Extreme learning machine with multi-structure and auto encoding receptive fields for image classification

Abstract

In order to adequately extract and utilize identifiable information in the image to improve classification accuracy, extreme learning machine with multi-structure and auto encoding receptive fields (ELM-MAERF) is proposed based on local receptive fields based extreme learning machine (ELM-LRF). The ELM-MAERF is mainly composed of two convolution-pooling layers, parallel encoders and classifier. In the two convolution-pooling layers, the local receptive fields and the fully connected receptive fields are trained by utilizing the theory of ELM autoencoder. The trained receptive fields are used to extract local features, multi-channel features and fully connected features. Parallel encoders are used to adequately encode and fuse these features. The classifier trained by the approximate empirical kernel map is used to classify the fusion features, which can effectively avoid the computational difficulties caused by processing large database. To demonstrate the effectiveness of ELM-MAERF, experiments are performed on four databases: Yale, MNIST, NORB and Caltech. The experimental results demonstrate the validity of trained receptive fields and structures in ELM-MAERF. Compared with the improved method based on ELM-LRF, the classification accuracy is improved by ELM-MAERF.