检索结果-内蒙古大学图书馆

A novel line based connected component labeling algorithm

学校读者我要写书评

暂无评论

A novel line based connected component labeling algorithm

International Conference on Computer Science and Information Technology (CSIT)

作者： Yebin Fan Shengsheng Yu Hualong Zhao Department of Computer Science Huazhong University of Science and Technology Wuhan China National Key Laboratory of Science and Technology on Multi-spectral Information Processing Technologies Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan China

This paper presents a fast connected component labeling algorithm based on line description method and optimized tree Union-Find strategy. The algorithm transforms the pixel-connected issue, which most of proposed algorithms focus on, into line-connected issue. This algorithm is comprised of three phrases, line extraction, connected component identification and label assignment. The line description method transforms the connected pixels into line form for reducing the scan time. While the new tree Union-Find strategy diminishes the redundant root compare operations. A comparison analysis is performed with other optimized famous component labeling algorithms. Our algorithm has shown an outstanding performance with respect to the processing time, which achieves 1.1~8 times as fast as the other algorithms in various test cases.

关键词： Noise

FWLBP: A scale invariant descriptor for texture classification

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Roy, Swalpa Kumar Bhattacharya, Nilavra Chanda, Bhabatosh Chaudhuri, Bidyut B. Ghosh, Dipak Kumar Optical Character Recognition Laboratory Computer Vision and Pattern Recognition Unit Indian Statistical Institute Kolkata700108 India School of Information University of Texas AustinTX78712 United States Image Processing Laboratory Electronics and Communication Sciences Unit Indian Statistical Institute Kolkata700108 India Department of Electronics and Communication Engineering National Institute of Technology Rourkela Rourkela769008 India

In this paper we propose a novel texture descriptor called Fractal Weighted Local Binary pattern (FWLBP). The fractal dimension (FD) measure is relatively invariant to scale-changes, and presents a good correlation with human viewpoint of surface roughness. We have utilized this property to construct a scale-invariant descriptor. Here, the input image is sampled using an augmented form of the local binary pattern (LBP) over three different radii, and then used an indexing operation to assign FD weights to the collected samples. The final histogram of the descriptor has its features calculated using LBP, and its weights computed from the FD image. The proposed descriptor is scale invariant, and is also robust in rotation or reflection, and partially tolerant to noise and illumination changes. In addition, the local fractal dimension is relatively insensitive to the bi-Lipschitz transformations, whereas its extension is adequate to precisely discriminate the fundamental of texture primitives. Experiment results carried out on standard texture databases show that the proposed descriptor achieved better classification rates compared to the state-of-the-art descriptors. Copyright © 2018, The Authors. All rights reserved.

关键词： Fractal dimension

Oriented Gradient Maps based automatic asymmetric 3D-2D face recognition

学校读者我要写书评

暂无评论

Oriented Gradient Maps based automatic asymmetric 3D-2D face...

IAPR International Conference on Biometrics (ICB)

作者： Di Huang Mohsen Ardabilian Yunhong Wang Liming Chen CNRS Ecole Centrale de Lyon LIRIS UMR5205 Université de Lyon Lyon France Laboratory of Intelligent Recognition and Image Processing Beijing Key Laboratory of Digital Media School of Computer Science and Engineering Beihang University Beijing China

Recently, asymmetric 3D-2D face recognition has been paid increasing attention. It enrolls in textured 3D faces and performs identification using only 2D facial images, therefore it generally achieves a better result than 2D algorithms do, and avoids inconvenience of data acquisition and computation of 3D methods as well. In this paper, a biological vision-based facial representation, namely Oriented Gradient Maps (OGMs), is introduced for such an application. It simulates the response of complex neurons to gradient information within a pre-defined neighborhood, and thus can describe local texture changes of 2D faces and local geometry variations of 3D faces at the same time. Due to its property of being highly distinctive, these OGMs improve accuracies of both matching steps of asymmetric face recognition, i.e. (1) 3D-2D matching using Canonical Correlation Analysis (CCA); (2) 2D-2D matching using LBP histogram based features and Sparse Representation Classifier (SRC). Some comparative experiments are carried out on the complete FRGC v2.0 database, and the achieved results clearly highlight the effectiveness of the biological vision-based facial description and its successful application to asymmetric face recognition.

