Novel Rifle Number Recognition Based on Improved YOLO in Military Environment  

作　　者：Hyun Kwon Sanghyun Lee 

机构地区：[1]Department of Artificial Intelligence and Data Science,Korea Military Academy,Seoul,Korea [2]Graduate School of Information Security,Korea Advanced Institute of Science and Technology,Daejeon,Korea

出　　处：《Computers, Materials & Continua》2024年第1期249-263,共15页计算机、材料和连续体（英文）

基　　金：supported by the Future Strategy and Technology Research Institute(RN:23-AI-04)of Korea Military Academy;the Hwarang-Dae Research Institute(RN:2023B1015)of Korea Military Academy,and Basic Science Research Program through the National Research Foundation of Korea(NRF);funded by the Ministry of Education(2021R1I1A1A01040308).

摘　　要：Deep neural networks perform well in image recognition,object recognition,pattern analysis,and speech recog-nition.In military applications,deep neural networks can detect equipment and recognize objects.In military equipment,it is necessary to detect and recognize rifle management,which is an important piece of equipment,using deep neural networks.There have been no previous studies on the detection of real rifle numbers using real rifle image datasets.In this study,we propose a method for detecting and recognizing rifle numbers when rifle image data are insufficient.The proposed method was designed to improve the recognition rate of a specific dataset using data fusion and transfer learningmethods.In the proposed method,real rifle images and existing digit images are fusedas trainingdata,andthe final layer is transferredto theYolov5 algorithmmodel.The detectionand recognition performance of rifle numbers was improved and analyzed using rifle image and numerical datasets.We used actual rifle image data(K-2 rifle)and numeric image datasets,as an experimental environment.TensorFlow was used as the machine learning library.Experimental results show that the proposed method maintains 84.42% accuracy,73.54% precision,81.81% recall,and 77.46% F1-score in detecting and recognizing rifle numbers.The proposed method is effective in detecting rifle numbers.

关 键 词：Machine learning deep neural network rifle number recognition DETECTION 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]