应用BP神经网络的目标识别效果评估
응용BP신경망락적목표식별효과평고
Performance evaluation in automatic target recognition using BP neural network
  • 万方数据
    计算机工程与应用 계산궤공정여응용
    COMPUTER ENGINEERING AND APPLICATIONS
    2010年 5期 148-150,156 ,共4页

    秦富童%岳丽华%万寿红

    진부동%악려화%만수홍

    目标识别%效果评估%BP神经网络 目標識彆%效果評估%BP神經網絡
    목표식별%효과평고%BP신경망락
    automatic target recognition%performance evaluation%BP neural network
    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.
    근거도상처리목표식별영역적실제응용화수구,학정료목표식별효과평고적지표급기계산방법.침대현유목표식별효과평고방법중존재과다적인공간예,사득평고결과대유교강주관성적문제,제출료일충기우BP신경망락적목표식별효과평고모형,해모형가이감소평고과정중인위인소적영향,제고평고결과적가신도.통과대실측수거진행실험,험증료해모형적평고결과여전가적정성평판구유교고적일치성.
    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.
    원문보기 원문다운로드 사이트로이동
저자의 최근 논문