Real-time hand gesture recognition technology significantly improves the user's experience for virtual reality/augmented reality(VR/AR) applications, which relies on the identification of the orientation of the ha...Real-time hand gesture recognition technology significantly improves the user's experience for virtual reality/augmented reality(VR/AR) applications, which relies on the identification of the orientation of the hand in captured images or videos. A new three-stage pipeline approach for fast and accurate hand segmentation for the hand from a single depth image is proposed. Firstly, a depth frame is segmented into several regions by histogrambased threshold selection algorithm and by tracing the exterior boundaries of objects after thresholding. Secondly, each segmentation proposal is evaluated by a three-layers shallow convolutional neural network(CNN) to determine whether or not the boundary is associated with the hand. Finally, all hand components are merged as the hand segmentation result. Compared with algorithms based on random decision forest(RDF), the experimental results demonstrate that the approach achieves better performance with high-accuracy(88.34% mean intersection over union, mIoU) and a shorter processing time(≤8 ms).展开更多
The image segmentation difficulties of small objects which are much smaller than their background often occur in target detection and recognition. The existing threshold segmentation methods almost fail under the circ...The image segmentation difficulties of small objects which are much smaller than their background often occur in target detection and recognition. The existing threshold segmentation methods almost fail under the circumstances. Thus, a threshold selection method is proposed on the basis of area difference between background and object and intra-class variance. The threshold selection formulae based on one-dimensional (1-D) histogram, two-dimensional (2-D) histogram vertical segmentation and 2-D histogram oblique segmentation are given. A fast recursive algorithm of threshold selection in 2-D histogram oblique segmentation is derived. The segmented images and processing time of the proposed method are given in experiments. It is compared with some fast algorithms, such as Otsu, maximum entropy and Fisher threshold selection methods. The experimental results show that the proposed method can effectively segment the small object images and has better anti-noise property.展开更多
开放集识别(Open Set Recognition,OSR)的主要目的是识别未标记数据中的新类样本,同时对已见类样本进行正确分类.现有的大多数识别方法对未标记数据的评估和伪标记信息的利用不足.本文提出一种基于主动学习的开放集图像识别方法(Open Se...开放集识别(Open Set Recognition,OSR)的主要目的是识别未标记数据中的新类样本,同时对已见类样本进行正确分类.现有的大多数识别方法对未标记数据的评估和伪标记信息的利用不足.本文提出一种基于主动学习的开放集图像识别方法(Open Set Image Recognition Method Based on Active Learning,AC-OSIR),充分利用未标记数据提升开放集识别性能.通过引入已见类别的语义知识,构建语义知识和图像特征的映射关系.对于未标记数据,利用阈值选择策略区分开放集样本和已见类样本,通过主动学习模型迭代地识别高置信度开放集样本和已见类样本,并将高置信度已见类样本添加到标记数据集中.本文在图像分类数据集CIFAR-10、TIN和LSUN,以及两个合成数据集的实验结果表明了基于主动学习的开放集图像识别方法的有效性.展开更多
文摘Real-time hand gesture recognition technology significantly improves the user's experience for virtual reality/augmented reality(VR/AR) applications, which relies on the identification of the orientation of the hand in captured images or videos. A new three-stage pipeline approach for fast and accurate hand segmentation for the hand from a single depth image is proposed. Firstly, a depth frame is segmented into several regions by histogrambased threshold selection algorithm and by tracing the exterior boundaries of objects after thresholding. Secondly, each segmentation proposal is evaluated by a three-layers shallow convolutional neural network(CNN) to determine whether or not the boundary is associated with the hand. Finally, all hand components are merged as the hand segmentation result. Compared with algorithms based on random decision forest(RDF), the experimental results demonstrate that the approach achieves better performance with high-accuracy(88.34% mean intersection over union, mIoU) and a shorter processing time(≤8 ms).
基金Sponsored by The National Natural Science Foundation of China(60872065)Science and Technology on Electro-optic Control Laboratory and Aviation Science Foundation(20105152026)State Key Laboratory Open Fund of Novel Software Technology,Nanjing University(KFKT2010B17)
文摘The image segmentation difficulties of small objects which are much smaller than their background often occur in target detection and recognition. The existing threshold segmentation methods almost fail under the circumstances. Thus, a threshold selection method is proposed on the basis of area difference between background and object and intra-class variance. The threshold selection formulae based on one-dimensional (1-D) histogram, two-dimensional (2-D) histogram vertical segmentation and 2-D histogram oblique segmentation are given. A fast recursive algorithm of threshold selection in 2-D histogram oblique segmentation is derived. The segmented images and processing time of the proposed method are given in experiments. It is compared with some fast algorithms, such as Otsu, maximum entropy and Fisher threshold selection methods. The experimental results show that the proposed method can effectively segment the small object images and has better anti-noise property.
文摘开放集识别(Open Set Recognition,OSR)的主要目的是识别未标记数据中的新类样本,同时对已见类样本进行正确分类.现有的大多数识别方法对未标记数据的评估和伪标记信息的利用不足.本文提出一种基于主动学习的开放集图像识别方法(Open Set Image Recognition Method Based on Active Learning,AC-OSIR),充分利用未标记数据提升开放集识别性能.通过引入已见类别的语义知识,构建语义知识和图像特征的映射关系.对于未标记数据,利用阈值选择策略区分开放集样本和已见类样本,通过主动学习模型迭代地识别高置信度开放集样本和已见类样本,并将高置信度已见类样本添加到标记数据集中.本文在图像分类数据集CIFAR-10、TIN和LSUN,以及两个合成数据集的实验结果表明了基于主动学习的开放集图像识别方法的有效性.
