Pixel-Level Remote Sensing Image Recognition Based on Bidirectional Word Vectors

Banknote Classification Based on Convolutional Neural Network in Quaternion Wavelet Domain

“…Table 6 shows the processing time of the proposed algorithm on each dataset which are 0.98ms, 2.90ms, 1.51ms, and 1.78ms for Ruble, USD, EUR, CNY respectively. The experimental results show that the elapse time of the proposed algorithm is significantly lower than VGGNet19 [10], PReLU-net [26], BN-inception [27], SAGP [30], ResNet28 [13], DWT [4], and equivalent to Mask [3]. Hence, it is concluded that the proposed algorithm can obtain the best balance between computation complexity and the banknote image recognition rate.…”

“…The change trends of classification rate of the proposed algorithm with the increasing training iterations on different datasets are illustrated in the second experiment. The proposed algorithm was compared with the other six traditional algorithms such as free Mask [3], DWT [4], VGGNet19 [10], PReLU-net [28], BN-inception [29], SAGP [30], and ResNet [13]. For the ResNet network, 128 layers and 4 residual blocks are built in this experiment.…”

“…For CNY dataset, the proposed algorithm achieved 100%, 99.47%, 98.94%, 99.27%, and 98.86%. It has seen from the experimental results that the classification accuracy of proposed algorithm can outperform than the Mask [3], DWT [4], VGG-Net19 [10], PReLU-net [26], BN-inception [27], SAGP [30], and ResNet-28 [13], respectively.…”

“…In order to further improve the effectiveness of the proposed banknote classification algorithm, we conduct experiment on the mixed banknote data set which is composed of 500 samples of Ruble, 800 samples of USD, 600 samples of EUR, and 600 samples of CNY. The obtained average recognition rate of the Mask [3], DWT [4], VGGNet19 [10], PReLU-net [26], BN-inception [27], SAGP [30], ResNet-28 [13], and the proposed algorithm are 85.49%, 89.27%, 93.75%, 95.18%, 96.42%, 97.52%, 98.06%, and 99.28% respectively. It is clear to see that the proposed algorithm can outperform the other banknote classification algorithms.…”

Pedestrian as Points: An Improved Anchor-Free Method for Center-Based Pedestrian Detection

“…Deep neural networks (DNNs) based on the fully convolutional neural network have showed great improvements over systems relying on hand-crafted features [1][2][3] on benchmark tasks. With the rapid progress in DNNs research in recent years, it has dramatically facilitated the development of computer vision, such as object detection [4][5][6], image retrieval [7][8][9], scene recognition [10,11], semantic segmentation [12][13][14], image classification and inpainting [15,16], and so on. In particular, the state-of-theart works in object detection continues to grow, including face recognition [17][18][19], pedestrian detection [20][21][22], vehicle detection [23,24], etc.…”