检索结果-内蒙古大学图书馆

Optimization of Probability Distributions for Residual Coding of Screen Content

Optimization of Probability Distributions for Residual Codin...

IEEE International conference on visual communications and image processing (VCIP) - visual communications in the Era of AI and Limited Resources

作者： Och, Hannah Strutz, Tilo Kaup, Andre Friedrich Alexander Univ Erlangen Nurnberg FAU Multimedia Commun & Signal Proc Cauerstr 7 D-91058 Erlangen Germany Leipzig Univ Telecommun Deutsch Telekom AG Inst Commun Engn Gustav Freytag Str 43-45 D-04277 Leipzig Germany

ISBN: (纸本)9781728185514

Probability distribution modeling is the basis for most competitive methods for lossless coding of screen content. One such state-of-the-art method is known as soft context formation (SCF). For each pixel to be encoded, a probability distribution is estimated based on the neighboring pattern and the occurrence of that pattern in the already encoded image. Using an arithmetic coder, the pixel color can thus be encoded very efficiently, provided that the current color has been observed before in association with a similar pattern. If this is not the case, the color is instead encoded using a color palette or, if it is still unknown, via residual coding. Both palette-based coding and residual coding have significantly worse compression efficiency than coding based on soft context formation. In this paper, the residual coding stage is improved by adaptively trimming the probability distributions for the residual error. Furthermore, an enhanced probability modeling for indicating a new color depending on the occurrence of new colors in the neighborhood is proposed. These modifications result in a bitrate reduction of up to 2.9 % on average. Compared to HEVC (HM-16.21 + SCM-8.8) and FLIF, the improved SCF method saves on average about 11 % and 18 % rate, respectively.

关键词： distribution modelling lossless coding screen content coding color image compression soft context formation

来源：评论

学校读者我要写书评

暂无评论

A STUDY ON MOUTH SHAPE-FEATURES SUITABLE FOR HMM SPEECH RECOGNITION USING FUSION OF visual AND AUDITORY INFORMATION

引用

IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS communications AND COMPUTER SCIENCES 1995年第11期E78A卷 1548-1552页

作者： DOI, N SHINTANI, A HAYASHI, Y OGIHARA, A TAKAMATSU, S Univ of Osaka Prefecture Sakai-shi Japan

Recently, some speech recognition methods using fusion of visual and auditory information have been researched. In this paper, a study on the mouth shape image suitable for fusion of visual and auditory information has been described. Features of mouth shape which are extracted from gray level image and binary image are adopted, and speech recognition using linear combination method has been performed. From results of speech recognition, the studies on the mouth shape features which are effective in fusion of visual and auditory information have been performed. And the effectiveness of using two kinds of mouth shape features also has been confirmed.

关键词： SPEECH RECOGNITION FUSION OF visual AND AUDITORY INFORMATION FEATURE OF MOUTH SHAPE image processing

来源：评论

学校读者我要写书评

暂无评论

image Retrieval Method using visual Query Suggestion and Relevance Feedback

Image Retrieval Method using Visual Query Suggestion and Rel...

引用

4th International conference on Wireless communications and Signal processing (WCSP)

作者： Zhang, Jing Yang, Yuncong Zhuo, Li Diao, Mengmeng Beijing Univ Technol Signal & Informat Proc Lab Beijing Peoples R China

ISBN: (纸本)9781467358293;9781467358309

Query suggestion is an effective human-computer interaction (HCI) approach in information retrieval. According to human vision system, the image retrieval method using visual query suggestion (VQS) can provide a friendly query interface to solve the query ambiguity problem. In this paper, the contentbased image retrieval (CBIR) system is realized first. Human-computer interaction used VQS to obtain users' intention. In this step, user submitted a query keyword to the system. VQS is utilized to provide a list of suggestions, each containing a keyword and a collection of representative images. If the user selects one of the image suggestions, this image will be viewed as the key image. Then CBIR system will retrieve the image sets to return the similar images based on the similarity of image features. In relevance feedback, user scored each returned image by the slider to optimize retrieval results. A friendly query interface is designed to carry out HCI in our system and the experimental result shows the proposed method can improve the average recall and precision efficiently.

关键词： human-computer interaction visual query suggestion content-based image retrieval relevance feedback

来源：评论

学校读者我要写书评

暂无评论

OBJECTIVE QUALITY ASSESSMENT FOR image RETARGETING BASED ON PERCEPTUAL DISTORTION AND INFORMATION LOSS

OBJECTIVE QUALITY ASSESSMENT FOR IMAGE RETARGETING BASED ON ...

