School of Microelectronics, Xidian University, Xi'an 710071, China.
Sensors (Basel). 2020 Oct 15;20(20):5822. doi: 10.3390/s20205822.
Convolutional neural networks (CNNs) can automatically learn features from pressure information, and some studies have applied CNNs for tactile shape recognition. However, the limited density of the sensor and its flexibility requirement lead the obtained tactile images to have a low-resolution and blurred. To address this issue, we propose a bilinear feature and multi-layer fused convolutional neural network (BMF-CNN). The bilinear calculation of the feature improves the feature extraction capability of the network. Meanwhile, the multi-layer fusion strategy exploits the complementarity of different layers to enhance the feature utilization efficiency. To validate the proposed method, a 26 class letter-shape tactile image dataset with complex edges was constructed. The BMF-CNN model achieved a 98.64% average accuracy of tactile shape. The results show that BMF-CNN can deal with tactile shapes more effectively than traditional CNN and artificial feature methods.
卷积神经网络 (CNN) 可以自动从压力信息中学习特征，一些研究已经将 CNN 应用于触觉形状识别。然而，传感器的有限密度及其灵活性要求导致获得的触觉图像具有低分辨率和模糊。为了解决这个问题，我们提出了双线性特征和多层融合卷积神经网络 (BMF-CNN)。特征的双线性计算提高了网络的特征提取能力。同时，多层融合策略利用不同层之间的互补性来提高特征利用效率。为了验证所提出的方法，构建了一个具有复杂边缘的 26 类字母形状触觉图像数据集。BMF-CNN 模型实现了 98.64%的平均触觉形状准确率。结果表明，与传统的 CNN 和人工特征方法相比，BMF-CNN 可以更有效地处理触觉形状。
