中国科学院机构知识库网格系统: 检索

浏览/检索结果: 共9条，第1-9条

帮助

条数/页：排序方式：
	Effective piecewise planar modeling based on sparse 3D points and convolutional neural network 期刊论文 OAI收割 NEUROCOMPUTING, 2020, 卷号: 378, 页码: 350-363 作者: Wang, Wei; Gao, Wei; Hu, Zhanyi \| 收藏 \| 浏览/下载：35/0 \| 提交时间：2020/03/30 Urban scene Piecewise planar stereo Markov Random Field Image over-segmentation Convolutional neural network
	RTSNet: Real-Time Semantic Segmentation Network for Outdoor Scenes 会议论文 OAI收割 Suzhou, China, July 29 - August 2, 2019 作者: Ma, Mingyu; Zou FS(邹风山); Xu F(徐方); Song JL(宋吉来) \| 收藏 \| 浏览/下载：38/0 \| 提交时间：2020/05/24 semantic segmentation real-time outdoor scenes RTSNet mean intersection-over-union
	An over-segmentation method for single-touching Chinese handwriting with learning-based filtering 期刊论文 OAI收割 INTERNATIONAL JOURNAL ON DOCUMENT ANALYSIS AND RECOGNITION, 2014, 卷号: 17, 期号: 1, 页码: 91-104 作者: 收藏 \| 浏览/下载：39/0 \| 提交时间：2015/08/12 Single-touching strings Chinese handwriting Over-segmentation Learning-based filtering Geometric features
	脱机中文手写字符串切分方法研究学位论文 OAI收割工学博士, 中国科学院自动化研究所: 中国科学院大学, 2013 作者: 许亮收藏 \| 浏览/下载：58/0 \| 提交时间：2015/09/02 字符切分粘连手写字符串脱机手写中文文本识别过切分切分线段过滤 character segmentation touching characters offline handwritten text recognition over-segmentation separating line filtering
	An approach for real-time recognition of online Chinese handwritten sentences 期刊论文 OAI收割 PATTERN RECOGNITION, 2012, 卷号: 45, 期号: 10, 页码: 3661-3675 作者: Wang, Da-Han; Liu, Cheng-Lin; Zhou, Xiang-Dong 收藏 \| 浏览/下载：23/0 \| 提交时间：2015/08/12 Online Chinese handwritten sentence recognition Real-time recognition Dynamic text line segmentation Dynamic over-segmentation Dynamic candidate lattice Path search
	Multi-focus image fusion algorithm based on adaptive PCNN and wavelet transform (EI CONFERENCE) 会议论文 OAI收割 International Symposium on Photoelectronic Detection and Imaging 2011: Advances in Imaging Detectors and Applications, May 24, 2011 - May 26, 2011, Beijing, China Wu Z.-G.; Wang M.-J.; Han G.-L. 收藏 \| 浏览/下载：75/0 \| 提交时间：2013/03/25 Being an efficient method of information fusion image fusion has been used in many fields such as machine vision medical diagnosis military applications and remote sensing.In this paper Pulse Coupled Neural Network (PCNN) is introduced in this research field for its interesting properties in image processing including segmentation target recognition et al. and a novel algorithm based on PCNN and Wavelet Transform for Multi-focus image fusion is proposed. First the two original images are decomposed by wavelet transform. Then based on the PCNN a fusion rule in the Wavelet domain is given. This algorithm uses the wavelet coefficient in each frequency domain as the linking strength so that its value can be chosen adaptively. Wavelet coefficients map to the range of image gray-scale. The output threshold function attenuates to minimum gray over time. Then all pixels of image get the ignition. So the output of PCNN in each iteration time is ignition wavelet coefficients of threshold strength in different time. At this moment the sequences of ignition of wavelet coefficients represent ignition timing of each neuron. The ignition timing of PCNN in each neuron is mapped to corresponding image gray-scale range which is a picture of ignition timing mapping. Then it can judge the targets in the neuron are obvious features or not obvious. The fusion coefficients are decided by the compare-selection operator with the firing time gradient maps and the fusion image is reconstructed by wavelet inverse transform. Furthermore by this algorithm the threshold adjusting constant is estimated by appointed iteration number. Furthermore In order to sufficient reflect order of the firing time the threshold adjusting constant is estimated by appointed iteration number. So after the iteration achieved each of the wavelet coefficient is activated. In order to verify the effectiveness of proposed rules the experiments upon Multi-focus image are done. Moreover comparative results of evaluating fusion quality are listed. The experimental results show that the method can effectively enhance the edge details and improve the spatial resolution of the image. 2011 SPIE.
	TurboPixel Segmentation Using Eigen-Images 期刊论文 OAI收割 IEEE TRANSACTIONS ON IMAGE PROCESSING, 2010, 卷号: 19, 期号: 11, 页码: 3024-3034 作者: Xiang, Shiming; Pan, Chunhong; Nie, Feiping; Zhang, Changshui 收藏 \| 浏览/下载：39/0 \| 提交时间：2015/08/12 Eigen-images image pyramid over-segmentation superpixel TurboPixel (TP)
	基于统计部首模型的联机手写汉字识别学位论文 OAI收割工学博士, 中国科学院自动化研究所: 中国科学院研究生院, 2010 作者: 马龙龙收藏 \| 浏览/下载：61/0 \| 提交时间：2015/09/02 联机手写汉字识别层次结构部首过分割部首识别路径搜索特殊部首检测 on-line handwritten chinese character recognition hierarchical structure radical over-segmentation radical recognition path search special radical detection
	A new segmentation method of CR images based on discrete wavelet transform and mathematics morphology (EI CONFERENCE) 会议论文 OAI收割 ICO20: Optical Information Processing, August 21, 2005 - August 26, 2005, Changchun, China 作者: Li Z.; Li Z. 收藏 \| 浏览/下载：64/0 \| 提交时间：2013/03/25 In this paper we propose a segmentation method of CR(computed radiography) images with being rid of under-segmentation and over-segmentation. An under-segmentation occurs when pixels belonging to different objects are grouped into a single region. Such errors are the most dangerous because they can invalidate the whole segmentation process. The phenomenon always takes place when we segment CR images because of the principle of CR. In order to depressed under-segmentation we enhance the CR images using DWT (discrete wavelet transform) to get more detail of CR image features. As we enhance the CR image the over-segmentation maybe occurs. Compared with under-segmentation the over-segmentation occurs when a single objects is subdivided by segmentation into several region. For the purpose of preventing from the over-segmentation we present a scheme for enhanced CR images based on watershed algorithm that solves over-segmentation problem. We use marker-based watershed algorithm. Together with gradient image and marker image watershed segmentation can make sure to partition CR image into meaningful object and avoid further segmentation of homogeneous regions. The result of the proposed algorithm are compared with those of other standard methods. Experiments have shown a better result and indeed solved under-segmentation and over-segmentation problems.