Name
Abstract | ||
|---|---|---|
This paper proposes a discriminative model that represents an object category with a batch of boosted image patches, motivated by detecting and localizing objects with sparse features. Instead of designing features carefully and category-specifically as in previous work, we extract a massive number of local image patches from the positive object instances and quantize them as weak classifiers. Then we extend the Adaboost algorithm for learning the patch-based model integrating object appearance and structure information. With the learned model, a few features are activated to localize instances in the testing images. In the experiments, we apply the proposed method with several public datasets and achieve advancing performance. |
Year | DOI | Venue |
|---|---|---|
2010 | 10.1109/ICPR.2010.754 | ICPR |
Keywords | Field | DocType |
testing image,integrating object appearance,adaboost algorithm,image representation,object appearance,object category,patch-based model,boosted image patches,localizing object,local image patch,quantization,image patch,feature extraction,object detection,positive object instance,sparse features,object representation,discriminative model,computational modeling,prediction algorithms | Computer vision,Adaboost algorithm,Object detection,Pattern recognition,Computer science,Image representation,Feature extraction,Prediction algorithms,Artificial intelligence,Quantization (signal processing),Discriminative model | Conference |
ISSN | ISBN | Citations |
1051-4651 | 978-1-4244-7542-1 | 0 |
PageRank | References | Authors |
0.34 | 4 | 4 |