引用

IEEE International conference on visual communications and image processing (VCIP)

作者： Hsu, Chih-Chung Lin, Chia-Wen Fang, Yuming Lin, Weisi School of Computer Engineering Nanyang Technological University Singapore

ISBN: (纸本)9781479902880

image retargeting techniques aim to obtain retargeted images with different sizes or aspect ratios for various display screens. Various content-aware image retargeting algorithms have been proposed recently. However, there is still no accurate objective metric for visual quality assessment of retargeted images. In this paper, we propose a novel objective metric for assessing visual quality of retargeted images based on perceptual geometric distortion and information loss. The proposed metric measures the geometric distortion of retargeted images by SIFT flow variation. Furthermore, a visual saliency map is derived to characterize human perception of the geometric distortion. On the other hand, the information loss in a retargeted image, which is calculated based on the saliency map, is integrated into the proposed metric. A user study is conducted to evaluate the performance of the proposed metric. Experimental results show the consistency between the objective assessments from the proposed metric and subjective assessments.

关键词： image Retargeting SIFT Flow Quality Assessment Quality Evaluation

来源：评论

学校读者我要写书评

暂无评论

An Efficient image Retrieval Model with Convolutional Neural Network based Text/image Identification for Copyright Violation Detection 30

An Efficient Image Retrieval Model with Convolutional Neural...

引用

30th IEEE Signal processing and communications Applications conference (SIU)

作者： Ozden, Harun Tavli, Bulent Demirci, M. Fatih Anadolu Ajansu Iletisim Teknol Direktorlugu Ankara Turkey TOBB Ekon Teknol Univ Elekt Elekt Muhendisligi Ankara Turkey Ankara Yildirim Beyazit Univ Bilgisayar Muhendishgi B Ankara Turkey

ISBN: (纸本)9781665450928

One of the most important problems faced by broadcasters is the unauthorized use of their images by third parties or organizations in a large-scale database, which contains hundreds of thousands of images. For this reason, it is important to perform an efficient and effective image retrieval, whose objective is to find the most similar images to a given test image. In addition, test images often contain text, and the presence of the text together with the visual part complicates the search process. In this paper, we present an image retrieval framework based on a bag of visual words, which has been shown to be effective in the literature. A convolutional neural network model is used to parse the text in the images. Experiments demonstrate the efficacy of this model in a large database.

关键词： Bag of visual Words SIFT Convolutional Neural Network image Retrieval

来源：评论

学校读者我要写书评

暂无评论

Volumetric End-to-End Optimized Compression for Brain images

Volumetric End-to-End Optimized Compression for Brain Images

引用

IEEE International conference on visual communications and image processing (VCIP)

作者： Gao, Shuo Zhang, Yueyi Liu, Dong Xiong, Zhiwei Univ Sci & Technol China Hefei Peoples R China

ISBN: (纸本)9781728180687

The amount of volumetric brain image increases rapidly, which requires a vast amount of resources for storage and transmission, so it's urgent to explore an efficient volumetric compression method. Recent years have witnessed the progress of deep learning-based approaches for two-dimensional (2D) natural image compression, but the field of learned volumetric image compression still remains unexplored. In this paper, we propose the first end-to-end learning framework for volumetric image compression by extending the advanced techniques of 2D image compression to volumetric images. Specifically, a convolutional autoencoder is used to compress 3D image cubes, and the non-local attention models are embedded in the convolutional autoencoder to jointly capture local and global correlations. Both hyperprior and autoregressive models are used to perform the conditional probability estimation in entropy coding. To reduce model complexity, we introduce a convolutional long short-term memory network for the autoregressive model based on channel-wise prediction. Experimental results on volumetric mouse brain images show that the proposed method outperforms JPEG2000-3D, HEVC and state-of-the-art 2D methods.

关键词： Volumetric image compression 3D convolutional neural network convolutional long short-term memory

来源：评论

学校读者我要写书评

暂无评论

MULTI-MODEL PREDICTION FOR image SET COMPRESSION

MULTI-MODEL PREDICTION FOR IMAGE SET COMPRESSION

引用

IEEE International conference on visual communications and image processing (VCIP)

作者： Shi, Zhongbo Sun, Xiaoyan Wu, Feng Univ Sci & Technol China Hefei Anhui Peoples R China Microsoft Res Asia Beijing Peoples R China

ISBN: (纸本)9781479902880

The key task in image set compression is how to efficiently remove set redundancy among images and within a single image. In this paper, we propose the first multi-model prediction (MoP) method for image set compression to significantly reduce inter image redundancy. Unlike the previous prediction methods, our MoP enhances the correlation between images using feature-based geometric multi-model fitting. Based on estimated geometric models, multiple deformed prediction images are generated to reduce geometric distortions in different image regions. The block-based adaptive motion compensation is then adopted to further eliminate local variances. Experimental results demonstrate the advantage of our approach, especially for images with complicated scenes and geometric relationships.

