Estimating the Support of a High-Dimensional Distribution
Neural Computation
Rotation-invariant and scale-invariant Gabor features for texture image retrieval
Image and Vision Computing
Ensemble one-class support vector machines for content-based image retrieval
Expert Systems with Applications: An International Journal
Hi-index | 0.00 |
By training and predicting the features that are extracted by pulse coupled neural network (PCNN), a noise immunity texture retrieval system combined with PCNN and one-class support vector machine (OCSVM) is proposed in this paper, which effectively improve the anti-noise performance of image retrieval system. The experiment results in different noise environment show that our proposed algorithm is able to obtain higher retrieval accuracy and better robustness to noise than traditional Euclidean distance based system.