检索结果-内蒙古大学图书馆

2nd International Conference on Pattern Recognition and Image Analysis IPRIA

作者： Soltani-Sarvestani, M. A. Zohreh, Azimifar Shiraz Univ Dept Comp Sci & Engn Shiraz Iran

ISBN: (纸本)9781479984459

Color can be a useful feature in many fields of AI that are based on machine vision. Unfortunately, many existing vision system do not use color to its full extent, largely because color-based recognition in outdoor scene is complicated, and existing color machine vision techniques have not been shown to be effective in realistic outdoor images. The problem of color recognition in outdoor is considerable when we are faced with glossy materials like automobiles. There is no powerful method to recognize color of a batch of pixels. Thus, for the first time, we propose a novel method to detect dominant color of a group of pixels. This method has many applications in object color detection especially for glossy objects.

关键词： color Classification sparse coding Bag of colors

来源：评论

学校读者我要写书评

暂无评论

Hierarchical sparse coding With Geometric Prior For Visual Geo-location

Hierarchical Sparse Coding With Geometric Prior For Visual G...

引用

IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Gopalan, Radmraman AT&T Labs Res Dept Video & Multimedia Technol Res Middletown NJ 07748 USA

ISBN: (纸本)9781467369640

We address the problem of estimating location information of an image using principles from automated representation learning. We pursue a hierarchical sparse coding approach that learns features useful in discriminating images across locations, by initializing it with a geometric prior corresponding to transformations between image appearance space and their corresponding location grouping space using the notion, of parallel transport on manifolds. We then extend this approach to account for the availability, of heterogeneous data modalities such as geo-tags and videos pertaining to different locations, and also study a relatively under-addressed problem of transferring knowledge available from certain, locations to infer the grouping of data from novel locations. We evaluate our approach on several standard datasets such as im2gps, San Francisco and MediaEval 2010, and obtain state-of-the-art results.

关键词： sparse coding initialization POSITION INFORMATION images Manifolds Imagery (Psychotherapy) Hierarchical

来源：评论

学校读者我要写书评

暂无评论

Automatic Brain Tumor Segmentation from MR Images via a Multimodal sparse coding Based Probabilistic Model 5

Automatic Brain Tumor Segmentation from MR Images via a Mult...

引用

2015 International Workshop on Pattern Recognition in NeuroImaging PRNI 2015

作者： Li, Yuhong Dou, Qi Yu, Jinze Jia, Fucang Qin, Jing Heng, Pheng-Ann Chinese Acad Sci Shenzhen Inst Adv Technol Shenzhen Peoples R China Chinese Univ Hong Kong Dept Comp Sci & Engn Hong Kong Hong Kong Peoples R China Shenzhen Univ Sch Med Natl Reg Key Technol Engn Lab Med Ultrasound Shenzhen Peoples R China

ISBN: (纸本)9781467371452

Accurate segmentation of brain tumor from MR image is crucial for the diagnosis and treatment of brain cancer. We propose a novel automated brain tumor segmentation method based on a probabilistic model combining sparse coding and Markov random field (MRF). We formulate the brain tumor segmentation task as a pixel -wise labeling problem with regard to three classes: tumor, edema and healthy tissue. For each class, dictionary learning is performed independently on multi -modality gray scale patches. sparse representation is then extracted based on a joint dictionary which is constructed by combing the three independent dictionaries. Finally, we build the probabilistic model aiming to estimate maximum a posterior (MAP) probability by introducing the sparse representation into likelihood probability and prior probability using the Markov random field (MRF) assumption. Compared with traditional methods, which employed hand-crafted low level features to construct the probabilistic model, our model can better represent the characteristics of a pixel and its relation with neighbors based on the sparse coefficients obtained from the learned dictionary. We validated our method on the MICAAI 2012 BRATS challenge brain MRI dataset and achieved comparable or better results compared with state-ofthe-art methods.

关键词： brain tumor segmentation multi-modality sparse coding probabilistic model maximum a posterior

来源：评论

学校读者我要写书评

暂无评论

A Novel Speech Emotion Recognition Method via Transfer PCA and sparse coding 10th

A Novel Speech Emotion Recognition Method via Transfer PCA a...

