检索结果-内蒙古大学图书馆

10th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Sanyal, Samriddha Kundu, Arnab Mukherjee, Dipti Prasad Indian Stat Inst 203 Barrackpore Trunk Rd Kolkata 700108 India

ISBN: (纸本)9781450347532

the problem of tracking ball in a soccer video is challenging because of sudden change in speed and orientation of the soccer ball. Successful tracking in such a scenario depends on the ability of the algorithm to balance prior constraints continuously against the evidence garnered from the sequences of images. this paper proposes a particle filter based algorithm that tracks the ball when it changes its direction suddenly or takes high speed. Exact, deterministic tracking algorithms based on discretized functional, suffer from severe limitations in the form of prior constraints. Our tracking algorithm has shown excellent result even for partial occlusion which is a major concern in soccer video. We have shown that the proposed tracking algorithm is at least 7.2% better compared to competing approaches for soccer ball tracking.

关键词： Tracking Soccer ball Particle filter Measurement space Resampling

来源：评论

学校读者我要写书评

暂无评论

Surface fitting in SPECT imaging useful for Detecting Parkinson's Disease and Scans Without Evidence of Dopaminergic Deficit

Surface fitting in SPECT imaging useful for Detecting Parkin...

引用

4th National conference on computer vision, Pattern Recognition, image processing and graphics (NCVPRIPG)

作者： Prashanth, R. Roy, Sumantra Dutta Mandal, Pravat K. Ghosh, Shantanu Indian Inst Technol Delhi Dept Elect Engn New Delhi 110016 India Natl Brain Res Ctr Neurospectroscopy & Neuroimaging Lab Gurgaon 122050 Haryana India Massachusetts Gen Hosp Martinos Ctr Biomed Imaging Boston MA 02114 USA Harvard Univ Sch Med Boston MA USA

ISBN: (纸本)9781479915880

Dopaminergic imaging using Single Photon Emission Computed Tomography (SPECT) with I-123-Ioflupane have shown to increase the diagnostic accuracy in Parkinson's Disease (PD). Studies show that around 10% of subjects who are clinically diagnosed as PD, have SPECT scans in the normal range and are called Scans Without Evidence of Dopaminergic Deficit (SWEDD) subjects. Subsequent follow-up on these subjects has indicated that they are unlikely to have PD. Detection and differentiation of PD and SWEDD is problematic in the early stages of the disease. Early and accurate diagnosis of PD and also SWEDD is crucial for early management, avoidance of unnecessary medical examinations and therapies;and their side-effects. We in our paper, use the SPECT images from 35 Normal, 36 PD and 38 SWEDD subjects as obtained from the Parkinson's Progression Markers Initiative (PPMI) database, to carry out intensity-based surface fitting using polynomial model. this is the first time that such kind of modeling is carried out on the SPECT images for the characterization of PD. Our results show that the surface profile in terms of model coefficients and goodness-of-fit parameters is different for Normal, Early PD and SWEDD subjects. Such kind of modeling may aid in the diagnosis of early PD and SWEDD from SPECT images.

关键词： Parkinson's disease Early diagnosis SPECT imaging image Segmentation Surface fitting Polynomial models

来源：评论

学校读者我要写书评

暂无评论

Generating Synthetic Handwriting using n-gram letter glyphs 16

Generating Synthetic Handwriting using n-gram letter glyphs

引用

10th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Dey, Arka Ujjal Harit, Gaurav Indian Inst Technol Jodhpur Old Residency Rd Jodhpur Rajasthan India

ISBN: (纸本)9781450347532

We propose a framework for synthesis of natural semi cursive handwritten Latin script that can find application in text personalization, or in generation of synthetic data for recognition systems. Our method is based on the generation of synthetic n-gram letter glyphs and their subsequent concatenation. We propose a non-parametric data driven generation scheme that is able to mimic the variation observed in handwritten glyph samples to synthesize natural looking synthetic glyphs. these synthetic glyphs are then stitched together to form complete words, using a spline based concatenation scheme. Further, as a refinement, our method is able to generate pen-lifts, giving our results a natural semi cursive look. through subjective experiments and detailed analysis of the results, we demonstrate the effectiveness of our formulation in being able to generate natural looking synthetic script.

