Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (5): 148-150.DOI: 10.3778/j.issn.1002-8331.2010.05.045

• 图形、图像、模式识别 • Previous Articles     Next Articles

Performance evaluation in automatic target recognition using BP neural network

QIN Fu-tong,YUE Li-hua,WAN Shou-hong   

  1. Department of Computer Science and Technology,University of Science and Technology of China,Hefei 230027,China
  • Received:2008-08-18 Revised:2008-11-10 Online:2010-02-11 Published:2010-02-11
  • Contact: QIN Fu-tong



  1. 中国科学技术大学 计算机科学与技术系,合肥 230027
  • 通讯作者: 秦富童

Abstract: Based on the application and requirement in Automatic Target Recognition(ATR) of image processing,the evaluation indexes and their calculation methods are designed.Aiming at the problem that there are so many man-made factors in existing methods that make the results of evaluation subjective,a performance evaluation model which is based on BP neural network is established.This model can reduce the effect of man-made factors and enhance the reliability of evaluation results.Through carrying out simulation and analysis by test data,the results of this model and the judgments of experts are in much high consistency.

Key words: automatic target recognition, performance evaluation, BP neural network

摘要: 根据图像处理目标识别领域的实际应用和需求,确定了目标识别效果评估的指标及其计算方法。针对现有目标识别效果评估方法中存在过多的人工干预,使得评估结果带有较强主观性的问题,提出了一种基于BP神经网络的目标识别效果评估模型,该模型可以减少评估过程中人为因素的影响,提高评估结果的可信度。通过对实测数据进行实验,验证了该模型的评估结果与专家的定性评判具有较高的一致性。

关键词: 目标识别, 效果评估, BP神经网络

CLC Number: