检索结果-内蒙古大学图书馆

IEEE International Conference on Video and Signal Based Surveillance 2006, AVSS 2006

作者： Wu, Qiang Zhang, Huaifeng Jia, Wenjing He, Xiangjian Yang, Jie Hintz, Tom Computer Vision Research Group University of Technology Sydney PO Box 123 Broadway NSW 2007 Australia Inst. of Image Process. and Pattern Recognition Shanghai Jiaotong Univ. China

ISBN: (纸本)0769526888

Car plate detection is a key component in automatic license plate recognition system. This paper adopts an enhanced cascaded tree style learner framework for car plate detection using the hybrid object features including the simple statistical features and Harr-like features. The statistical features are useful for simplifying the process on cascade classifier. The cascaded tree-style detector design will further reduce the false alarm and the false dismissal while retaining a high detection ratio. The experimental results obtained by the proposed algorithm exhibit the encouraging performance. © 2006 IEEE.

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

A cascaded genetic algorithm for efficient optimization and pattern matching 2nd

引用

2nd International Conference on Advances in pattern recognition, ICAPR 2001

作者： Garai, Gautam Computer Division Saha Institute of Nuclear Physics 1/AF Bidhannagar Calcutta700064 India Computer Vision and Pattern Recognition Unit Indian Statistical Institute 203 B. T. Road Calcutta700035 India

ISBN: (纸本)3540417672

A modified Genetic Algorithm (GA) based search strategy is presented here that is computationally more efficient than the conventional GA. Here the idea is to start a GA with the chromosomes of small length. Such chromosomes represent possible solutions with coarse resolution. A finite space around the position of solution in the first stage is subject to the GA at the second stage. Since this space is much smaller than the original search space, chromosomes of same length now represent finer resolution. In this way, the search progresses from coarse to fine solution in a cascaded manner. Since chromosomes of small size are used at each stage, the overall approach becomes computationally more efficient than a single stage algorithm with the same degree of final resolution. Also, since at the lower stage we work on low resolution, the algorithm can avoid local spurious extrema. The effectiveness of the proposed GA has been demonstrated for the optimization of some synthetic functions and on pattern recognition problems namely dot pattern matching and object matching with edge map. © Springer-Verlag Berlin Heidelberg 2001.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Robust recognition of 1-D barcodes using camera phones

Robust recognition of 1-D barcodes using camera phones

引用

International Conference on pattern recognition

作者： Steffen Wachenfeld Sebastian Terlunen Xiaoyi Jiang Computer Vision and Pattern Recognition Group Department ofComputer Science University of Munster Germany

In this paper we present an algorithm for the recognition of 1D barcodes using camera phones, which is highly robust regarding the the typical image distortions. We have created a database of barcode images, which covers typical distortions, such as inhomogeneous illumination, reflections, or blurriness due to camera movement. We present results from experiments with over 1,000 images from this database using a Matlab implementation of our algorithm, as well as experiments on the go, where a Symbian C++ implementation running on a camera phone is used to recognize barcodes in daily life situations. The proposed algorithm shows a close to 100% accuracy in real life situations and yields a very good resolution dependent performance on our database, ranging from 90.5% (640 × 480) up to 99.2% (2592 × 1944). The database is freely available for other researchers.

关键词： Robustness Cameras Image recognition pattern recognition Image databases Displays Lighting Optical reflection Morphological operations computer vision

来源：评论

学校读者我要写书评

暂无评论

New texture-spatial features for keyword spotting in video images 3

New texture-spatial features for keyword spotting in video i...

引用

3rd IAPR Asian Conference on pattern recognition, ACPR 2015

作者： Shivakumara, Palaiahnakote Liang, Guozhu Roy, Sangheeta Pal, Umapada Lu, Tong Faculty of Computer Science and Information Technology University of Malaya Kuala Lumpur Malaysia National Key Lab for Novel Software Technology Nanjing University Nanjing China Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

ISBN: (纸本)9781479961009

Keyword spotting in video document images is challenging due to low resolution and complex background of video images. We propose the combination of Texture-Spatial-Features (TSF) for keyword spotting in video images without recognizing them. First, a segmentation method extracts words from text lines in each video image. Then we propose the set of texture features for identifying text candidates in the word image with the help of k-means clustering. The proposed method finds proximity between text candidates to study the spatial arrangement of pixels that result in feature vectors for spotting words in the input frame. The proposed method is evaluated on word images of different fonts, contrasts, backgrounds and font sizes, which are chosen from standard databases such as ICDAR 2013 video and our video data. Experimental results show that the proposed method outperforms the existing method in terms of recall, precision and f-measure. © 2015 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Generalized Multimodal Fusion via Poisson-Nernst-Planck Equation

arXiv

引用

arXiv 2024年

作者： Xiong, Jiayu Wang, Jing Xiang, Hengjing Xue, Jun Xu, Chen Jiang, Zhouqiang Xiamen Key Lab of Computer Vision and Pattern Recognition Huaqiao University Xiamen China