关键词： HandWriting Synthesis Gaussian Process n-gram

来源：评论

学校读者我要写书评

暂无评论

On defocus, diffusion and depth estimation

引用

PATTERN RECOGNITION LETTERS 2007年第3期28卷 311-319页

作者： Namboodiri, Vinay P. Chaudhuri, Subhasis Indian Inst Technol Vis & Image Proc Lab Dept Elect Engn Bombay 400076 Maharashtra India

An intrinsic property of real aperture imaging has been that the observations tend to be defocused. this artifact has been used in an innovative manner by researchers for depth estimation, since the amount of defocus varies with varying depth in the scene. there have been various methods to model the defocus blur. We model the defocus process using the model of diffusion of heat. the diffusion process has been traditionally used in low level vision problems like smoothing, segmentation and edge detection. In this paper a novel application of the diffusion principle is made for generating the defocus space of the scene. the defocus space is the set of all possible observations for a given scene that can be captured using a physical lens system. Using the notion of defocus space we estimate the depth in the scene and also generate the corresponding fully focused equivalent pin-hole image. the algorithm described here also brings out the equivalence of the two modalities, viz. depth from focus and depth from defocus for structure recovery. (c) 2006 Elsevier B.V. All rights reserved.

关键词： depth from defocus shape estimation diffusion spectral method

来源：评论

学校读者我要写书评

暂无评论

Complexity Assisted Consistent Quality Rate Control for High Resolution H.264 Video Conferencing 5

Complexity Assisted Consistent Quality Rate Control for High...

引用

5th National conference on computer vision, Pattern Recognition, image processing and graphics (NCVPRIPG)

作者： Bhattacharyya, Subhomoy Chakrabarti, Indrajit Kolekar, Maheshkumar H. Squid Syst Inc Hyderabad 500062 Andhra Pradesh India Indian Inst Technol Kharagpur 721302 W Bengal India Indian Inst Technol Patna 800013 Bihar India

ISBN: (纸本)9781467385640

Video based multimedia services are showing major growth in recent years. though the video coding recommendation ITU-T H.265/HEVC is in operating state, the majority of real-time video applications including video conferencing and live streaming of events rely mainly on less computationally intensive H.264/AVC coding standard which is well established among video industry. Rate control algorithms are indispensable for delivering superior quality video over limited bandwidth connections. In this paper, we propose a rate control technique which provides consistent quality video output over time in a limited bandwidth video conferencing scenario. Using the concept of video traffic prediction and linear complexity model, we compute the complexity of the video sequence in real time. We present a better estimate of quantization parameter at the GOP (group of picture) layer. Our proposed method maintains similar quality for reconstructed video when compared to rate control scheme of JM 19.0 implemented in real-time video conferencing system with restricted quality variation. On an average, 22% improvement has been observed in terms of standard deviation of frame PSNR values when compared to JM 19.0 rate control scheme implemented in high resolution video conferencing scenario.

关键词： rate control H.264/AVC video traffic prediction consistent quality GOP layer

来源：评论

学校读者我要写书评

暂无评论

A Bottom-Up and Top-Down Approach for image Captioning using Transformer 11

A Bottom-Up and Top-Down Approach for Image Captioning using...

引用

11th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Parameswaran, Sandeep Narayan Das, Sukhendu Indian Inst Technol Madras Chennai Tamil Nadu India

ISBN: (纸本)9781450366151

Describing the contents of an image automatically has been a fundamental problem in the field of artificial intelligence and computer vision. Existing approaches are either top-down, which start from a simple representation of an image and convert it into a textual description;or bottom-up, which come up with attributes describing numerous aspects of an image to form the caption or a combination of both. Recurrent neural networks (RNN) enhanced by Long Short-Term Memory networks (LSTM) have become a dominant component of several frameworks designed for solving the image captioning task. Despite their ability to reduce the vanishing gradient problem, and capture dependencies, they are inherently sequential across time. In this work, we propose two novel approaches, a top-down and a bottom-up approach independently, which dispenses the recurrence entirely by incorporating the use of a Transformer, a network architecture for generating sequences relying entirely on the mechanism of attention. Adaptive positional encodings for the spatial locations in an image and a new regularization cost during training is introduced. the ability of our model to focus on salient regions in the image automatically is demonstrated visually. Experimental evaluation of the proposed architecture on the MS-COCO dataset is performed to exhibit the superiority of our method.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Event Geo-Localization and Tracking From Crowd-Sourced Video Metadata 16

Event Geo-Localization and Tracking From Crowd-Sourced Video...