关键词： image set compression multiple models prediction HEVC

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Model for Natural Face De-Identiation with Adjustable Privacy

A Hybrid Model for Natural Face De-Identiation with Adjustab...

引用

IEEE International conference on visual communications and image processing (VCIP)

作者： Wen, Yunqian Liu, Bo Xie, Rong Zhu, Yunhui Cao, Jingyi Song, Li Shanghai Jiao Tong Univ Inst Image Commun & Network Engn Shanghai Peoples R China Univ Technol Sydney Sch Comp Sci Sydney NSW Australia

ISBN: (纸本)9781728180687

As more and more personal photos are shared and tagged in social media, security and privacy protection are becoming an unprecedentedly focus of attention. Avoiding privacy risks such as unintended verification, b ecomes increasingly challenging. To enable people to enjoy uploading photos without having to consider these privacy concerns, it is crucial to study techniques that allow individuals to limit the identity information leaked in visual data. In this paper, we propose a novel hybrid model consists of two stages to generate visually pleasing deidentified f ace i mages a ccording t o a s ingle i nput. Meanwhile, we successfully preserve visual similarity with the original face to retain data usability. Our approach combines latest advances in GAN-based face generation with well-designed adjustable randomness. In our experiments we show visually pleasing deidentified output of our method while preserving a high similarity to the original image content. Moreover, our method adapts well to the verificator of unknown structure, which further improves the practical value in our real life.

关键词： privacy protection multi-level features fusion GAN-based face generation randomness

来源：评论

学校读者我要写书评

暂无评论

3D-CNN Autoencoder for Plenoptic image Compression

3D-CNN Autoencoder for Plenoptic Image Compression

引用

IEEE International conference on visual communications and image processing (VCIP)

作者： Zhong, Tingting Jin, Xin Tong, Kedeng Tsinghua Shenzhen Int Grad Sch Shenzhen Key Lab Broadband Network & Multimedia Shenzhen 518055 Peoples R China

ISBN: (纸本)9781728180687

Recently, plenoptic image has attracted great attentions because of its applications in various scenarios. However, high resolution and special pixel distribution structure bring huge challenges to its storage and transmission. In order to adapt compression to the structural characteristic of plenoptic image, in this paper, we propose a Data Structure Adaptive 3D-convolutional(DSA-3D) autoencoder. The DSA-3D autoencoder enables up-sampling and down-samping the sub-aperture sequence along the angular resolution or spatial resolution, thereby avoiding the artifacts caused by directly compressing plenoptic image and achieving better compression efficiency. In addition, we propose a special and efficient S quare rearrangement to generate sub-aperture sequence. We compare Square with Zigzag sub-aperture sequence rearrangements, and analyzed the compression efficiency of block image compression and whole image compression. Compared with traditional hybrid encoders HEVC, JPEG2000 and JPEG PLENO(WaSP), the proposed DSA-3D(Square) autoencoder achieves a superior performance in terms of PSNR metrics.

关键词： Plenoptic image compression Autoencoder network 3D-CNN

来源：评论

学校读者我要写书评

暂无评论

Foveation-Based image Quality Assessment

Foveation-Based Image Quality Assessment

引用

IEEE visual communications and image processing conference

作者： Tsai, Wen-Jiin Liu, Yi-Shih Natl Chiao Tung Univ Dept Comp Sci Hsinchu 30050 Taiwan

ISBN: (纸本)9781479961399

Since human vision has much greater resolutions at the center of our visual field than elsewhere, different criteria of quality assessment should be applied on the image areas with different visual resolutions. This paper proposed a foveation-based image quality assessment method which adopted different sizes of windows in quality assessment for a single image. visual salience models which estimate visual attention regions are used to determine the foveation center and foveation resolution models are used to guide the selection of window sizes for the areas over spatial extent of the image. Finally, the quality scores obtained from different window sizes are pooled together to get a single value for the image. The proposed method has been applied to IQA metrics, SSIM, PSNR, and UQI. The result shows that both Spearman and Kendall correlation coefficients can be improved significantly by our foveation-based method.

关键词： image quality assessment foveation human visual system visual salience model

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：