Uniform linear motion blur often occurs in the camera imaging, which results in image degradation seriously. Therefore, this paper proposes a method to identify the motion blur extent accurately. Since a motion blur angle could be identified accurately by Radon transform and the motion blur direction could be rotated to the horizontal, only the horizontal motion blurred images are needed to be researched. For a motion blurred image without noises, the Fourier transform is used to transform it to frequency domain, the motion blur length is estimated by the BP neural network and the input of BP network is the sum of the amplitudes in the central region of the spectrum. For a blurred image with noises, the bispectrum transform is applied, the motion blur length is estimated by BP neural network and the input of BP network is the maximum value of each column of bispectrum. The simulation experiments show that the proposed method in this paper is correct and efficient. When the SNR is larger or equal to 23 dB in noisy images, the mean error of blur parameter identification by proposed method is below 5%, which is superior to that of conventional schemes.