关键词： Face Face recognition Principal component analysis Three dimensional displays Histograms Neurons Probes

TOWARDS CODABLE WATERMARKING FOR INJECTING MULTI-BITS INFORMATION TO LLMS

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Lean Yang, Wenkai Chen, Deli Zhou, Hao Lin, Yankai Meng, Fandong Zhou, Jie Sun, Xu National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China Gaoling School of Artificial Intelligence Renmin University of China China Pattern Recognition Center WeChat AI Tencent Inc. China DeepSeek AI

As large language models (LLMs) generate texts with increasing fluency and realism, there is a growing need to identify the source of texts to prevent the abuse of LLMs. Text watermarking techniques have proven reliable in distinguishing whether a text is generated by LLMs by injecting hidden patterns. However, we argue that existing LLM watermarking methods are encoding-inefficient and cannot flexibly meet the diverse information encoding needs (such as encoding model version, generation time, user id, etc.). In this work, we conduct the first systematic study on the topic of Codable Text Watermarking for LLMs (CTWL) that allows text watermarks to carry multi-bit customizable information. First of all, we study the taxonomy of LLM watermarking technologies and give a mathematical formulation for CTWL. Additionally, we provide a comprehensive evaluation system for CTWL: (1) watermarking success rate, (2) robustness against various corruptions, (3) coding rate of payload information, (4) encoding and decoding efficiency, (5) impacts on the quality of the generated text. To meet the requirements of these non-Pareto-improving metrics, we follow the most prominent vocabulary partition-based watermarking direction, and devise an advanced CTWL method named Balance-Marking. The core idea of our method is to use a proxy language model to split the vocabulary into probability-balanced parts, thereby effectively maintaining the quality of the watermarked text. Extensive experimental results show that our method outperforms the baseline under comprehensive evaluation. Our code is available at https://***/lancopku/codable-watermarking-for-llm. © 2023, CC BY.

关键词： Signal encoding

-labeling for brick product graphs

学校读者我要写书评

暂无评论

Journal of Combinatorial Optimization 2014年第2期31卷 447-462页

作者： Shao, Zehui Xu, Jin Yeh, Roger K. School of Information Science and Technology Chengdu University Chengdu China Key Laboratory of Pattern Recognition and Intelligent Information Processing Institutions of Higher Education of Sichuan Province Chengdu China School of Electronic Engineering and Computer Science Peking University Beijing China Department of Applied Mathematics Feng Chia University Taichung Taiwan

Let $$G=(V, E)$$ be a graph. Denote $$d_G(u, v)$$ the distance between two vertices $$u$$ and $$v$$ in $$G$$ . An $$L(2, 1)$$ -labeling of $$G$$ is a function $$f: V \rightarrow \{0,1,\cdots \}$$ such that for any two vertices $$u$$ and $$v$$ , $$|f(u)-f(v)| \ge 2$$ if $$d_G(u, v) = 1$$ and $$|f(u)-f(v)| \ge 1$$ if $$d_G(u, v) = 2$$ . The span of $$f$$ is the difference between the largest and the smallest number in $$f(V)$$ . The $$\lambda $$ -number of $$G$$ , denoted $$\lambda (G)$$ , is the minimum span over all $$L(2,1 )$$ -labelings of $$G$$ . In this article, we confirm Conjecture 6.1 stated in X. Li et al. (J Comb Optim 25:716–736, 2013) in the case when (i) $$\ell $$ is even, or (ii) $$\ell \ge 5$$ is odd and $$0 \le r \le 8$$ .

关键词：

3D EAGAN: 3D edge-aware attention generative adversarial network for prostate segmentation in transrectal ultrasound images

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Mengqing Shao, Xiao Jiang, Liping Wu, Kaizhi School of Information Engineering Nanchang Hangkong University Jiangxi Nanchang China School of Computer Science Nanjing University of Information Science and Technology Jiangsu Nanjing China The First Affiliated Hospital of Nanchang University Nanchang University Jiangxi Nanchang China Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang China

Background: Segment prostates from transrectal ultrasound (TRUS) images plays an essential role in the diagnosis and treatment of prostate cancer. However, traditional segmentation methods are time-consuming and laborious. To address this issue, there is an urgent need to develop computer algorithms that can automatically segment prostates from TRUS images, which makes it become the direction and form of future development. Purpose: Automatic prostate segmentation in TRUS images has always been a challenging problem, since prostates in TRUS images have ambiguous boundaries and inhomogeneous intensity distribution. Although many prostate segmentation methods have been proposed, they still need to be improved due to the lack of sensibility to edge information. Consequently, the objective of this study is to devise a highly effective prostate segmentation method that overcomes these limitations and achieves accurate segmentation of prostates in TRUS images. Methods: A 3D edge-aware attention generative adversarial network (3D EAGAN)-based prostate segmentation method is proposed in this paper, which consists of an edge-aware segmentation network (EASNet) that performs the prostate segmentation and a discriminator network that distinguishes predicted prostates from real prostates. The proposed EASNet is composed of an encoder-decoder-based U-Net backbone network, a detail compensation module, four 3D spatial and channel attention modules, an edge enhance module, and a global feature extractor. The detail compensation module is proposed to compensate for the loss of detailed information caused by the down-sampling process of the encoder. The features of the detail compensation module are selectively enhanced by the 3D spatial and channel attention module. Furthermore, an edge enhance module is proposed to guide shallow layers in the EASNet to focus on contour and edge information in prostates. Finally, features from shallow layers and hierarchical features from the decod

