针对常规最大类间方差法在多阈值图像分割中存在的运算量大、计算时间长、分割精度较低等问题,该文提出一种基于改进的自适应差分演化(JADE)算法的2维Otsu多阈值分割法。首先,为增强初始化种群的质量、提升控制参数的适应性,将混沌映射...针对常规最大类间方差法在多阈值图像分割中存在的运算量大、计算时间长、分割精度较低等问题,该文提出一种基于改进的自适应差分演化(JADE)算法的2维Otsu多阈值分割法。首先,为增强初始化种群的质量、提升控制参数的适应性,将混沌映射机制融入到JADE算法中;进而,通过该改进算法求解2维Otsu多阈值图像的最佳分割阈值;最终,将该算法与差分进化(DE), JADE,改进正弦参数自适应的差分进化(LSHADE-cn Ep Sin)以及增强的适应性微分变换差分进化(EFADE) 4种算法的2维Otsu多阈值图像分割进行比较。实验结果表明,与其它4种算法相比,基于改进JADE算法的2维Otsu多阈值图像分割在分割速度以及精度上均有较明显的改善。展开更多
To solve the problem that the digital image recognition accuracy of concrete structure cracks is not high under the condition of uneven ill umination and complex surface color of concrete structure,this paper has prop...To solve the problem that the digital image recognition accuracy of concrete structure cracks is not high under the condition of uneven ill umination and complex surface color of concrete structure,this paper has proposed a block segmentation method of maximum entropy threshold based on the digital image data obtained by the ACTIS automatic detection system.The steps in this research are as follows:1.The crack digital images of concrete specimens with typical fea-tures were collected by using the Actis system of KURABO Co,Ltd,of Japan in the concrete beam bending test.2.The images are segmented into blocks to dis-tinguish backgrounds of different grayscale.3.The max imum interclass average gray difference method is used to distinguish the sub-blocks and screen out the image blocks that need to be segmented.4.Segmentation is made to the image with 2D max imum entropy threshold segmentation method to obtain the binary image,and the target image can be obtained by screening the connected domain features of the binary image.Results have shown that compared with other algo-rithms,the proposed method can effectively decrease the image over-segmentation and under segmentation rates,highlight the characteristics of the target cracks,solve the problems of excessive difference between the identified length and actual length of cracks caused by background gray level change and uneven ilumnination,and effectively improve the recognition accuracy of bridge concrete cracks.展开更多
随着大数据和硬件的快速发展,细粒度分类任务应运而生,其目的是对粗粒度的大类别进行子类分类。为利用类间细微差异,提出基于RPN(Region Proposal Network)与B-CNN(Bilinear CNN)的细粒度图像分类算法。利用OHEM(Online Hard Example Mi...随着大数据和硬件的快速发展,细粒度分类任务应运而生,其目的是对粗粒度的大类别进行子类分类。为利用类间细微差异,提出基于RPN(Region Proposal Network)与B-CNN(Bilinear CNN)的细粒度图像分类算法。利用OHEM(Online Hard Example Mine)筛选出对识别结果影响大的图像,防止过拟合;将筛选后的图像输入到由soft-nms(Soft Non Maximum Suppression)改进的RPN网络中,得到对象级标注的图像,同时减少假阴性概率;将带有对象级标注信息的图像输入到改进后的B-CNN中,改进后的B-CNN可以融合不同层特征并加强空间联系。实验结果表明,在CUB200-2011和Standford Dogs数据集平均识别精度分别达到85.50%和90.10%。展开更多
文摘针对常规最大类间方差法在多阈值图像分割中存在的运算量大、计算时间长、分割精度较低等问题,该文提出一种基于改进的自适应差分演化(JADE)算法的2维Otsu多阈值分割法。首先,为增强初始化种群的质量、提升控制参数的适应性,将混沌映射机制融入到JADE算法中;进而,通过该改进算法求解2维Otsu多阈值图像的最佳分割阈值;最终,将该算法与差分进化(DE), JADE,改进正弦参数自适应的差分进化(LSHADE-cn Ep Sin)以及增强的适应性微分变换差分进化(EFADE) 4种算法的2维Otsu多阈值图像分割进行比较。实验结果表明,与其它4种算法相比,基于改进JADE算法的2维Otsu多阈值图像分割在分割速度以及精度上均有较明显的改善。
文摘To solve the problem that the digital image recognition accuracy of concrete structure cracks is not high under the condition of uneven ill umination and complex surface color of concrete structure,this paper has proposed a block segmentation method of maximum entropy threshold based on the digital image data obtained by the ACTIS automatic detection system.The steps in this research are as follows:1.The crack digital images of concrete specimens with typical fea-tures were collected by using the Actis system of KURABO Co,Ltd,of Japan in the concrete beam bending test.2.The images are segmented into blocks to dis-tinguish backgrounds of different grayscale.3.The max imum interclass average gray difference method is used to distinguish the sub-blocks and screen out the image blocks that need to be segmented.4.Segmentation is made to the image with 2D max imum entropy threshold segmentation method to obtain the binary image,and the target image can be obtained by screening the connected domain features of the binary image.Results have shown that compared with other algo-rithms,the proposed method can effectively decrease the image over-segmentation and under segmentation rates,highlight the characteristics of the target cracks,solve the problems of excessive difference between the identified length and actual length of cracks caused by background gray level change and uneven ilumnination,and effectively improve the recognition accuracy of bridge concrete cracks.
文摘随着大数据和硬件的快速发展,细粒度分类任务应运而生,其目的是对粗粒度的大类别进行子类分类。为利用类间细微差异,提出基于RPN(Region Proposal Network)与B-CNN(Bilinear CNN)的细粒度图像分类算法。利用OHEM(Online Hard Example Mine)筛选出对识别结果影响大的图像,防止过拟合;将筛选后的图像输入到由soft-nms(Soft Non Maximum Suppression)改进的RPN网络中,得到对象级标注的图像,同时减少假阴性概率;将带有对象级标注信息的图像输入到改进后的B-CNN中,改进后的B-CNN可以融合不同层特征并加强空间联系。实验结果表明,在CUB200-2011和Standford Dogs数据集平均识别精度分别达到85.50%和90.10%。