Previous studies have highlighted significant advancements in multimodal fusion. Nevertheless, such methods often encounter challenges regarding the efficacy of feature extraction, data integrity, consistency of feature dimensions, and adaptability across various downstream tasks. This paper proposes a generalized multimodal fusion method (GMF) via the Poisson-Nernst-Planck (PNP) equation, which adeptly addresses the aforementioned issues. Theoretically, the optimization objective for traditional multimodal tasks is formulated and redefined by integrating information entropy and the flow of gradient backward step. Leveraging these theoretical insights, the PNP equation is applied to feature fusion, rethinking multimodal features through the framework of charged particles in physics and controlling their movement through dissociation, concentration, and reconstruction. Building on these theoretical foundations, GMF disassociated features which extracted by the unimodal feature extractor into modality-specific and modality-invariant subspaces, thereby reducing mutual information and subsequently lowering the entropy of downstream tasks. The identifiability of the feature’s origin enables our approach to function independently as a frontend, seamlessly integrated with a simple concatenation backend, or serve as a prerequisite for other modules. Experimental results on multiple downstream tasks show that the proposed GMF achieves performance close to the state-of-the-art (SOTA) accuracy while utilizing fewer parameters and computational resources. Furthermore, by integrating GMF with advanced fusion methods, we surpass the SOTA results. © 2024, CC BY-NC-SA.

关键词： Poisson equation

来源：评论

学校读者我要写书评

暂无评论

PON: Proposal Optimization Network for Temporal Action Proposal Generation 16th

PON: Proposal Optimization Network for Temporal Action Propo...

引用

16th International Conference on Intelligent Computing, ICIC 2020

作者： Peng, Xiaoxiao Du, Jixiang Zhang, Hongbo Department of Computer Science and Technology Huaqiao University Quanzhou China Fujian Key Laboratory of Big Data Intelligence and Security Huaqiao University Quanzhou China Xiamen Key Laboratory of Computer Vision and Pattern Recognition Huaqiao University Quanzhou China

ISBN: (纸本)9783030607951

Temporal action localization is a challenging task in video understanding. Although great progress has been made in temporal action localization, the most advanced methods still have the problem of sharp performance degradation when an action proposal generated. Most methods use sliding windows method or simply group frames according to frame-level scores. These methods are not enough to provide accurate action boundary and maintain reasonable temporal structure. In order to solve these problems, we propose a novel proposal optimization network to generate start score, end score, action score and regression score, and then remove the redundancy by NMS algorithm. In the proposed method, we introduce a metric loss function to maintain the temporal structure of action proposal in the training process. To verify the effectiveness of the proposed method, we have made comparative experiments on ActivityNet-1.3 dataset respectively, and the proposed method has surpassed some of the state-of-the-art methods on the dataset. © 2020, Springer Nature Switzerland AG.

关键词： Passive optical networks

来源：评论

学校读者我要写书评

暂无评论

Blind Image Inpainting via Omni-dimensional Gated Attention and Wavelet Queries

Blind Image Inpainting via Omni-dimensional Gated Attention ...

引用

IEEE computer Society Conference on computer vision and pattern recognition Workshops (CVPRW)

作者： Shruti S. Phutke Ashutosh Kulkarni Santosh Kumar Vipparthi Subrahmanyam Murala Computer Vision and Pattern Recognition Lab Indian Institute of Technology Ropar Rupnagar Punjab

Blind image inpainting is a crucial restoration task that does not demand additional mask information to restore the corrupted regions. Yet, it is a very less explored research area due to the difficulty in discriminating between corrupted and valid regions. There exist very few approaches for blind image inpainting which sometimes fail at producing plausible inpainted images. Since they follow a common practice of predicting the corrupted regions and then inpaint them. To skip the corrupted region prediction step and obtain better results, in this work, we propose a novel end-to-end architecture for blind image inpainting consisting of wavelet query multi-head attention transformer block and the omni-dimensional gated attention. The proposed wavelet query multi-head attention in the transformer block provides encoder features via processed wavelet coefficients as query to the multi-head attention. Further, the proposed omni-dimensional gated attention effectively provides all dimensional attentive features from the encoder to the respective decoder. Our proposed approach is compared numerically and visually with existing state-of-the-art methods for blind image inpainting on different standard datasets. The comparative and ablation studies prove the effectiveness of the proposed approach for blind image inpainting. The testing code is available at : https://***/shrutiphutke/Blind_Omni_Wav_Net

关键词：

来源：评论

学校读者我要写书评

暂无评论

ARNET: ACTIVE-REFERENCE NETWORK FOR FEW-SHOT IMAGE SEMANTIC SEGMENTATION

ARNET: ACTIVE-REFERENCE NETWORK FOR FEW-SHOT IMAGE SEMANTIC ...