关键词： Generative adversarial networks

Novel low power supply DC-coupled 1.25 Gb/s laser diode driver

学校读者我要写书评

暂无评论

Guti Dianzixue Yanjiu Yu Jinzhan/Research and Progress of Solid State Electronics 2006年第4期26卷 498-503页

作者： Fu, Shengmeng Chen, Zhaoyang Institute for Pattern Recognition and Artificial Intelligence Huazhong University of Science and Technology Wuhan 430074 China Key Laboratory for Image Information Processing and Intelligent Control Huazhong University of Science and Technology Wuhan 430074 China

Since the DC-coupled interface between the driver and the laser diode makes it impossible for the conventional drivers to work with low power supply, an output stage has been proposed. A novel APC can suppress the output average optical power and extinction ratio within ±0.3 dBm and ±0.4 dB(-40°C to 100°C), respectively. The initialization time is not more than 0.6 μs because the fast binary search algorithm is incorporated into the APC. The burst-on delay and burst-off delay are less than 5 ns and meet the requirement of PON system. The chip is fabricated in TSMC 0.8 μm BiCMOS process and occupies an area of 1.56 mm × 1.67 mm with a power consumption of 105 mW.

关键词： Diodes

Efficient spatialtemporal context modeling for action recognition?

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Cao, Congqi Lu, Yue Zhang, Yifan Jiang, Dongmei Zhang, Yanning Natl. Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Shaanxi Provincial Key Lab on Speech and Image Information Processing School of Computer Science Northwestern Poly-technical University Xi'an710129 China National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Beijing100190 China

Contextual information plays an important role in action recognition. Local operations have difficulty to model the relation between two elements with a long-distance interval. However, directly modeling the contextual information between any two points brings huge cost in computation and memory, especially for action recognition, where there is an additional temporal dimension. Inspired from 2D criss-cross attention used in segmentation task, we propose a recurrent 3D criss-cross attention (RCCA-3D) module to model the dense long-range spatiotemporal contextual information in video for action recognition. The global context is factorized into sparse relation maps. We model the relationship between points in the same line along the direction of horizon, vertical and depth at each time, which forms a 3D criss-cross structure, and duplicate the same operation with recurrent mechanism to transmit the relation between points in a line to a plane finally to the whole spatiotemporal space. Compared with the non-local method, the proposed RCCA-3D module reduces the number of parameters and FLOPs by 25% and 30% for video context modeling. We evaluate the performance of RCCA-3D with two latest action recognition networks on three datasets and make a thorough analysis of the architecture, obtaining the optimal way to factorize and fuse the relation maps. Comparisons with other state-of-the-art methods demonstrate the effectiveness and efficiency of our model. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

Epileptic EEG signal classification with marching pursuit based on harmony search method

学校读者我要写书评

暂无评论

Epileptic EEG signal classification with marching pursuit ba...

IEEE International Conference on Systems, Man and Cybernetics

作者： Ping Guo Jing Wang X. Z. Gao Jarno M. A. Tanskanen Laboratory of Image Processing and Pattern Recognition Beijing Normal University Beijing China School of Foundational Education Peking University Health Science Center China Department of Automation and Systems Technology Aalto University School of Electrical Engineering Finland Department of Biomedical Engineering Tampere University of Technology Finland

In Epilepsy EEG signal classification, the main time-frequency features can be extracted by using sparse representation with marching pursuit (MP) algorithm. However, the computational burden is so heavy that it is almost impossible to apply MP to real time signal processing. To reduce complexity of sparse representation, we propose to adopt harmony search method in searching the best atoms. Because harmony search method can find the best atoms in continuous time-frequency dictionary, the performance of epilepsy EEG signal classification is enhanced. The validity of this method is proved by experimental results.

关键词： Feature extraction Electroencephalography Dictionaries Classification algorithms Training Matching pursuit algorithms Accuracy