Abstract | ||
---|---|---|
This paper presents a set of effective and efficient features, namely strip features, for detecting objects in real-scene images. Although shapes of a specific class usually have large intraclass variance, some basic local shape elements are relatively stable. Based on this observation, we propose a set of strip features to describe the appearances of those shape elements. Strip features capture object shapes with edgelike and ridgelike strip patterns, which significantly enrich the efficient features such as Haar-like and edgelet features. The proposed features can be efficiently calculated via two kinds of approaches. Moreover, the proposed features can be extended to a perturbed version (namely, perturbed strip features) to alleviate the misalignment caused by deformations. We utilize strip features for object detection under an improved boosting framework, which adopts a complexity-aware criterion to balance the discriminability and efficiency for feature selection. We evaluate the proposed approach for object detection on the public data sets, and the experimental results show the effectiveness and efficiency of the proposed approach. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/TSMCB.2012.2235066 | IEEE T. Cybernetics |
Keywords | Field | DocType |
feature selection efficiency,edge-likestrip patterns,ridge-like strip patterns,learning (artificial intelligence),fast object detection,strip features,complexity-aware criterion,feature extraction,improved boosting framework,object detection,shape elements,real-scene images,intraclass variance,feature selection discriminability,perturbed strip features,learning artificial intelligence | Viola–Jones object detection framework,Data set,Feature selection,Computer science,Haar-like features,Artificial intelligence,Computer vision,Object detection,Pattern recognition,Object-class detection,Feature extraction,Boosting (machine learning),Machine learning | Journal |
Volume | Issue | ISSN |
43 | 6 | 2168-2275 |
Citations | PageRank | References |
5 | 0.45 | 32 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Wei Zheng | 1 | 71 | 4.82 |
Hong Chang | 2 | 1834 | 96.46 |
Luhong Liang | 3 | 420 | 29.04 |
Haoyu Ren | 4 | 50 | 7.81 |
Shiguang Shan | 5 | 6322 | 283.75 |
Xilin Chen | 6 | 6291 | 306.27 |