引用

2021 IEEE International Conference on Multimedia and Expo, ICME 2021

作者： Shi, Guangchen Wu, Yirui Palaiahnakote, Shivakumara Pal, Umapada Lu, Tong College of Computer and Information Hohai University China Department of Computer System and Information Technology University of Malaya Malaysia Computer Vision and Pattern Recognition Unit Indian Statistical Institute India National Key Lab for Novel Software Technology Nanjing University China

ISBN: (纸本)9781665438643

To make predictions on unseen classes, few-shot segmentation becomes a research focus recently. However, most methods build on pixel-level annotation requiring quantity of manual work. Moreover, inherent information on same-category objects to guide segmentation could have large diversity in feature representation due to differences in size, appearance, layout, and so on. To tackle these problems, we present an active-reference network (ARNet) for few-shot segmentation. The proposed active-reference mechanism not only supports accurately co-occurrent objects in either support or query images, but also relaxes high constraint on pixel-level labeling, allowing for weakly boundary labeling. To extract more intrinsic feature representation, a category-modulation module (CMM) is further applied to fuse features extracted from multiple support images, thus forgetting useless and enhancing contributive information. Experiments on PASCAL-5i dataset show the proposed method achieves a m-IOU score of 56.5% for 1-shot and 59.8% for 5-shot segmentation, being 0.5% and 1.3% higher than current state-of-the-art method. © 2021 IEEE

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Off-line signature identification using background and foreground information

Off-line signature identification using background and foreg...

引用

2011 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2011

作者： Pal, Srikanta Alireza, Alaei Pal, Umapada Blumenstein, Michael School of Information and Communication Technology Griffith University Gold Coast QLD Australia Department of Studies in Computer Science University of Mysore Mysore 570 006 India Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata India

ISBN: (纸本)9780769545882

Biometric systems play an important role in the field of information security as they are extremely required for user authentication. Automatic signature recognition and verification is one of the biometric techniques, which is currently receiving renewed interest and is only one of several techniques used to verify the identities of individuals. Signatures provide a secure means for confirmation and authorization in legal documents. So nowadays, signature identification and verification becomes an essential component in automating the rapid processing of documents containing embedded signatures. In this paper, a technique for a bi-script off-line signature identification system is proposed. In the proposed signature identification system, the signatures of English and Bengali (Bangla) are considered for the identification process. Different features such as under sampled bitmaps, modified chain-code direction features and gradient features computed from both background and foreground components are employed for this purpose. Support Vector Machines (SVMs) and Nearest Neighbour (NN) techniques are considered as classifiers for signature identification in the proposed system. A database of 1554 English signatures and 1092 Bengali signatures are used to generate the experimental results. Various results based on different features are calculated and analysed. The highest accuracies of 99.41%, 98.45%;and 97.75% are obtained based on the modified chain-code direction, under-sampled bitmaps and gradient features respectively using 1800 (1100 English+700 Bengali) samples for training and 846 (454 English+392 Bengali) samples for testing. © 2011 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

A Global-to-Local Approach to Binarization of Degraded Document Images

A Global-to-Local Approach to Binarization of Degraded Docum...

引用

International Conference on pattern recognition

作者： Barun Biswas Ujjwal Bhattacharya Bidyut B. Chaudhuri Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata 108 India

ISBN: (纸本)9781479952106

This article deals with binarization of degraded document images. In the proposed approach, Canny edge image of the input degraded document image is obtained after blurring it with a Gaussian filter. Next, the gray values of the two pixels of the input image at the left and right of each edge pixel are noted to form a histogram of these gray values which possesses two distinct peaks and the lowest valley between them provides the global threshold value. Each pixel with gray value greater than the above threshold is turned as background pixel. A small square window is considered around each non-background pixel and certain simple statistics are computed on the gray values of the pixels of this small window based on which the said pixel is turned either background or foreground. Such a local thresholding method at the latter stage can efficiently handle various degradations in the document. The binarized image so obtained is finally subjected to certain common post-processing operations. The proposed method has been compared with a few existing binarization techniques.

关键词： Image edge detection Histograms Degradation Smoothing methods PSNR Image color analysis

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：