Efficient Object Detection and Segmentation for Fine-Grained Recognition
Authors:
- Anelia AngelovaAAAnelia Angelova
- Shenghuo ZhuSZShenghuo Zhu
- 1 June 2013
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 811-818
Abstract
We propose a detection and segmentation algorithm for the purposes of fine-grained recognition. The algorithm first detects low-level regions that could potentially belong to the object and then performs a full-object segmentation through propagation. Apart from segmenting the object, we can also `zoom in' on the object, i.e. center it, normalize it for scale, and thus discount the effects of the background. We then show that combining this with a state-of-the-art classification algorithm leads to significant improvements in performance especially for datasets which are considered particularly hard for recognition, e.g. birds species. The proposed algorithm is much more efficient than other known methods in similar scenarios. Our method is also simpler and we apply it here to different classes of objects, e.g. birds, flowers, cats and dogs. We tested the algorithm on a number of benchmark datasets for fine-grained categorization. It outperforms all the known state-of-the-art methods on these datasets, sometimes by as much as 11%. It improves the performance of our baseline algorithm by 3-4%, consistently on all datasets. We also observed more than a 4% improvement in the recognition performance on a challenging large-scale flower dataset, containing 578 species of flowers and 250,000 images.Keywords
This publication has 13 references indexed in Scilit:
- Modeling the spatial layout of images beyond spatial pyramidsPattern Recognition Letters, 2012
- Birdlets: Subordinate categorization using volumetric primitives and pose-normalized appearance2011
- Combining randomization and discrimination for fine-grained image categorization2011
- Large-scale image classification: Fast feature extraction and SVM training2011
- Discriminative clustering for image co-segmentation2010
- An Efficient Approach to Semantic SegmentationInternational Journal of Computer Vision, 2010
- Closing the loop in scene interpretation2008
- Histograms of Oriented Gradients for Human Detection2005
- Efficient Graph-Based Image SegmentationInternational Journal of Computer Vision, 2004
- "GrabCut"2004