【摘要】 提出了一种基于傅立叶描述子和神经网络的步态识别方法。对于每个步态序列,通过背景减差检测运动目标的轮廓,使用傅立叶描述子对轮廓线进行描述,获取步态特征。运用人工神经网络分析方法,对步态进行自动识别。结果表明所提的步态识别方法具有较高的识别性能。更多还原

【Abstract】 This paper proposed a gait recognition method based on Fourier Descriptors(FDs) and Artificial Neural Network.For each image sequence,background subtraction algorithm was firstly used to segment the silhouettes of moving object from the background.Then the body contours were processed by Discrete Fourier Transform(DFT) and the gait feathers are expressed by FDs.Artificial Neural Network was finally applied to analysis and recognition automatically.The experimental results demonstrated that the approach had a good recognition performance.更多还原