Creating Efficient Visual Codebook Ensembles for Object Categorization
| Autor: | Hui Wei, Hui-Lan Luo, Loi Lei Lai |
|---|---|
| Rok vydání: | 2011 |
| Předmět: |
Contextual image classification
Computer science business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Codebook Pattern recognition Machine learning computer.software_genre Ensemble learning Computer Science Applications Visualization Human-Computer Interaction Data set Set (abstract data type) ComputingMethodologies_PATTERNRECOGNITION Categorization Control and Systems Engineering Histogram Artificial intelligence Electrical and Electronic Engineering Cluster analysis business computer Software |
| Zdroj: | IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans. 41:238-253 |
| ISSN: | 1558-2426 1083-4427 |
| DOI: | 10.1109/tsmca.2010.2064300 |
| Popis: | An image comprises information, such as color, texture, shape, and intensity, which humans use in parallel for perception. Based on this knowledge, three methods of constructing visual codebook ensembles are proposed in this paper. The first technique introduced diverse individual visual codebooks by randomly choosing interesting points. The second technique was based on a random subtraining image data set with random interesting points. The third method directly utilized different patch information for constructing an ensemble with high diversity. The codebook ensembles were learned to capture and convey image properties from different aspects. Based on these codebook ensembles, different types of image presentations could be obtained. A classification ensemble could be learned based on the different expression data sets from the same training image set. The use of a classification ensemble to categorize new images can lead to improved performance. The detailed experimental analyses on several data sets revealed that the present ensemble approaches were resistant to variations in view, lighting, occlusion, and intraclass variations. In addition, they resulted in state-of-the-art performance in categorization. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|