检索结果-内蒙古大学图书馆

IEEE International Conference on Acoustics, Speech, and Signal processing

作者： Jaehyun Im Inhye Yoon Monson H. Hayes Joonki Paik Image Processing and Intelligent Systems Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul 156-756 Korea

ISBN: (纸本)9781479903573

In this paper, we present a novel contrast enhancement method for backlit images that consists of three steps: i) computation of the transmission coefficients using the dark channel prior, ii) generation of multiple images having different exposures based on the transmission coefficients, and iii) image fusion. Compared to global intensity transformation methods and spatially invariant contrast enhancement algorithms, our approach first extracts under-exposed regions using the dark channel prior map, and then performs spatially adaptive contrast enhancement. As a result, the contrast of the image is increased, especially for backlit scenes and those with very wide dynamic range, while still preserving image details and color.

关键词： contrast enhancement contrast enhancement method TRANSMISSION COEFFICIENT Lighting Backlights image CONTRAST multiple image compensated images wide dynamic range imagery (Psychotherapy)

来源：评论

学校读者我要写书评

暂无评论

Regularized Iterative Restoration of Combined Optical and Color Filter Array Degradation

Regularized Iterative Restoration of Combined Optical and Co...

引用

International Conference on Future Generation Communication and Networking Symposia, FGCNS

作者： Yoonjong Yoo Sinyoung Jun Jeongho Shin Joonki Paik Image Processing and Intelligent System Laboratory Department of Advanced Imaging Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul South Korea Department of Web information Engineering Hankyong National University Gyeonggi South Korea

This paper presents an image formation model of a digital camera with consideration of both optical and the Bayer color filter array (CFA) degradations. Based on the proposed model, a regularized iterative image restoration algorithm is presented to deconvolve the space-variant image degradation. The spatially adaptive version further improves the restoration quality. Hardware implementation issues are briefly summarized, and future modification plan is presented.

关键词： Optical filters Optical arrays Degradation image restoration Interpolation Color Cameras Deconvolution Lenses Optical films

来源：评论

学校读者我要写书评

暂无评论

Spatially Adaptive image Restoration and its FIR Implementation

Spatially Adaptive Image Restoration and its FIR Implementat...

引用

International Conference on Future Generation Communication and Networking Symposia, FGCNS

作者： Jinyoung Youn Younguk Park Jeongho Shin Joonki Paik Image Processing and Intelligent System Laboratory Graduate School of Advanced Imaging Science Department of Advanced Imaging Multimedia and Film Chung-Ang University Seoul South Korea Department of Web information Engineering Hankyong National University Gyeonggi South Korea

This paper presents a spatially adaptive image restoration for EDoF lens images. A practical implementation method is also discussed for real-time applications. For basic image restoration we adopt the truncated constrained least squares (TCLS) filter, and for adaptively selecting the weights of the observed and the restored images we compute local variance. Based on experimental results, we can claim that the proposed restoration algorithm can successfully remove the image degradation with suppressing noise amplification.

关键词： image restoration Finite impulse response filter Degradation Lenses Least squares methods Adaptive filters image processing Conferences Adaptive systems intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of wavelet-based scale-invariant feature extraction using different wavelet bases

Comparative analysis of wavelet-based scale-invariant featur...

引用

作者： Lim, Joohyun Kim, Youngouk Paik, Joonki Image Processing and Intelligent Systems Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University 221 Heuksuk-Dong Dongjak-Ku Seoul 156-756 Korea Republic of 401-402 B/D 193 Yakdae-Dong WonMi-Gu Puchon-Si KyungGi-Do 420-140 Korea Republic of

ISBN: (纸本)9783642105456

In this paper, we present comparative analysis of scale-invariant feature extraction using different wavelet bases. The main advantage of the wavelet transform is the multi-resolution analysis. Furthermore, wavelets enable localigation in both space and frequency domains and high-frequency salient feature detection. Wavelet transforms can use various basis functions. This research aims at comparative analysis of Daubechies, Haar and Gabor wavelets for scale-invariant feature extraction. Experimental results show that Gabor wavelets outperform better than Daubechies, Haar wavelets in the sense of both objective and subjective measures. © 2009 Springer-Verlag Berlin Heidelberg.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Ringing artifact removal in digital restored images using multi-resolution edge map

Ringing artifact removal in digital restored images using mu...

引用

作者： Kim, Sangjin Jun, Sinyoung Lee, Eunsung Shin, Jeongho Paik, Joonki Image Processing and Intelligent Systems Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University 221 Heuksuk-Dong Dongjak-Ku Seoul 156-756 Korea Republic of Department of Web Information Engineering Hankyong National University 67 Seokjeong-Dong Anseong Kyonggi-Do 456-749 Korea Republic of

ISBN: (纸本)9783642105456

This paper presents a novel approach to reducing ringing artifact in digitally restored images by using multi-resolution edge map. The performance of reducing ringing artifacts depends on the accurate classification of the local features in the image. The discrete wavelet transform (DWT) provides effective insight into both spatial and frequency characteristics of an image. Through the DWT analysis, we show that ringing artifacts can be suppressed to a great extent by using multiple-level edge maps, which provide enhanced matching to local edges. Base on the experimental results, the proposed method can reduce ringing artifacts with minimized edge degradation by using DWT analysis. © 2009 Springer-Verlag Berlin Heidelberg.

关键词： Discrete wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Active shape model-based gait recognition using infrared images

International Journal of Signal Processing, Image Processing...