引用

10th Chinese Conference on Biometric Recognition (CCBR)

作者： Song, Peng Zheng, Wenming Liu, Jingjing Li, Jing Zhang, Xinran Yantai Univ Sch Comp & Control Engn Yantai 264005 Peoples R China Southeast Univ Minist Educ Key Lab Child Dev & Learning Sci Nanjing 210096 Jiangsu Peoples R China Southeast Univ Sch Informat Sci & Engn Nanjing 210096 Jiangsu Peoples R China

ISBN: (纸本)9783319254173;9783319254166

In practice, the training data and testing data are often from different datasets, which have an adverse impact on speech emotion recognition rates. To tackle this problem, in this paper, a novel transfer principal component analysis (TPCA) and sparse coding based speech emotion recognition method is proposed. The TPCA approach is first presented for feature dimension reduction, then the sparse coding algorithm is introduced to learn the robust feature representations for both labeled source and unlabeled target corpora. To evaluate the performance of our proposed method, the experiments are conducted on two public datasets. Experimental results demonstrate that our proposed approach significantly outperforms the automatic recognition method, and obtains better performance than the state-of-the-art method.

关键词： Dimension reduction sparse coding Transfer learning Speech emotion recognition

来源：评论

学校读者我要写书评

暂无评论

Action recognition with approximate sparse coding

Action recognition with approximate sparse coding

引用

IEEE International Conference on Image Processing, ICIP 2015

作者： Wang, Yu Kato, Jien Graduate School of Information Science Nagoya University Japan

ISBN: (纸本)9781479983391

In this paper, we present a novel feature encoding approach called Approximate sparse coding (ASC). ASC computes the sparse codes for a large collection of prototype descriptors in the off-line learning phase with sparse coding (SC);and look up the nearest prototype's sparse code for each to-be-encoded descriptor in the encoding phase with Approximate Nearest Neighbour (ANN) search. It shares the low dimensionality of SC and the fast speed of ANN, which are both desired properties for the human action recognition task. We excessively evaluated ASC on the popular HMDB51 dataset, and confirme it is able to encode large number of video features into discriminative low dimensional representations efficientl. © 2015 IEEE.

关键词： action recognition approximate nearest neighbour approximate sparse coding sparse coding

来源：评论

学校读者我要写书评

暂无评论

Maximum constrained sparse coding for image representation 9

Maximum constrained sparse coding for image representation

引用

9th International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR) - Pattern Recognition and Computer Vision

作者： Zhang, Jie Zhao, Danpei Jiang, Zhiguo Beihang Univ Sch Astronaut Image Proc Ctr Beijing 100191 Peoples R China Beijing Key Lab Digital Media Beijing 100191 Peoples R China

ISBN: (纸本)9781510600546

sparse coding exhibits good performance in many computer vision applications by finding bases which capture high-level semantics of the data and learning sparse coefficients in terms of the bases. However, due to the fact that bases are non-orthogonal, sparse coding can hardly preserve the samples' similarity, which is important for discrimination. In this paper, a new image representing method called maximum constrained sparse coding (MCSC) is proposed. sparse representation with more active coefficients means more similarity information, and the infinite norm is added to the solution for this purpose. We solve the optimizer by constraining the codes' maximum and releasing the residual to other dictionary atoms. Experimental results on image clustering show that our method can preserve the similarity of adjacent samples and maintain the sparsity of code simultaneously.

关键词： sparse coding image representation maximum constraint infinite norm

来源：评论

学校读者我要写书评

暂无评论

Orthogonal and Smooth Subspace Based on sparse coding for Image Classification

Orthogonal and Smooth Subspace Based on Sparse Coding for Im...

引用

16th Pacific-Rim Conference on Multimedia (PCM)

作者： Dai, Fushuang Zhao, Yao Chang, Dongxia Lin, Chunyu Beijing Jiaotong Univ Inst Informat Sci Beijing 100044 Peoples R China Beijing Key Lab Adv Informat Sci & Network Techno Beijing Peoples R China

ISBN: (纸本)9783319240787;9783319240770

Many real-world problems usually deal with high-dimensional data, such as images, videos, text, web documents and so on. In fact, the classification algorithms used to process these high-dimensional data often suffer from the low accuracy and high computational complexity. Therefore, we propose a framework of transforming images from a high-dimensional image space to a low-dimensional target image space, based on learning an orthogonal smooth subspace for the SIFT sparse codes (SC-OSS). It is a two stage framework for subspace learning. Firstly, a sparse coding followed by spatial pyramid max pooling is used to get the image representation. Then, the image descriptor is mapped into an orthonormal and smooth subspace to classify images in low dimension. The proposed algorithm adds the orthogonality and a Laplacian smoothing penalty to constrain the projective function coefficient to be orthogonal and spatially smooth. The experimental results on the public datasets have shown that the proposed algorithm outperforms other subspace methods.

关键词： Image classification Orthogonal and smooth subspace sparse coding Max pooling

来源：评论

学校读者我要写书评

暂无评论

sparse coding based dense feature representation model for hyperspectral image classification

引用

JOURNAL OF ELECTRONIC IMAGING 2015年第6期24卷 063009-063009页

作者： Oguslu, Ender Zhou, Guoqing Zheng, Zezhong Iftekharuddin, Khan Li, Jiang Old Dominion Univ Batten Coll Engn & Technol Dept Elect & Comp Engn Norfolk VA 23529 USA Turkish Air Force NCO Vocat Coll Dept Elect TR-35410 Izmir Turkey Guilin Univ Technol Guangxi Key Lab Spatial Informat & Geomat Engn Guilin 541004 Guangxi Peoples R China Univ Elect Sci & Technol China Sch Resources & Environm Chengdu 610054 Peoples R China

We present a sparse coding based dense feature representation model (a preliminary version of the paper was presented at the SPIE Remote Sensing Conference, Dresden, Germany, 2013) for hyperspectral image (HSI) classification. The proposed method learns a new representation for each pixel in HSI through the following four steps: sub-band construction, dictionary learning, encoding, and feature selection. The new representation usually has a very high dimensionality requiring a large amount of computational resources. We applied the I-1/I-q regularized multiclass logistic regression technique to reduce the size of the new representation. We integrated the method with a linear support vector machine (SVM) and a composite kernels SVM (CKSVM) to discriminate different types of land cover. We evaluated the proposed algorithm on three well-known HSI datasets and compared our method to four recently developed classification methods: SVM, CKSVM, simultaneous orthogonal matching pursuit, and image fusion and recursive filtering. Experimental results show that the proposed method can achieve better overall and average classification accuracies with a much more compact representation leading to more efficient sparse models for HSI classification. (C) 2015 SPIE and IS&T

关键词： sparse coding feature extraction remote sensing hyperspectral imagery hyperspectral classification

来源：评论

学校读者我要写书评

暂无评论

Environmental microorganism classification using sparse coding and weakly supervised learning 2

Environmental microorganism classification using sparse codi...

引用

2nd ACM International Workshop on Environmental Multimedia Retrieval, EMR 2015

作者： Li, Chen Shirahama, Kimiaki Grzegorzek, Marcin Pattern Recognition Group University of Siegen Siegen Germany

ISBN: (纸本)9781450335584

Environmental Microorganisms (EMs), such as Epistylis and Rotifera, are very tiny living beings in human environments and decompose pollutants as their nutrition. The classification of EMs plays a fundamental role for establishing sustainable ecosystem. However, this is traditionally done by molecular methods using DNA or RNA analysis, or morphological methods using microscopes. These methods require huge monetary costs or manual efforts. In this paper, we propose an EM classification method by directly processing microscopic images. We especially address two problems: The first is a small training dataset problem. Because EM samples are collected from unstable real-world environments, it is difficult to stably obtain a large number of EM images. To effectively represent scarce training images, we use sparse coding (SC) which extracts sufficient local features from an image and reconstructs it by a sparse linear combination of bases. The second is a noisy image problem. Because EM samples are often found in dirty regions, their images often show a noisy background. To overcome this, we use Weakly Supervised Learning (WSL) which jointly performs the localisation and classification of EMs by examining the local information in training images. Experimental results on real-world images show the effectiveness and potential of our system. © 2015 ACM.

关键词： Environmental Microorganism Region-based support vector machine sparse coding Weakly Supervised Learning

来源：评论

学校读者我要写书评

暂无评论

Supervised sparse coding with local geometrical constraints 40

Supervised sparse coding with local geometrical constraints

引用

40th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2015

作者： Zhang, Hanchao Xu, Jinhua Department of Computer Science and Technology East China Normal University Shanghai China Shanghai Key Laboratory of Multidimensional Information Processing East China Normal University Shanghai China

ISBN: (纸本)9781467369978

sparse coding algorithms with geometrical constraints have received much attention recently. However, these methods are unsupervised and might lead to less discriminative representations. In this paper, we propose a supervised localityconstrained sparse coding method for classification. Two graphs are constructed, a labeled graph and an unlabeled graph. sparse codes with a labeled geometrical constraint will be more discriminative, however we cannot embed test samples with unknown label into a labeled graph. By coupling the two graphs, we aim to make the difference between sparse codes with labeled and unlabeled geometrical constraints as small as possible. As a result, sparse codes of test data can be obtained with the unlabeled geometrical constraint and the discrimination of the labeled geometrical constraint is maintained. Experiments on some benchmark datasets demonstrate the effectiveness of the proposed method. © 2015 IEEE.

关键词： geometrical constraint manifold embedding manifold learning sparse coding supervised

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：