Abstract：As the most fundamental medical means, venipuncture remains challenging for medical workers. This paper proposed a vein detection and location method for near infrared image. Firstly, an embedded system based on the near-infrared was designed, by which the vein images of both left and right dorsal hand from 43 subjects were captured to finally build a database composed of 325 dorsal hand vein images after preprocessing. Secondly, YOLO Nano algorithm was improved by trimming the network structure to reduce the model size and the output scale to adapt to the size of the detection target. The spatial pyramid pooling structure was introduced to improve the detection accuracy for its strong detail feature description and efficient feature computation. The database was divided into training set and test set in a proportion of 7∶3 and labeled and expanded. After tested on our embedded system, the results showed that the size of the improved YOLO Nano was reduced by 15%, while the average precision (AP) was increased from 91.68% to 93.23% and the detection time reached 529 ms, reduced by 22% compared to YOLO Nano. The improved YOLO Nano outperformed the original YOLO Nano in terms of both detection speed and accuracy, which realized the detection of puncturable veins.
[1] Li Yuhe, Qiao Zhendong, Zhang Shaoqin, et al. A Novel Method for Low-contrast and High-noise Vessel Segmentation and Location in Venipuncture [J]. IEEE Transactions on Medical Imaging, 2017, 36(11): 2216-2227. [2] Zeman, Herbert D. Prototype vein contrast enhancer [J]. Optical Engineering, 2005, 44(8): 086401. [3] Shahzad A, Saad NM, Walter N, et al. An efficient method for subcutaneous veins localization using Near Infrared imaging [C]// 2014 5th International Conference on Intelligent and Advanced Systems (ICIAS). Kuala Lumpur: IEEE, 2014: 1-4. [4] Wang L, Leedham G. Near- and far- infrared imaging for vein pattern biometrics [C]// IEEE International Conference on Video and Signal Based Surveillance. Sydney: IEEE, 2006: 52-52. [5] 郑均辉, 甘泉. NIBLACK 改进算法在手指静脉识别中的应用研究 [J]. 微型电脑应用, 2015, 31(5): 36-38. [6] Besra B, Mohapatra RK. Extraction of segmented vein patterns using repeated line tracking algorithm [C]// 2017 3rd IEEE International Conference on Sensing, Signal Processing and Security (ICSSS). Chennai: IEEE, 2017: 89-92. [7] 胡慧鹏, 高小明, 彭勇. 基于改进谷形检测增强和Canny边缘修正的手指静脉识别方法 [J]. 西南科技大学学报(自然科学版), 2019, 34(2): 92-97. [8] Tang Cong, Feng Yunsong, Yang Xing, et al. The object detection based on deep learning [C]// 4th International Conference on Information Science and Control Engineering (ICISCE). Changsha: IEEE, 2017: 723-728. [9] Redmon J, Divvala S, Girshick R, et al. You only look once: Unified, real-time object detection [C]// IEEE Conference on Com. [10] Redmon J, Farhadi A. YOLO9000: better, faster, stronger [C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu: IEEE, 2017: 6517-6525. [11] Redmon J, Farhadi A. YOLOv3: an incremental improvement [DB/OL]. https://arxiv.org/abs/1804.02767, 2018-04-08/2022-01-20. [12] Wong A, Famuori M, Shafiee MJ, et al. YOLO Nano: a highly compact you only look once convolutional neural network for object detection [DB/OL]. https://arxiv.org/abs/1910.01271, 2019-10-03/2022-01-20. [13] He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Spatial pyramid pooling in deep convolutional networks for visual recognition [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 37(9): 1904-1916. [14] Shahzad A, Walter N, Malik AS, et al. Multispectral venous images analysis for optimum illumination [C]//2013 IEEE International Conference on Image Processing (ICIP). Melbourne: IEEE, 2013: 2383-2387. [15] He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Deep residual learning for image recognition [C]// IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE, 2016: 770-778. [16] Chollet F. Xception: Deep learning with depthwise separable convolutions [C]// 30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu: IEEE, 2017: 1800-1807. [17] Wang Jun, Yang Kai, Pan Zaiyu, et al. Minutiae-based weighting aggregation of deep convolutional features for vein recognition [J]. IEEE Access, 2018, 6: 61640-61650. [18] Kingma D, Ba J. Adam: A method for stochastic optimization [DB/OL]. https://arxiv.org/abs/1412.6980v1, 2014-12-22/2022-01-20. [19] Kanungo T, Mount DM, Netanyahu NS, et al. An efficient k-means clustering algorithm: analysis and implementation [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7): 881-892. [20] Sun XD, Wu PC and Hoi, SCH. Face detection using deep learning: An improved faster RCNN approach [J]. NeuroComputing, 2018, 299: 42-50. [21] Ren S., He K., Girshick R., et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2017, 39(6): 1137-1149. [22] Tian Y., Yang G., Wang Z., et al. Apple detection during different growth stages in orchards using the improved YOLO-V3 model[J]. Computers and electronics in agriculture, 2019, 157: 417-426. [23] 黎洲, 黄妙华. 基于YOLO_v2模型的车辆实时检测 [J]. 中国机械工程, 2018, 29(5): 1869-1874. [24] 王粉花, 黄超, 赵波, 等. 基于YOLO算法的手势识别 [J]. 北京理工大学学报, 2020, 40(8): 873-879. [25] 许虞俊, 李晨. 基于YOLO优化的轻量级目标检测网络 [J]. 计算机科学, 2021, 48(11A): 265-269. [26] 杨玉敏, 廖育荣, 林存宝, 等. 轻量化卷积神经网络目标检测算法综述 [J]. 舰船电子工程, 2021, 41(4): 31-36. [27] 邓天民,方芳,周臻浩. 基于改进空间金字塔池化卷积神经网络的交通标志识别 [J]. 计算机应用, 2020, 40(10): 2872-2880. [28] Kim KJ, Kim PK, Chung YS et al., Multi-Scale Detector for Accurate Vehicle Detection in Traffic Surveillance Data [J]. IEEE Access, 2019, 7: 78311-78319. [29] 张博,张苗辉,陈运. 基于空间金字塔池化和深度卷积神经网络的作物害虫识别 [J]. 农业工程学报, 2019, 35(19): 209-215.