引用

International Journal of Signal processing, image processing and Pattern Recognition 2008年第4期2卷 1-12页

作者： Kim, Daehee Lee, Seungwon Paik, Jooki Image Processing and Intelligent Systems Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University 221 Heuksuk-Dong Dongjak-Ku Seoul 156-756 Korea Republic of

We present a gait recognition system using infra-red (IR) images. Since an IR camera is not affected by the intensity of illumination, it is able to provide constant recognition performance regardless of the amount of illumination. Model-based object tracking algorithms enable robust tracking with partial occlusions or dynamic illumination. However, this algorithm often fails in tracking objects if strong edge exists near the object. Replacement of the input image by an IR image guarantees robust object region extraction because background edges do not affect the IR image. In conclusion, the proposed gait recognition algorithm improves accuracy in object extraction by using IR images and the improvements finally increase the recognition rate of gaits.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Fingerprint Watermarking for H.264 Streaming Media

Fingerprint Watermarking for H.264 Streaming Media

引用

Frontiers in the Convergence of Bioscience and Information Technologies, FBIT

作者： Sooyeun Jung Dongeun Lee Seongwon Lee Joonki Paik Image Processing and Intelligent Systems Laboratory Department of Image Engineering Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul South Korea Department of Computer Engineering Kwangwoon University Seoul South Korea

In this paper we propose a method that identifies users at H.264 streaming using watermarking with fingerprints. The watermark can efficiently reduce the potential danger of forgery or alteration. Especially a biometric watermark has various advantages. Among entire biometric characteristics, the fingerprint is the most convenient and economical. In this paper we propose a novel fingerprint-based watermarking technique that can survive under very low bit-rate compression. The proposed algorithm consists of enhancement of a fingerprint image, watermark insertion using discrete wavelet transform. In this paper we also analyze H.264 compression pattern and its effects on watermarking. After restoring the damaged watermark sequence using various filters, the algorithm extracts the embedded watermark. The proposed algorithm can achieve robust watermark extraction against H.264 compressed videos.

关键词： Fingerprint recognition Watermarking Streaming media image coding Biometrics Discrete wavelet transforms Forgery image matching Pattern analysis image restoration

来源：评论

学校读者我要写书评

暂无评论

COMPRESSIVE SENSING-BASED image DENOISING USING ADAPTIVE MULTIPLE SAMPLING AND OPTIMAL ERROR TOLERANCE

COMPRESSIVE SENSING-BASED IMAGE DENOISING USING ADAPTIVE MUL...

引用

IEEE International Conference on Acoustics, Speech, and Signal processing

作者： Wonseok Kang Eunsung Lee Eunjung Chea Aggelos K. Katsaggelos Joonki Paik Image Processing and Intelligent Systems Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Seoul Chung-Ang University Korea Department of Electrical Engineering and Computer Science Northwestern University Evanston IL 60208 USA

ISBN: (纸本)9781479903573

In this paper, we present a compressive sensing-based image denoising algorithm using spatially adaptive image representation and estimation of optimal error tolerance based on sparse signal analysis. The proposed method performs block-based multiple compressive sampling after decomposing the sparse signal into feature and non-feature regions using simple statistical analysis. For minimization of recovery error and number of iterations, the modified OMP method estimates the optimal error tolerance using the average variance in the recovery step. Experimental results demonstrate that the proposed denoising algorithm better removes noise without undesired artifacts than existing state-of-the-art methods in terms of both objective (PSNR/SSIM) and subjective measures. processing time of the proposed method is 5 to 10 times faster than the standard OMP-based method.

关键词： Tolerances physiologic tolerance Sampling system recovery image denoising image representation images Signal analysis Statistical analysis Statistical methods image denoising algorithm

来源：评论

学校读者我要写书评

暂无评论

Single camera-based full depth map estimation using color shifting property of a multiple color-filter aperture

Single camera-based full depth map estimation using color sh...

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Seungwon Lee Junghyun Lee Monson H. Hayes Aggelos K. Katsaggelos Joonki Paik Image Processing and Intelligent Systems Laboratory Graduate School of Advanced Imaging Science Multimedia and Film Chung-Ang University Seoul South Korea Department of Electrical Engineering and Computer Science Northwestern University Evanston IL USA

A multiple color-filter aperture (MCA) camera can provide depth information as well as color and intensity in the single-camera framework, where the MCA generates misalignment between color channels depending on the distance of a region-of-interest. In this paper, we present a single camera-based estimation of the full depth map using the color shifting property of the MCA. For estimating the color shifting vectors (CSVs) among red, green, and blue color channels, edges are extracted at each color channel. At the edge, we estimate CSVs using normalized cross correlation combined with color shifting mask map. A full depth map is then generated by depth interpolation using the matting Laplacian method from sparsely estimated CSVs at an edge location. Experimental results show that the proposed method can not only estimate the full depth map but also correct the misaligned color image to generate photorealistic color images using a single camera equipped with MCA.

关键词： image color analysis Cameras Estimation Channel estimation image edge detection Interpolation Apertures

来源：评论

学校读者我要写书评

暂无评论

New corner detector using non-cornerness measure

New corner detector using non-cornerness measure

引用

IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia)

作者： Woon Cho Seokmok Park Jacob D'avy Joonki Paik The University of Tennessee Knoxville TN USA Image Processing and Intelligent Systems Laboratory Graduate School of Advanced Imaging Science and Film Chung-Ang University Seoul Korea University of Tennessee Knoxville Knoxville TN US

In this paper, we present a novel corner detection method based on a new non-cornerness measure. The non-cornerness function is comprised of two steps: 1) eliminate any pixel located in a flat region and 2) remove a pixel that is positioned along an edge in any orientation. The experimental results show that our proposed method outperforms previous corner detectors.

关键词： Detectors image edge detection Indexes Boundary conditions Computer vision Real-time systems Information and communication technology

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：