引用

10th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： More, Amit Chaudhuri, Subhasis Indian Inst Technol Dept Elect Engn Bombay Maharashtra India

ISBN: (纸本)9781450347532

We propose a novel technique for event geo-localization (i.e. 2-D location of the event on the surface of the earth) from the sensor metadata of crowd-sourced videos collected from smartphone devices. With the help of sensors available in the smartphone devices, such as digital compass and GPS receiver, we collect metadata information such as camera viewing direction and location along with the video. the event localization is then posed as a constrained optimization problem using available sensor metadata. Our results on the collected experimental data shows correct localization of events, which is particularly challenging for classical vision based methods because of the nature of the visual data. Since we only use sensor metadata in our approach, computational overhead is much less compared to what would be if video information is used. At the end, we illustrate the benefits of our work in analyzing the video data from multiple sources through geo-localization.

关键词： Event localization Smartphone Digital Compass Optimization GPS

来源：评论

学校读者我要写书评

暂无评论

Informed Multimodal Latent Subspace Learning via Supervised Matrix Factorization 16

Informed Multimodal Latent Subspace Learning via Supervised ...

引用

10th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Gaurav, Ramashish Verma, Mridula Shukla, K. K. BHU Indian Inst Technol Varanasi Uttar Pradesh India

ISBN: (纸本)9781450347532

Matrix factorization technique has been widely used as a popular method to learn a joint latent-compact subspace, when multiple views or modals of objects (belonging to single-domain or multiple-domain) are available. Our work confronts the problem of learning an informative latent subspace by imparting supervision to matrix factorization for fusing multiple modals of objects, where we devise simpler supervised additive updates instead of multiplicative updates, thus scalable to large scale datasets. To increase the classification accuracy we integrate the label information of images with the process of learning a semantically enhanced subspace. We perform extensive experiments on two publicly available standard image datasets of NUS WIDE and compare the results with state-of-the-art subspace learning and fusion techniques to evaluate the efficacy of our framework. Improvement obtained in the classification accuracy confirms the effectiveness of our approach. In essence, we propose a novel method for supervised data fusion thus leading to supervised subspace learning.

关键词： image Classification Joint Subspace Learning Supervised Matrix Factorization

来源：评论

学校读者我要写书评

暂无评论

A STRATIFIED REGISTRATION FRAMEWORK FOR DSA ARTIFACT REDUCTION USING RANDOM WALKER 16

A STRATIFIED REGISTRATION FRAMEWORK FOR DSA ARTIFACT REDUCTI...

引用

10th indian conference on computer vision, graphics and image processing (ICVGIP)

作者： Sundarapandian, Manivannan Kalpathi, Ramakrishnan Siemens Healthcare Private Ltd 84 Hosur Rd Bangalore 560100 Karnataka India Indian Inst Sci Dept Elect Engn Bangalore 560012 Karnataka India

ISBN: (纸本)9781450347532

In Digital Subtraction Angiography (DSA), non-rigid registration of the mask and contrast images to reduce the motion artifacts is a challenging problem. In this paper, we have proposed a novel stratified registration framework for DSA artifact reduction. We use quad-trees to generate the non-uniform grid of control points and obtain the sub-pixel displacement offsets using Random Walker (RW). We have also proposed a sequencing logic for the control points and an incremental LU decomposition approach that enables reuse of the computations in the RW step. We have tested our approach using clinical data sets, and found that our registration framework has performed comparable to the graph-cuts (at the same partition level), in regions wherein 95% artifact reduction was achieved. the optimization step achieves a speed improvement of 4.2 times with respect to graph-cuts.

关键词： image Registration Random Walker DSA quad-trees

来源：评论

学校读者我要写书评

暂无评论

Parallel architectures for image processing

引用

ELECTRONICS & COMMUNICATION ENGINEERING JOURNAL 1998年第3期10卷 139-151页

作者： Downton, A Crookes, D Univ Essex Dept Elect Syst Engn Colchester CO4 3SQ Essex England Queens Univ Belfast Dept Comp Sci Belfast BT7 1NN Antrim North Ireland

image processing is often considered a good candidate for the application of parallel processing because of the large volumes of data and the complex algorithms commonly encountered. this paper presents a tutorial introduction to the field of parallel image processing. After introducing the classes of parallel processing a brief review of architectures for parallel image processing is presented. Software design for low-level image processing and parallelism in high-level image processing are discussed and an application of parallel processing to handwritten postcode recognition is described. the paper concludes with a look at future technology and market trends.

关键词： image processing image recognition Parallel architecture Digital signal processing chips software design Microprocessors and microcomputers parallel architectures handwritten postcode recognition Optical information, image and video signal processing digital signal processing chips optical character recognition computer vision and image processing techniques high-level image processing low-level image processing parallel processing

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：