针对复杂工况环境下异常条形码的识别问题,提出了一种新的基于特征提取与BP神经网络协同作用的异常条形码判别方法。首先,为有效对条形码图像特征进行表征,从图像histogram of oriented gradient(HOG)特征、曲线特征、纹理粗糙度、纹理...针对复杂工况环境下异常条形码的识别问题,提出了一种新的基于特征提取与BP神经网络协同作用的异常条形码判别方法。首先,为有效对条形码图像特征进行表征,从图像histogram of oriented gradient(HOG)特征、曲线特征、纹理粗糙度、纹理灰度特征着手,建立条形码识别的特征库;在此基础上,建立以LM-BP神经网络为核心的辨识框架对条形码特征进行训练和辨识;最后,通过模拟国网新疆电力有限公司电力科学研究院计量生产自动化系统现场的条形码图像验证了算法的合理性。实验结果表明:基于特征提取与LM-BP神经网络协同辨识的方法能有效对条形码状态进行识别,其识别精度可达88. 29%。展开更多
Based on the method of probability and statistics, the authors analyzed the physical and mechanical properties of loess in specified area, and discussed its main indexes, the coefficient of variation, and the corre- l...Based on the method of probability and statistics, the authors analyzed the physical and mechanical properties of loess in specified area, and discussed its main indexes, the coefficient of variation, and the corre- lation among the physical and mechanical indexes. Regression equations are built among those indexes, the re- suits show that the variability of mechanical indexes is higher than that of the physical indexes, and the physical indexes have better correlation than the relation between physical and mechanical indexes. The conclusions of this study would contribute to further research about loess in western Liaoning.展开更多
文摘针对复杂工况环境下异常条形码的识别问题,提出了一种新的基于特征提取与BP神经网络协同作用的异常条形码判别方法。首先,为有效对条形码图像特征进行表征,从图像histogram of oriented gradient(HOG)特征、曲线特征、纹理粗糙度、纹理灰度特征着手,建立条形码识别的特征库;在此基础上,建立以LM-BP神经网络为核心的辨识框架对条形码特征进行训练和辨识;最后,通过模拟国网新疆电力有限公司电力科学研究院计量生产自动化系统现场的条形码图像验证了算法的合理性。实验结果表明:基于特征提取与LM-BP神经网络协同辨识的方法能有效对条形码状态进行识别,其识别精度可达88. 29%。
文摘Based on the method of probability and statistics, the authors analyzed the physical and mechanical properties of loess in specified area, and discussed its main indexes, the coefficient of variation, and the corre- lation among the physical and mechanical indexes. Regression equations are built among those indexes, the re- suits show that the variability of mechanical indexes is higher than that of the physical indexes, and the physical indexes have better correlation than the relation between physical and mechanical indexes. The conclusions of this study would contribute to further research about loess in western Liaoning.
