检索结果-内蒙古大学图书馆

Optimal sub-shape models by minimum description length

学校读者我要写书评

暂无评论

Optimal sub-shape models by minimum description length

Conference on computer vision and pattern recognition (CVPR)

作者： G. Langs P. Peloschek H. Bischof Institute for Computer Graphics and Vision Graz University of Technology Graz Austria Pattern Recognition and Image Processing Group University of Technology Vienna Vienna Austria Department of Clinical Radiology Vienna Medical University Vienna Austria

Active shape models are powerful and widely used tool to interpret complex image data. By building models of shape variation they enable search algorithms to use a priori knowledge in an efficient and gainful way. However, due to the linearity of PCA, non-linearities like rotations or independently moving sub-parts in the data can deteriorate the resulting model considerably. Although non-linear extensions of active shape models have been proposed and application specific solutions have been used, they still need a certain amount of user interaction during model building. In this paper the task of building/choosing optimal models is tackled in a more generic information theoretic fashion. In particular, we propose an algorithm based on the minimum description length principle to find an optimal subdivision of the data into sub-parts, each adequate for linear modeling. This results in an overall more compact model configuration. Which in turn leads to a better model in terms of modes of variations. The proposed method is evaluated on synthetic data, medical images and hand contours.

关键词： Active shape model Biomedical imaging Principal component analysis computer vision Linearity Polynomials pattern recognition computer graphics Radiology Image processing

MsEDNet: Multi-Scale Deep Saliency Learning for Moving Object Detection

学校读者我要写书评

暂无评论

MsEDNet: Multi-Scale Deep Saliency Learning for Moving Objec...

IEEE International Conference on Systems, Man, and Cybernetics

作者： Prashant W. Patil Subrahmanyam Murala Abhinav Dhall Sachin Chaudhary Indian Institute of Technology Delhi New Delhi Delhi IN Computer Vision and Pattern Recognition Lab Indian Institute of Technology Ropar INDIA Learning Afffect and Semantic Image AnalysIs (LASII) Group Indian Institute of Technology Ropar INDIA

Moving object detection (foreground and background) is an important problem in computer vision. Most of the works in this problem are based on background subtraction. However, these approaches are not able to handle scenarios with infrequent motion of object, illumination changes, shadow, camouflage etc. To overcome these, here a two stage robust and compact method for moving object detection (MOD) is proposed. In first stage, to generate the saliency map, background image is estimated using a temporal histogram technique with the help of several input frames. In the second stage, multiscale encoder-decoder network is used to learn multiscale semantic feature of estimated saliency for foreground extraction. The encoder is used to extract multi-scale features from multi-scale saliency map. The decoder part is designed to learn the mapping of low resolution multi-scale features into high resolution output frame. To observe the efficacy of proposed MsEDNet, experiments are conducted on two benchmark datasets (change detection (CDnet-2014) and Wallflower) for MOD. The precision, recall and F-measure are used as performance parameter for comparison with the existing state-of-the-art methods. Experimental results show a significant improvement in detection accuracy and decrement in execution time as compared to the state-of-the-art methods for MOD.

关键词： Feature extraction Estimation Decoding Object detection Histograms Lighting Semantics

TransDocUNet: A Transformer-based UNet Architecture for Degraded Document Image Binarization 23

学校读者我要写书评

暂无评论

TransDocUNet: A Transformer-based UNet Architecture for Degr...

Proceedings of the Fourteenth Indian Conference on computer vision, Graphics and Image Processing

作者： Risab Biswas Soumik Sarkhel Swalpa Kumar Roy Umapada Pal Artificial Intelligence Group Optiks Innovations Pvt. Ltd. (P360) India Department of Computer Science and Engineering Alipurduar Government Engineering and Management College India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

ISBN: (纸本)9798400716256

The enhancement of historical document images is critical for improving the quality and legibility of scanned or captured document images. Convolutional-based techniques previously generated competitive results for document image binarization, however, due to their inherent locality, these models are often limited in explicitly expressing long-range dependency. Transformers (ViT) have evolved as an alternative design with a global self-attention mechanism to tackle this issue, however, they can result in restricted localization capabilities due to a lack of low-level details. To address this problem, we propose TransDocUNet, a CNN-Transformer hybrid UNet architecture for document image binarization that merits both attention and convolution capabilities in a U-Net architecture and serves as a strong alternative to the existing solutions. The experimental results, obtained using the DIBCO/H-DIBCO datasets, highlight that our proposed method outperforms all the existing competing methods in terms of both objective quality metrics and visual quality assessment, achieving state-of-the-art performance in document image binarization. In addition, we undertake an ablation study to understand the role of dilation in the CNN to capture feature dependencies while reducing the computational cost as well. The findings helped us arrive at the final model and provide valuable insights into the importance of acquiring both global and local contextual information for tasks like enhancing document images.

