Traffic Sign Recognition Based on Learning Vector Quantization and Convolution Neural Network
| Autor: | Xiaolan Xie, Qiangqing Zheng |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Learning vector quantization
business.industry Computer science Dimensionality reduction 020208 electrical & electronic engineering Pattern recognition 02 engineering and technology Convolutional neural network Identification (information) Computer Science::Computer Vision and Pattern Recognition Principal component analysis 0202 electrical engineering electronic engineering information engineering Traffic sign recognition 020201 artificial intelligence & image processing Artificial intelligence business Eigenvalues and eigenvectors Network model |
| Zdroj: | ICIIP |
| DOI: | 10.1145/3232116.3232145 |
| Popis: | This paper analyzes and studies the task of traffic sign recognition in the complex traffic road environment, analyzes the defects of the traditional classification algorithm and CNN (convolutional neural network) algorithm, cannot maximize the elimination of the lack of use of image disturbance information and hidden image information. This paper proposes a traffic sign recognition algorithm based on CNN, PCA (Principal Component Analysis) and LVQ (Learning Vector Quantization) algorithm, and uses PCA algorithm and LVQ algorithm to perform eigenvectors generated by CNN model. Dimensionality reduction and classification processing eliminates picture interference information and in-depth use of hidden information in pictures, further improves the accuracy of identification of traffic signs in complex environments, validates the effectiveness of the proposed method on the GTSRB data set, and relates to depth volumes. The product network model, LeNet-5, performs comparative experiments and proves that this method can further improve the classification accuracy. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|