论文信息 - Analysis on low-resolution image correlation pattern recognition algorithm in finite space

Analysis on low-resolution image correlation pattern recognition algorithm in finite space

Abstract Because traditional correlation pattern recognition algorithm cannot accurately identify low-resolution images, a low-resolution image correlation pattern recognition algorithm based on block-centric symmetric local binary model and weighted principal component analysis algorithm is proposed. Firstly, the feature of low-resolution image is extracted by using block CS-LBP operator. The weighted PCA operator is used to reduce the feature, and the classification feature is obtained. Secondly, the optimal classification class is selected by the nearest neighbor classifier, the recognition rate is calculated, and the whole algorithm is analyzed. Finally, the experiment is carried out. The experimental results showed that the algorithm has good recognition effect on ORL, and it is robust to the change of light and weather.

Gang Li | Yanling Li

[1] Jie Zheng,et al. Identification of lesion images from gastrointestinal endoscope based on feature extraction of combinational methods with and without learning process , 2016, Medical Image Anal..

[2] Yong He,et al. A Novel Hyperspectral Feature-Extraction Algorithm Based on Waveform Resolution for Raisin Classification , 2015, Applied spectroscopy.

[3] Li Sun,et al. Directional feature: a novel feature for group target detection in high resolution SAR images , 2017 .

[4] Ezzatollah Salari,et al. Single-image super resolution using evolutionary sparse coding technique , 2017, IET Image Process..

[5] Yaochu Jin,et al. Evolutionary Multiobjective Image Feature Extraction in the Presence of Noise , 2015, IEEE Transactions on Cybernetics.

[6] Carlas S. Smith,et al. Probability-based particle detection that enables threshold-free and robust in vivo single-molecule tracking , 2015, Molecular biology of the cell.