关键词： Binarization CNN Deep Learning Document Image Enhancement TransUNet UNet vision Transformer

Neighbourhood-guided feature reconstruction for occluded person re-identification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yu, Shijie Chen, Dapeng Zhao, Rui Chen, Haobin Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition SIAT-SenseTime Joint Lab Shenzhen Institute of Advanced Technology Chinese Academy of Sciences University of Chinese Academy of Sciences China SenseTime Group Limited Shanghai AI Lab Shanghai China

Person images captured by surveillance cameras are often occluded by various obstacles, which lead to defective feature representation and harm person re-identification (Re-ID) performance. To tackle this challenge, we propose to reconstruct the feature representation of occluded parts by fully exploiting the information of its neighborhood in a gallery image set. Specifically, we first introduce a visible part-based feature by body mask for each person image. Then we identify its neighboring samples using the visible features and reconstruct the representation of the full body by an outlierremovable graph neural network with all the neighboring samples as input. Extensive experiments show that the proposed approach obtains significant improvements. In the large-scale Occluded- DukeMTMC benchmark, our approach achieves 64.2% mAP and 67.6% rank-1 accuracy which outperforms the state-of-the-art approaches by large margins, i.e.,20.4% and 12.5%, respectively, indicating the effectiveness of our method on occluded Re-ID problem. Copyright © 2021, The Authors. All rights reserved.

关键词： Security systems

Local jet pattern: A robust descriptor for texture classification

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Roy, Swalpa Kumar Chanda, Bhabatosh Chaudhuri, Bidyut B. Ghosh, Dipak Kumar Dubey, Shiv Ram Electronics and Communication Sciences Unit Indian Statistical Institute Kolkata700108 India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata700108 India Department of Electronics & Communication Engineering National Institute of Technology Rourkela Orissa769008 India Computer Vision Group Indian Institute of Information Technology Sri City Andhra Pradesh517646 India

Methods based on locally encoded image features have recently become popular for texture classification tasks, particularly in the existence of large intra-class variation due to changes in illumination, scale, and viewpoint. Inspired by the theories of image structure analysis, this work proposes an efficient, simple, yet robust descriptor namely local jet pattern (LJP) for texture classification. In this approach, a jet space representation of a texture image is computed from a set of derivatives of Gaussian (DtGs) filter responses up to second order, so-called local jet vectors (LJV), which also satisfy the Scale Space properties. The LJP is obtained by using the relation of center pixel with its' local neighborhoods in jet space. Finally, the feature vector of a texture image is formed by concatenating the histogram of LJP for all elements of LJV. All DtGs responses up to second order together preserves the intrinsic local image structure, and achieves invariance to scale, rotation, and reflection. This allows us to design a discriminative and robust framework for texture classification. Extensive experiments on five standard texture image databases, employing nearest subspace classifier (NSC), the proposed descriptor achieves 100%, 99.92%, 99.75%, 99.16%, and 99.65% accuracy for Outex_TC10, Outex_TC12, KTH-TIPS, Brodatz, CUReT, respectively, which are better compared to state-of-the-art methods. Copyright © 2017, The Authors. All rights reserved.

关键词： Textures

A feasibility study of on-board data compression for infrared cameras of space observatories

学校读者我要写书评

暂无评论

A feasibility study of on-board data compression for infrare...

International Conference on pattern recognition

作者： C. Reimers A.N. Belbachir H. Bischof R. Ottensamer D.A. Cesarsky H. Feuchtgruber F. Kerschbaum A. Poglitsch Institute of Astronomy University of Technology Vienna Vienna Austria Pattern Recognition and Image Procesing Group University of Technology Vienna Vienna Austria Institute of Computer Graphics and Vision Technical University of Graz Graz Austria Max-Planck Institute of Extraterrestrial Physics Garching Germany

In this paper, the feasibility of on-board data reduction/compression concept described in is evaluated for infrared images taken from space observatories. The method described in, which was initially designed and developed for the PACS (photodetector array camera and spectrometer) instrument, makes use of on-board integration to achieve higher compression ratio (CR) for applications with a modest telemetry rate. The evaluation of the reduction concept takes into account the visual performance (distortion) and the compression ratio. The distortion is assessed by calculating the reconstruction error using 4 metrics, namely, root mean square error (RMSE), signal-to-noise-ratio (SNR), peak-signal-to-noise-ratio (PSNR) and potential information loss (PIL). A quantitative evaluation of the on-board compression concept is performed on data from the infrared camera ISOCAM (infrared space observatory camera). We conclude with a short summary.

关键词： Data compression Cameras Observatories Image coding Infrared imaging Picture archiving and communication systems Photodetectors Spectroscopy Instruments Chromium

diffGrad: An optimization method for convolutional neural networks

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Dubey, Shiv Ram Chakraborty, Soumendu Roy, Swalpa Kumar Mukherjee, Snehasis Singh, Satish Kumar Chaudhuri, Bidyut Baran The Computer Vision Group Indian Institute of Information Technology Sri City Andhra Pradesh Chittoor517646 India The Indian Institute of Information Technology Uttar Pradesh Lucknow India The Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata700108 India Techno India University Sector V Salt Lake City Kolkata700091 India The Computer Vision and Biometrics Laboratory Indian Institute of Information Technology Allahabad211015 India

