Scene recognition is an essential part in the vision-based robot navigation domain. The successful application of deep learning technology has triggered more extensive preliminary studies on scene recognition, which all use extracted features from networks that are trained for recognition tasks. In the paper, we interpret scene recognition as a region-based image retrieval problem and present a novel approach for scene recognition with an end-to-end trainable Multi-column convolutional neural network (MCNN) architecture. The proposed MCNN utilizes filters with receptive fields of different sizes to have Multi-level and Multi-layer image perception, and consists of three components: front-end, middle-end and back-end. The first seven layers VGG16 are taken as front-end for two-dimensional feature extraction, Inception-A is taken as the middle-end for deeper learning feature representation, and Large-Margin Softmax Loss (L-Softmax) is taken as the back-end for enhancing intra-class compactness and inter-class-separability. Extensive experiments have been conducted to evaluate the performance according to compare our proposed network to existing state-of-the-art methods. Experimental results on three popular datasets demonstrate the robustness and accuracy of our approach. To the best of our knowledge, the presented approach has not been applied for the scene recognition in literature.