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.

中文翻译：

---

具有多结构和自动编码感受野的极限学习机，用于图像分类

为了充分提取和利用图像中的可识别信息以提高分类精度，基于局部感受野的极限学习机（ELM-LRF）提出了具有多结构和自动编码感受野的极限学习机（ELM-MAERF） . ELM-MAERF 主要由两个卷积池化层、并行编码器和分类器组成。在两个卷积池化层中，局部感受野和全连接感受野利用 ELM 自编码器的理论进行训练。训练后的感受野用于提取局部特征、多通道特征和全连接特征。并行编码器用于充分编码和融合这些特征。用近似经验核图训练的分类器对融合特征进行分类，可以有效避免处理大型数据库带来的计算困难。为了证明 ELM-MAERF 的有效性，在四个数据库上进行了实验：Yale、MNIST、NORB 和 Caltech。实验结果证明了 ELM-MAERF 中受训感受野和结构的有效性。与基于ELM-LRF的改进方法相比，ELM-MAERF提高了分类精度。