检索结果-内蒙古大学图书馆

AI WALKUP: A Computer-Vision Approach to Quantifying MDS-UPDRS in Parkinson's Disease

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xiang, Xiang Zhang, Zihan Ma, Jing Deng, Yao Key Lab of Image Processing and Intelligent Control Ministry of Education School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

Parkinson's Disease (PD) is the second most common neurodegenerative disorder. The existing assessment method for PD is usually the Movement Disorder Society - Unified Parkinson's Disease Rating Scale (MDS-UPDRS) to assess the severity of various types of motor symptoms and disease progression. However, manual assessment suffers from high subjectivity, lack of consistency, and high cost and low efficiency of manual communication. We want to use a computer vision based solution to capture human pose images based on a camera, reconstruct and perform motion analysis using algorithms, and extract the features of the amount of motion through feature engineering. The proposed approach can be deployed on different smartphones, and the video recording and artificial intelligence analysis can be done quickly and easily through our APP. Copyright © 2024, The Authors. All rights reserved.

关键词： Computer vision

Genetic U-Net: Automatically designed deep networks for retinal vessel segmentation using a genetic algorithm

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wei, Jiahong Fan, Zhun Department of Electronic Engineering Shantou University Guangdong515063 China Key Lab of Digital Signal and Image Processing of Guangdong Province Guangdong515063 China

Recently, many methods based on hand-designed convolutional neural networks (CNNs) have achieved promising results in automatic retinal vessel segmentation. However, these CNNs remain constrained in capturing retinal vessels in complex fundus images. To improve their segmentation performance, these CNNs tend to have many parameters, which may lead to overfitting and high computational complexity. Moreover, the manual design of competitive CNNs is time-consuming and requires extensive empirical knowledge. Herein, a novel automated design method, called Genetic U-Net, is proposed to generate a U-shaped CNN that can achieve better retinal vessel segmentation but with fewer architecture-based parameters, thereby addressing the above issues. First, we devised a condensed but flexible search space based on a U-shaped encoder-decoder. Then, we used an improved genetic algorithm to identify better-performing architectures in the search space and investigated the possibility of finding a superior network architecture with fewer parameters. The experimental results show that the architecture obtained using the proposed method offered a superior performance with less than 1% of the number of the original U-Net parameters in particular and with significantly fewer parameters than other state-of-the-art models. Furthermore, through in-depth investigation of the experimental results, several effective operations and patterns of networks to generate superior retinal vessel segmentations were identified. Copyright © 2020, The Authors. All rights reserved.

关键词： Genetic algorithms

A novel cross-lingual voice cloning approach with a few text-free samples

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Zhou, Xinyong Che, Hao Wang, Xiaorui Xie, Lei Shaanxi Provincial Key Lab of Speech and Image Information Processing School of Computer Science Northwestern Polytechnical University Xian China Kwai Beijing China

This paper proposes a novel cross-lingual voice cloning framework by utilizing bottleneck (BN) features obtained from speaker-independent automatic speech recognition system in the target language. Firstly, we use audio-text pairs of a single speaker in the target language to train a latent prosody model, which models the relationships between the text and the BN features. Then the acoustic model, which translates the BN features to the acoustic features, is trained with multi-speaker's audio data in the target language. Finally, the acoustic model is fine-tuned with target speaker's speech in the original language without the corresponding texts, as the BN features are served as the bridge. Our approach has the following advantages: 1) no recordings from bilingual speakers are required;2) audio-text pairs are not required for acoustic model training;3) no extra complicated modules are needed to encode speaker or language. Experimental results show that, with only several minutes of audio from a new English speaker, our proposed system can synthesize this speaker's Mandarin speech with decent naturalness and speaker similarity. Copyright © 2019, The Authors. All rights reserved.

关键词： Cloning

REMOTE SENSING image CLASSIFICATION BASED ON MULTIPLE MORPHOLOGICAL COMPONENT ANALYSIS

学校读者我要写书评

暂无评论

REMOTE SENSING IMAGE CLASSIFICATION BASED ON MULTIPLE MORPHO...

