论文部分内容阅读
研究超声图像感兴趣区域准确检测问题,针对传统检测算法检测耗时、精度低等缺陷,提出了多神经网络的超声图像检测算法。首先采用离散余弦变换对超声图像感兴趣区域进行特征信息提取,然后分别利用两种神经网络对图像感兴趣区域进行检测,最后利用证据理论对检测结果进行融合,得到最终检测结果。在Matlab环境下进行仿真,仿真结果表明,多神经网络检测算法较传统方法的检测速度更高,定位更加准确。研究超声图像感兴趣区域准确检测问题,针对传统检测算法检测耗时、精度低等缺陷,提出了多神经网络的超声图像检测算法。首先采用离散余弦变换对超声图像感兴趣区域进行特征信息提取,然后分别利用两种神经网络对图像感兴趣区域进行检测,最后利用证据理论对检测结果进行融合,得到最终检测结果。在Matlab环境下进行仿真,仿真结果表明,多神经网络检测算法较传统方法的检测速度更高,定位更加准确。
To study the problem of accurate detection of the region of interest in ultrasound images, aiming at the shortcoming of time-consuming and low-accuracy detection of traditional detection algorithms, an ultrasonic image detection algorithm based on multi-neural networks is proposed. First, discrete cosine transform (DWT) is used to extract the feature information of the region of interest in the ultrasound image. Then, two kinds of neural networks are respectively used to detect the region of interest in the image. Finally, the evidence is fused to obtain the final detection result. Simulation is carried out in the Matlab environment. The simulation results show that the detection method of multi-neural network is more accurate and accurate than the traditional method. To study the problem of accurate detection of the region of interest in ultrasound images, aiming at the shortcoming of time-consuming and low-accuracy detection of traditional detection algorithms, an ultrasonic image detection algorithm based on multi-neural networks is proposed. First, discrete cosine transform (DWT) is used to extract the feature information of the region of interest in the ultrasound image. Then, two kinds of neural networks are respectively used to detect the region of interest in the image. Finally, the evidence is fused to obtain the final detection result. Simulation is carried out in the Matlab environment. The simulation results show that the detection method of multi-neural network is more accurate and accurate than the traditional method.