Stochastic Gradient Decent (SGD) is one of the core techniques behind the success of deep neural networks. The gradient provides information on the direction in which a function has the steepest rate of change. The main problem with basic SGD is to change by equal sized steps for all parameters, irrespective of gradient behavior. Hence, an efficient way of deep network optimization is to make adaptive step sizes for each parameter. Recently, several attempts have been made to improve gradient descent methods such as AdaGrad, AdaDelta, RMSProp and Adam. These methods rely on the square roots of exponential moving averages of squared past gradients. Thus, these methods do not take advantage of local change in gradients. In this paper, a novel optimizer is proposed based on the difference between the present and the immediate past gradient (i.e., diffGrad). In the proposed diffGrad optimization technique, the step size is adjusted for each parameter in such a way that it should have a larger step size for faster gradient changing parameters and a lower step size for lower gradient changing parameters. The convergence analysis is done using the regret bound approach of online learning framework. Rigorous analysis is made in this paper over three synthetic complex non-convex functions. The image categorization experiments are also conducted over the CIFAR10 and CIFAR100 datasets to observe the performance of diffGrad with respect to the state-of-the-art optimizers such as SGDM, AdaGrad, AdaDelta, RMSProp, AMSGrad, and Adam. The residual unit (ResNet) based Convolutional Neural Networks (CNN) architecture is used in the experiments. The experiments show that diffGrad outperforms other optimizers. Also, we show that diffGrad performs uniformly well for training CNN using different activation functions. The source code is made publicly available at https://***/shivram1987/diffGrad. Copyright © 2019, The Authors. All rights reserved.

关键词： Optimization

Motion Analysis of Endovascular Stent-Grafts by MDL Based Registration

学校读者我要写书评

暂无评论

Motion Analysis of Endovascular Stent-Grafts by MDL Based Re...

International Conference on computer vision (ICCV)

作者： Georg Langs Nikos Paragios Rene Donner Pascal Desgranges Alain Rahmouni Hicham Kobeiter GALEN Group Laboratoire de Mathématiques Appliquées aux Systàmes Ecole Centrale de Paris France Institute for Computer Graphics and Vision Graz University of Technology Austria Pattern Recognition and Image Processing Group University of Technology Vienna Austria University of Paris XII Paris France

The endovascular repair of a traumatic rupture of the thoracic aorta - that would otherwise lead to the death of the patient - is performed by delivering a stent-graft into the vessel at the rupture location. The age range of the affected patients is large and the stent-graft will stay in the body for the remaining life. The technique is relatively new, and no experience with regard to long-term effects, and durability exists. To predict long-term complications, such as ruptures or destructive interactions with surrounding tissue during the life of the patient, it is important to understand the - rather intense and constant - movement of the stent- graft during the cardiac cycle. A computed tomography with heart gating (gated CT) acquires sequences that show the region of the stent-graft at different time points. We analyze the motion of stent-grafts with a model based approach. Stent-grafts are represented as sparse sets of axis points extracted from the gated CT, and motion patterns are captured by a minimum description length based group-wise registration of the stent-graft at different time points. No parameterization or a priori definition of the topology is necessary, and highly variable elasticity properties in the data volume can by accounted for by the sparse statistical model, that captures correlations and motion components of the stent-graft. We report results for deformation models and registration accuracy for 5 patients.

关键词： Motion analysis Computed tomography Biomedical imaging Heart Buildings computer graphics pattern recognition Image processing Hospitals Data mining

Multiple domain experts collaborative learning: Multi-source domain generalization for person re-identification

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Yu, Shijie Zhu, Feng Chen, Dapeng Zhao, Rui Chen, Haobin Zhu, Jinguo Tang, Shixiang Qiao, Yu ShenZhen Key Lab of Computer Vision and Pattern Recognition Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences University of Chinese Academy of Sciences China SenseTime Group Limited Shanghai AI Lab Shanghai China Qing Yuan Research Institute Shanghai Jiao Tong University Shanghai China

Recent years have witnessed significant progress in person re-identification (ReID). However, current ReID approaches still suffer from considerable performance degradation when unseen testing domains exhibit different characteristics from the source training ones, known as the domain generalization problem. Given multiple source training domains, previous Domain Generalizable ReID (DG-ReID) methods usually learn all domains together using a shared network, which can't learn sufficient knowledge from each domain. In this paper, we propose a novel Multiple Domain Experts Collaborative Learning (MECL) framework for better exploiting all training domains, which benefits from the proposed Domain-Domain Collaborative Learning (DDCL) and Universal-Domain Collaborative Learning (UDCL). DDCL utilizes domain-specific experts for fully exploiting each domain, and prevents experts from over-fitting the corresponding domain using a meta-learning strategy. In UDCL, a universal expert supervises the learning of domain experts and continuously gathers knowledge from all domain experts. Note, only the universal expert will be used for inference. Extensive experiments on DG-ReID benchmarks demonstrate the effectiveness of DDCL and UDCL, and show that the whole MECL framework significantly outperforms state-of-the-arts. Experimental results on DG-classification benchmarks also reveal the great potential of applying MECL to other DG tasks. Code will be released. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning