Hierarchical palmprint feature extraction and recognition based on multi‐wavelets and complex network

Zhou, Lijian; Zhang, Chen; Wang, Zuowei; Wang, Ying; Lu, Zhe‐Ming

doi:10.1049/iet-ipr.2017.0520

Cited by 14 publications

(10 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This mechanism can enhance the time domain motion in the time template by selecting the appropriate fuzzy membership function µ(i). Figure 4 is a graph of four membership functions, and four membership functions are set to µ1 to µ4, which are defined as equations ( 9) to (12), respectively. Where, the variable i indicates that the four membership functions are set to µ1 to µ4.…”

Section: A Convolutional Neural Network Characteristics Based On Motion Informationmentioning

confidence: 99%

See 1 more Smart Citation

Intelligent Recognition of Medical Motion Image Combining Convolutional Neural Network With Internet of Things

Zhou

Gao

2019

IEEE Access

View full text Add to dashboard Cite

For the small-scale motion in medical motion images, the traditional medical motion image intelligent recognition algorithm has low recognition accuracy, and requires a large amount of calculation statistics. There is no self-learning function, which seriously affects the accuracy and speed of medical motion image recognition. Therefore, in order to improve the accuracy of human body small-scale motion recognition in medical motion images and the computational efficiency of large-scale data sets, an intelligent recognition algorithm based on convolutional neural network for medical motion images is proposed. The algorithm first learns the dense trajectory features and depth features, and then further fuses the dense trajectory features with the deep learning features. Finally, the extreme learning machine is applied to the convolutional neural network, and the fused features are further trained as input information of the convolutional neural network, and the features from the bottom layer to the upper layer can be extracted step by step from the raw data of the pixel level. Simulation experiments show that the algorithm can effectively improve the recognition accuracy of small-scale motion in medical moving images and improve the speed of motion.INDEX TERMS Internet of things, convolutional neural network, medical motion image, intelligent recognition.

show abstract

Section: A Convolutional Neural Network Characteristics Based On Motion Informationmentioning

confidence: 99%

“…The algorithm has higher computational efficiency, but it is not ideal for small-scale motion recognition. Zhou proposed a time-series deep confidence network that can complete online human motion image recognition [12]. This model solves the current deep confidence network model only.…”

Section: Introductionmentioning

confidence: 99%

Intelligent Recognition of Medical Motion Image Combining Convolutional Neural Network With Internet of Things

Zhou

Gao

2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…For strengthening different spatial-frequency characters, different prefilters are constructed for different multi-wavelets. The Chui-Lian (CL) multi-wavelet [41] and the corresponding CL repeated row pre-filter are selected in this paper according to the multi-wavelet decomposition analysis of a palmprint image in [42].…”

Section: Multi-wavelet Analysismentioning

confidence: 99%

“…1c, in which LL, LH, HL, HH components are obtained corresponding to multi-wavelet filters. Refer to the analysis in [42], LL 1 , LL 2 , and LL 3 components are chosen as the features, which are seen as three samples of a class to enlarge the number of samples in this paper. To observe three selected sub-images clearly, their histogram equalised images are shown in Fig.…”

Section: Multi-wavelet Analysismentioning

confidence: 99%

“…Since the time-frequency analysis method can present the spatial-frequency characters of a palmprint image at the same time, the Gabor wavelet [36], curvelet [37], and multi-wavelet [38] analyses have been used to extract the palmprint features. By comparing their performance, the multi-wavelet analysis is selected to augment the samples in this study.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Combining multi‐wavelet and CNN for palmprint recognition against noise and misalignment

Zhou

Guo

Lin

et al. 2019

IET Image Processing

Self Cite

View full text Add to dashboard Cite

Research on Load Feature Extraction Method of Typical Users Based on Deep Learning

Zhu¹,

Wei²,

Wei-yang³

et al. 2021

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

Hierarchical palmprint feature extraction and recognition based on multi‐wavelets and complex network

Cited by 14 publications

References 16 publications

Intelligent Recognition of Medical Motion Image Combining Convolutional Neural Network With Internet of Things

Intelligent Recognition of Medical Motion Image Combining Convolutional Neural Network With Internet of Things

Combining multi‐wavelet and CNN for palmprint recognition against noise and misalignment

Research on Load Feature Extraction Method of Typical Users Based on Deep Learning

Contact Info

Product

Resources

About