Locality sensitive batch feature extraction for high-dimensional data
| Autor: | Changyun Wen, Jie Ding, Chin Seng Chua, Guoqi Li |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Clustering high-dimensional data
0209 industrial biotechnology Computer science Cognitive Neuroscience Feature vector Feature extraction 02 engineering and technology computer.software_genre k-nearest neighbors algorithm 020901 industrial engineering & automation Artificial Intelligence 0202 electrical engineering electronic engineering information engineering Training set business.industry Dimensionality reduction Kanade–Lucas–Tomasi feature tracker Pattern recognition Manifold Computer Science Applications Data set Feature (computer vision) 020201 artificial intelligence & image processing Data mining Artificial intelligence business computer Curse of dimensionality |
| Zdroj: | Neurocomputing. 171:664-672 |
| ISSN: | 0925-2312 |
| DOI: | 10.1016/j.neucom.2015.07.076 |
| Popis: | For feature extraction, the dimensionality of the feature space is usually much larger than the size of training set. This is known as under sample problem. At this time, local structure is more important than global structure. In this paper, locality sensitive batch feature extraction (LSBFE) is derived based on a new gradient optimization model by exploiting both local and global discriminant structure of data manifold. With the proposed LSBFE, a set of features can be extracted simultaneously. Recognition rate is improved compared with batch feature extraction (BFE), which only considers global information. It is shown that the proposed method achieves good performance for face databases, handwritten digit database, object database and DBWorld data set. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect