检索结果-内蒙古大学图书馆

Bayesian Deep Learning for image Reconstruction: From structured sparsity to uncertainty estimation

ieee signal processing MAGAZINE 2023年第1期40卷 73-84页

作者： Dong, Weisheng Wu, Jinjian Li, Leida Shi, Guangming Li, Xin Hong Kong Polytech Univ Dept Comp Hong Kong Peoples R China Xidian Univ Sch Artificial Intelligence Xian 710071 Peoples R China Nanyang Technol Univ Singapore Singapore Xidian Univ Sch Artificial Intelligence Xian 710071 Peoples R China Nanyang Technol Univ Sch Elect & Elect Engn Rapid Rich Object Search Lab Singapore Singapore Xidian Univ Sch Elect Engn Xian Peoples R China Xidian Univ Sch Artificial Intelligence Xian 710071 Peoples R China Univ Sci & Technol China Elect Engn & informat Sci Hefei Peoples R China West Virginia Univ Lane Dept Comp Sci & Elect Engn Morgantown WV 26506 USA

Conventional wisdom in model-based computational imaging incorporates physics-based imaging models, noise characteristics, and image priors into a unified Bayesian framework. Rapid advances in deep learning have inspired a new generation of data-driven computational imaging systems with performances even better than those of their model-based counterparts. However, the design of learning-based algorithms for computational imaging often lacks transparency, making it difficult to optimize the entire imaging system in a complete manner.

关键词： Deep learning Uncertainty image coding computational modeling Imaging signal processing algorithms Network architecture

来源：评论

学校读者我要写书评

暂无评论

Towards image retrieval by texture segmentation with genetic programming

Towards image retrieval by texture segmentation with genetic...

引用

ieee symposium on computational intelligence in image and signal processing

作者： Ciesielski, Vic Kurniawan, Djaka Song, Andy RMIT Univ Sch Comp Sci & Informat Technol Melbourne Vic 3001 Australia

ISBN: (纸本)9781424407071

This paper examines the feasibility of an approach to image retrieval from a heterogeneous collection based on texture. For each texture of interest (T), a T-vs-other classifier is evolved for small n x n windows using genetic programming. The classifier is then used to segment the images in the collection. If there is a significant contiguous area of T in an image, it is considered to contain that texture for retrieval purposes. We have experimented with sky and grass textures in the Corel Volume 12 image set Experiments with a single image indicate that classifiers for the two textures can be learned to a high accuracy. Experiments with a test set of 714 Corel images gave a retrieval accuracy of 84% for both sky and grass textures. These results suggest that the use of texture could enhance retrieval accuracy in content based image retrieval systems.

关键词： image retrieval

来源：评论

学校读者我要写书评

暂无评论

An automated GA-based fuzzy image enhancement method

An automated GA-based fuzzy image enhancement method

引用

ieee symposium on computational intelligence in image and signal processing

作者： Khayat, Omid Razjouyan, Javad Aghvami, Mina Shahdoosti, Hamid Reza Loni, Babak

ISBN: (纸本)9781424427604

This paper presents an automated algorithm for image enhancement. A novel parametric indices of fuzziness (PIF) is introduced, which serves as the optimization criterion of the contrast enhancement procedure. The proposed PIT comprises the Sugeno class of involutive fuzzy complements and the first order fuzzy moment of the image. The PIT as the measure of fuzziness should be maximized, and the maximum of PIT is tuned based on the first-order fuzzy moment of the image. The parameters of the transformation function are found by the genetic algorithm aiming to maximize the PIF. Finally, several experiments are made to demonstrate the efficiency of the proposed method.

关键词： image enhancement Measure of fuzziness Fuzzy complements Parametric indices of fuzziness Genetic algorithm

来源：评论

学校读者我要写书评

暂无评论

Identification of dynamic nonlinear systems using computational intelligence techniques

Identification of dynamic nonlinear systems using computatio...

引用

ieee symposium on computational intelligence in image and signal processing

作者： Turchetti, Claudio Gianfelici, Francesco Univ Politecn Marche Dipartimento Elettron Intelligenza Artificiale & I-60131 Ancona Italy

ISBN: (纸本)9781424407071

A novel approach based on computational intelligence techniques for the identification of nonlinear dynamic systems is presented in this paper. The technique encompasses both the properties of the Karhunen-Loeve Transform in representing stochastic processes and the approximation capabilities of multi-layer neural networks. Experimental results on nonlinear systems governed by difference equations demonstrate the effectiveness of the proposed approach that is based on a real-time learning algorithm. Exhaustive experimentation on specific case studies was performed and some experimental results were compared with other existing techniques such as the Lee-Schetzen method, Least Mean Square (LMS), Recursive Least Square (RLS) and Normalized Least Mean Square (NLMS) algorithms. A better identification-accuracy was also achieved, and a reduction of some orders of magnitude in training-times compared with the well-known Lee-Schetzen method was obtained, thus making the proposed methodology one of the current best practices in this field.

关键词： system identification multi-layer neural networks Karhunen-Loeve Transform nonlinear dynamic systems

来源：评论

学校读者我要写书评

暂无评论

Exploiting automatic image segmentation to human detection and depth estimation

Exploiting automatic image segmentation to human detection a...

引用

symposium Series on computational intelligence, ieee SSCI 2011 - 2011 ieee symposium on computational intelligence for Multimedia, signal and Vision processing, CIMSIVP 2011

作者： Tseng, Hsiao-Chun Shyu, Jia-Jye Chang, Jyh-Yeong Lin, Chin-Teng Department of Electrical Engineering National Chiao Tung University Hsinchu Taiwan

ISBN: (纸本)9781424499151

In this paper, we combine image segmentation techniques and face detection methods to extract the human from scenes. Firstly, skin regions are detected and an ellipse fitting method is employed to detect the face region and consequently locate the human position. Then we propose an improved automatic seeded region growing algorithm to segment the image. The initial seeds are generated automatically, and the remaining pixels are classified to the nearest region. After the region growing procedure, two neighboring regions with high similarity are merged. The human body is determined by confining semantic human body region in segmented regions, and those belonging to the human face and human body are merged afterward. Lastly, we will detect the human vertical y-coordinate values in the image, and the depths can then be estimated according to the depth look-up tables of the camera. © 2011 ieee.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

image segmentation using a weighted kernel PCA approach to spectral clustering

Image segmentation using a weighted kernel PCA approach to s...

引用

ieee symposium on computational intelligence in image and signal processing

作者： Alzate, Carlos Suykens, Johan A. K. Katholieke Univ Leuven Dept Elect Engn ESAT SCD SISTA B-3001 Louvain Belgium

ISBN: (纸本)9781424407071

In classical graph-based image segmentation, a data-driven matrix is constructed representing similarities between every pair of pixels. The eigenvectors of such matrices contain relevant information about the clusters present on the image. An approach to image segmentation using spectral clustering with out-of-sample extensions is presented. This approach is based on the weighted kernel PCA framework. An advantage of the proposed method is the possibility to train and validate the clustering model on subsampled parts of the image to be segmented. The cluster indicators for the remaining pixels can then be inferred using the out-of-sample extension. This subsampling scheme can be used to reduce the computation time of the segmentation. Simulation results with grayscale and color images show improvements in terms of computation times together with visually appealing clusters.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

An adaptive approach to the segmentation of DCE-MR images of the breast: Comparison with classical thresholding algorithms

An adaptive approach to the segmentation of DCE-MR images of...

引用

ieee symposium on computational intelligence in image and signal processing

作者： Kaleli, Fatih Aydin, Nizamettin Ertas, Gokhan Gulcur, H. Ozcan Bahcesehir University Engineering Faculty Turkey Bogazici University Biomedical Engineering Institute Turkey

ISBN: (纸本)9781424407071

The segmentation of MR images has been playing an important role to improve the detection and diagnosis of breast cancer. Main problem in breast images is the identification of the boundary between chest wall and breast tissue. Minimizing the effects of patient motion is also important step in segmentation process. In image processing, there are many different segmentation algorithms. The most common used method among them is thresholding. However, classic thresholding methods are not effective for axial MR breast images completely because of the fact that the sequence artifacts in axial MR breast images are very high. For this reason, we have proposed a regional thresholding algorithm to segment MR images successfully. The outstanding problem is how to obtain an automatic procedure for detecting boundary between breast tissue and chest wall.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

A novel approach to collect training images from WWW for image thesaurus building

A novel approach to collect training images from WWW for ima...

引用

ieee symposium on computational intelligence in image and signal processing

作者： Park, Joohyoun Nang, Jongho Sogang Univ Dept Comp Sci & Engn Seoul South Korea

ISBN: (纸本)9781424407071

This paper introduces a novel approach to change gathered images from WWW into training images to build an image thesaurus. The requirements for being training images are a large number of images and with highly relevant to a given concept. To fulfill these requirements, a system should be able to collect a large number of relevant images to a given concept from WWW by the proposed criterion of relevance to the concept for each image. Then, the irrelevant images would be filtered out by the modified hierarchical clustering method based on the weighted combination of 5 MPEG-7 visual descriptors[9] and the proposed criterion of relevance to the concept for each cluster. Upon experimental results, the precision of the set of images generated by the proposed method is about 18% higher than that of the set of images generated by other methods[1][2].

关键词： auto image annotation content based image retrieval

来源：评论

学校读者我要写书评

暂无评论

Design of an image-Jamming signal Detection System 10

Design of an Image-Jamming Signal Detection System

引用

10th International symposium on computational intelligence and Design (ISCID)

作者： Zhang, Yang Shi, Chuan Dai, Huanyao LEETC Luoyang Peoples R China

ISBN: (纸本)9781538636756

image-jamming is one of the effective modes of self-defense interference against airborne (missile-borne) radar. It uses the multipath propagation strategy to prevent the radar from intercepting the exact location of jammer platform. Based on the analysis of the principle of image-jamming, this paper introduces a method of detecting image-jamming signals by using the polarization phase difference characteristics of received signals. According to this method, an image-jamming signal detection system was designed, and its composition and work flow were described in detail.

关键词： image jamming jamming signal detection polarization signal

来源：评论

学校读者我要写书评

暂无评论

Integrating the Role of computational intelligence and Digital signal processing in Education: Emerging Technologies and Mathematical Tools

引用

ieee signal processing MAGAZINE 2021年第3期38卷 154-162页

作者： Prochazka, Ales Vysata, Oldrich Marik, Vladimir Czech Tech Univ Cybernet Prague Czech Republic Univ Chem & Technol Dept Comp & Control Engn Prague 16628 Czech Republic Czech Tech Univ Czech Inst Informat Robot & Cybernet Prague 16628 Czech Republic Charles Univ Prague Fac Med Hradec Kralove Dept Neurol Prague 50005 Czech Republic Czech Tech Univ Czech Inst Informat Robot & Cybernet Prague 16000 Czech Republic

Rapid progress in the development of technological and computational tools has motivated substantial changes in the educational approach to the different disciplines of signal, image, and video processing. Moreover, the parallel evolution of sensor systems, data acquisition methods, and computational intelligence has emphasized the importance of signal processing and information engineering, particularly its role in integrating different scientific disciplines through the use of a common set of tools and underlying mathematics. Modern educational courses follow these trends and generally combine the teaching of fundamental computational methods of signal and system modeling with applications to selected case studies. The unifying idea is to apply similar mathematical methods for data processing in completely diverse areas. Emerging methods used in education contribute to this progress, and they provide opportunities to bring together specialists from different disciplines. New technologies facilitate real or virtual activities through excursions to remote laboratories, allowing the demonstration of robotic and speech recognition systems, for example. Participation in seminars, videoconferences, and discussions during colloquia meetings, when included in educational courses, can form further progressive and attractive teaching methods for the rapidly developing interdisciplinary area of signal processing.

关键词： Collaboration Digital signal processing Speech recognition Software tools Systems modeling Mathematics Educational courses Curriculum development Engineering education

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：