牧草自动识别是对普通数码相机获取的牧草数字图像进行预处理、特征提取与特征匹配等环节处理,达到利用计算机实现牧草分类的目的。牧草自动识别具有成本低,易于采集,准确性高等优点,是实现草地数字化的基础。图像预处理是保证识别精度...牧草自动识别是对普通数码相机获取的牧草数字图像进行预处理、特征提取与特征匹配等环节处理,达到利用计算机实现牧草分类的目的。牧草自动识别具有成本低,易于采集,准确性高等优点,是实现草地数字化的基础。图像预处理是保证识别精度的关键环节,本文以典型草原优质牧草禾本科种子为研究对象,研究图像的预处理方法,获取感兴趣区域(Region of Interest,ROI)。主要步骤包括:首先对图像进行去噪、灰度化、二值化处理,然后对二值图像进行形态学腐蚀、膨胀运算,确定种子边缘,最后根据种子主体位置建立坐标系,分割原始图像,获取ROI。为验证预处理方法的有效性,本文利用主成分分析(Principal Components Analysis,PCA)提取特征,对20个样本的禾本科牧草种子1000幅图像进行识别,平均识别率达到94.6%。展开更多
基于Contourlet变换与最小二乘支持向量机(least squares support vector machine,LSSVM),提出了一种玉米种子高精度识别算法。该算法首先对玉米种子图像进行多层Contourlet分解,结合指数函数和反正弦函数,提出了一种新型的阈值函数模...基于Contourlet变换与最小二乘支持向量机(least squares support vector machine,LSSVM),提出了一种玉米种子高精度识别算法。该算法首先对玉米种子图像进行多层Contourlet分解,结合指数函数和反正弦函数,提出了一种新型的阈值函数模型对高频分解系数进行去噪处理;其次,将低频分解系数与去噪后的高频分解系数进行重构,得到去噪后的玉米种子图像;最后采用LSSVM对去噪后的玉米种子图像进行识别,采用径向基函数模型作为LSSVM核函数模型。试验结果表明,对去噪后的图像进行LSSVM识别的精度优于直接对图像进行LSSVM、SVM识别的精度。展开更多
This paper is focused on the problem of the ability of seeding particles to follow the flow field. One of the most important factors influencing the resultant accuracy of the measurement is using the proper seeding pa...This paper is focused on the problem of the ability of seeding particles to follow the flow field. One of the most important factors influencing the resultant accuracy of the measurement is using the proper seeding particles for feeding the flow when measuring by PIV （Particle Image Velocimetry） method. The aim of the paper is to provide comprehensible instruction for choosing the proper type of seeding particles with regard to the flow characteristics and required measurement accuracy. The paper presents two methods with the help of which it is possible to determine the seeding particles＇ ability to follow the flow field. The first method is based on the direct calculation of the phase lag and amplitude ratio between the particle and the fluid. The calculation is based on solution of the BBO （Basset Boussinesq Oseen） equation for spherical particle. The other method results from the calculation of the particle time response, which defines the maximum frequency of disturbances, which are to be followed by the particle. In the conclusion, the method of choosing the seeding particles is proposed, depending on the required measurement accuracy.展开更多
Segmenting blurred and conglutinated bubbles in a flotation image is done using a new segmentation method based on Seed Region and Boundary Growing（SRBG）.Bright pixels located on bubble tops were extracted as the se...Segmenting blurred and conglutinated bubbles in a flotation image is done using a new segmentation method based on Seed Region and Boundary Growing（SRBG）.Bright pixels located on bubble tops were extracted as the seed regions.Seed boundaries are divided into four curves：left-top,right-top,right-bottom, and left-bottom.Bubbles are segmented from the seed boundary by moving these curves to the bubble boundaries along the corresponding directions.The SRBG method can remove noisy areas and it avoids over- and under-segmentation problems.Each bubble is segmented separately rather than segmenting the entire flotation image.The segmentation results from the SRBG method are more accurate than those from the Watershed algorithm.展开更多
文摘牧草自动识别是对普通数码相机获取的牧草数字图像进行预处理、特征提取与特征匹配等环节处理,达到利用计算机实现牧草分类的目的。牧草自动识别具有成本低,易于采集,准确性高等优点,是实现草地数字化的基础。图像预处理是保证识别精度的关键环节,本文以典型草原优质牧草禾本科种子为研究对象,研究图像的预处理方法,获取感兴趣区域(Region of Interest,ROI)。主要步骤包括:首先对图像进行去噪、灰度化、二值化处理,然后对二值图像进行形态学腐蚀、膨胀运算,确定种子边缘,最后根据种子主体位置建立坐标系,分割原始图像,获取ROI。为验证预处理方法的有效性,本文利用主成分分析(Principal Components Analysis,PCA)提取特征,对20个样本的禾本科牧草种子1000幅图像进行识别,平均识别率达到94.6%。
文摘基于Contourlet变换与最小二乘支持向量机(least squares support vector machine,LSSVM),提出了一种玉米种子高精度识别算法。该算法首先对玉米种子图像进行多层Contourlet分解,结合指数函数和反正弦函数,提出了一种新型的阈值函数模型对高频分解系数进行去噪处理;其次,将低频分解系数与去噪后的高频分解系数进行重构,得到去噪后的玉米种子图像;最后采用LSSVM对去噪后的玉米种子图像进行识别,采用径向基函数模型作为LSSVM核函数模型。试验结果表明,对去噪后的图像进行LSSVM识别的精度优于直接对图像进行LSSVM、SVM识别的精度。
文摘This paper is focused on the problem of the ability of seeding particles to follow the flow field. One of the most important factors influencing the resultant accuracy of the measurement is using the proper seeding particles for feeding the flow when measuring by PIV （Particle Image Velocimetry） method. The aim of the paper is to provide comprehensible instruction for choosing the proper type of seeding particles with regard to the flow characteristics and required measurement accuracy. The paper presents two methods with the help of which it is possible to determine the seeding particles＇ ability to follow the flow field. The first method is based on the direct calculation of the phase lag and amplitude ratio between the particle and the fluid. The calculation is based on solution of the BBO （Basset Boussinesq Oseen） equation for spherical particle. The other method results from the calculation of the particle time response, which defines the maximum frequency of disturbances, which are to be followed by the particle. In the conclusion, the method of choosing the seeding particles is proposed, depending on the required measurement accuracy.
基金supported in part by the National Science & Technology Support Plan of China(No.2009BAB48B02)
文摘Segmenting blurred and conglutinated bubbles in a flotation image is done using a new segmentation method based on Seed Region and Boundary Growing（SRBG）.Bright pixels located on bubble tops were extracted as the seed regions.Seed boundaries are divided into four curves：left-top,right-top,right-bottom, and left-bottom.Bubbles are segmented from the seed boundary by moving these curves to the bubble boundaries along the corresponding directions.The SRBG method can remove noisy areas and it avoids over- and under-segmentation problems.Each bubble is segmented separately rather than segmenting the entire flotation image.The segmentation results from the SRBG method are more accurate than those from the Watershed algorithm.
