detection competition. The proposed techniques for exploiting global classification results are found to significantly improve the accuracy of local object detection.
KeywordsObject Detection Object Class Image Scene Hierarchical Segmentation Visual Object Class
Unable to display preview. Download preview PDF.
- 1.ISO/IEC. Information technology - Multimedia content description interface - Part 3: Visual (2002) 15938-3:2002(E)Google Scholar
- 3.Koikkalainen, P.: Progress with the tree-structured self-organizing map. In: 11th European Conference on Artificial Intelligence. European Committee for Artificial Intelligence (ECCAI) (August 1994)Google Scholar
- 4.Koskela, M., Laaksonen, J., Sjöberg, M., Muurinen, H.: PicSOM experiments in TRECVID 2005. In: Proceedings of the TRECVID 2005 Workshop, Gaithersburg, MD, USA, pp. 262–270 (November 2005)Google Scholar
- 5.Laaksonen, J., Koskela, M., Oja, E.: PicSOM—Self-organizing image retrieval with MPEG-7 content descriptions. IEEE Transactions on Neural Networks, Special Issue on Intelligent Multimedia Processing 13(4), 841–853 (2002)Google Scholar