A deep learning based bank card detection and recognition method in complex scenes

Lin, Hanyang; Zhan, Yongzhao; Liu, Shiqin; Xiao, Ke; Chen, Yuzhong

doi:10.1007/s10489-021-03119-2

Cited by 3 publications

(1 citation statement)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specially, deep learning has excelled and captured the attention of all over the world in recent years in the field of analysis of medical images, particularly in utilizing convolutional neural network (CNN) to construct end-to-end networks for image analysis [16]. CNN, which is one of the most significant networks in deep learning, can be able to construct multi-layered convolutional network for the purpose of learning and extracting features [17][18][19].…”

Section: Introductionmentioning

confidence: 99%

A lightweight white blood cells detection network based on CenterNet and feature fusion modules

Wu,

Zou,

Zuo

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

White blood cells detection is significant to the diagnosis of many diseases. However, the detection accuracy can be influenced by the significant differences in color, size and morphology of white blood cells in the images. In this paper, an improved CenterNet with smaller model size, fewer parameters, and lower computational complexity is proposed for the white blood cells accurate detection. Firstly, the lightweight backbone GhostNetv2 is selected to reduce the model size, parameters and computational complexity of the network. Then, a feature pyramid network with the ECA attention mechanism and the multi-scale feature extraction modules is constructed to enhance the capability of feature extraction and focus more on white blood cells. Finally, the heatmap loss function is modified by proposing an improved MSE loss function to enhance the fitting ability between the predicted values and the ground truth of the heatmap. Experimental results show that the model size of the proposed lightweight CenterNet is only 19.9MB, and the mAP.5 is 97.36%. The model size is reduced by 84% while the mAP.5 and FPS are increased by 0.7% and 10.4 compared to the original CenterNet. Moreover, the detection accuracy of the proposed lightweight CenterNet is comparable to the existing mainstream networks and its detection performance on different datasets is good, while the model size, parameters and computational complexity of the network is significantly reduced, and can be used for white blood cells detection effectively.

show abstract