6 May 2020 in IET Cyber-Physical Systems: Theory & Applications
On the basis of the problem that the image background is simple and the traditional shooting equipment of fruit flies is too high, this study improved the convolutional neural network model. First, the authors changed Softmax classifier to support vector machine (SVM). Moreover, then used convolution layers for extracting features of fruit fly images. Finally, they fed features into SVM for training. Experiments show that the model has been classifying the Bactrocera dorsalis Hendel, Bactrocera cucurbitae , Bactrocera tau and Bactrocera scutellata with accuracy over 92.04%, accordingly making the effective classification of the complex background fruit fly images possible. Moreover, it also provides a good practical application prospect.
23 March 2020 in IEEE Access
Cyber-Physical-Social Systems (CPSS) integrates cyber, physical and social spaces together, which makes our lives more convenient and intelligent by providing personalized service. In this paper, we will provide CPSS service for fine-grained recognition. Fine-grained visual recognition is a hot but challenging research in computer vision that aims to recognize object subcategories. The reason why it is challenging is that it extremely depends on the subtle discriminative features of local parts. Recently, some bilinear feature based methods were proposed, and the experimental results show state-of-the-art performance. However, most of them neglect the spatial relationships of part-region feature among multiple layers. In this paper, a novel approach of Self-layer and Cross-layer Bilinear Aggregation(SCBA) is proposed for fine-grained recognition. Firstly, a self-layer bilinear feature fusion module is proposed to model the spatial relationship of feature at the same layer. Secondly, we propose a cross-layer bilinear feature fusion module to capture the inter-layer interreaction of information to boost the ability of feature representation. In summary, the method we proposed not only can learn the correlations among different layers but the same layer, which makes it efficient and the experimental results show that it achieves state-of-the-art accuracy on three common fine-grained image datasets.