IEEE International Geoscience and Remote Sensing Symposium

作者： Xiang Xu Jun Li Mauro Dalla Mura Guangdong Key Laboratory for Urbanization and Geo-Simulation School of Geography and Planning Sun Yat-sen University GIPSA-Lab Department of Image and Signal Processing

ISBN: (纸本)9781479979301

In this work, we propose a new multiple morphological component analysis (MMCA) based decomposition framework for remote sensing image classification. The proposed MMCA framework aims at exploiting relevant textural characteristics present in a scene such as content, coarseness, contrast or directionality. Specifically, MMCA decomposes an image into a pair of morphological components (for each textural characteristic), which can be associated to a smooth and a textural components. The extracted features are then used for classification with a multinomial logistic regression (MLR). The experimental results, conducted using both a hyperspectral and a synthetic aperture radar (SAR) images, reveal that the proposed scheme can lead to state-of-the-art classification accuracy.

关键词： Remote sensing image classification Multiple morphological component analysis (MMCA) Textural features

Tiny noise, big mistakes: adversarial perturbations induce errors in brain–computer interface spellers

学校读者我要写书评

暂无评论

National Science Review 2021年第4期8卷 78-90页

作者： Xiao Zhang Dongrui Wu Lieyun Ding Hanbin Luo Chin-Teng Lin Tzyy-Ping Jung Ricardo Chavarriaga Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and AutomationHuazhong University of Science and Technology School of Civil Engineering and Mechanics Huazhong University of Science and Technology Centre of Artificial Intelligence Faculty of Engineering and Information Technology University of Technology Sydney Swartz Center for Computational Neuroscience Institute for Neural ComputationUniversity of California San Diego Center for Advanced Neurological Engineering Institute of Engineering in Medicine University of California San Diego ZHAW Data Lab Zürich University of Applied Sciences

An electroencephalogram(EEG)-based brain–computer interface(BCI) speller allows a user to input text to a computer by thought. It is particularly useful to severely disabled individuals, e.g. amyotrophic lateral sclerosis patients, who have no other effective means of communication with another person or a *** studies so far focused on making EEG-based BCI spellers faster and more reliable; however, few have considered their security. This study, for the first time, shows that P300 and steady-state visual evoked potential BCI spellers are very vulnerable, i.e. they can be severely attacked by adversarial perturbations,which are too tiny to be noticed when added to EEG signals, but can mislead the spellers to spell anything the attacker wants. The consequence could range from merely user frustration to severe misdiagnosis in clinical applications. We hope our research can attract more attention to the security of EEG-based BCI spellers, and more broadly, EEG-based BCIs, which has received little attention before.

关键词： electroencephalogram brain-computer interfaces BCI spellers adversarial examples

Push and Pull Search Embedded in an M2M Framework for Solving Constrained Multi-objective Optimization Problems

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Fan, Zhun Wang, Zhaojun Li, Wenji Yuan, Yutong You, Yugen Yang, Zhi Sun, Fuzan Ruan, Jie Li, Zhaocheng Department of Electronic Engineering Shantou University Guangdong China Key Lab of Digital Signal and Image Processing of Guangdong Province Shantou University Guangdong China

In dealing with constrained multi-objective optimization problems (CMOPs), a key issue of multi-objective evolutionary algorithms (MOEAs) is to balance the convergence and diversity of working populations. However, most state-of-the-art MOEAs show poor performance in balancing them, and can easily cause the working populations to concentrate on a part of regions of the Pareto fronts, leading to a serious imbalanced searching between preserving diversity and achieving convergence. This paper proposes a method which combines a multi-objective to multi-objective (M2M) approach with the push and pull search (PPS) framework, namely PPS-M2M. To be more specific, the proposed algorithm decomposes a CMOP into a set of simple CMOPs. Each simple CMOP corresponds to a sub-population and is solved in a collaborative manner. When dealing with constraints, each sub-population follows a procedure of "ignore the constraints in the push stage and consider the constraints in the pull stage", which helps each working sub-population get across infeasible regions. In order to evaluate the performance of the proposed PPS-M2M, it is compared with the other six algorithms, including M2M, MOEA/D-Epsilon, MOEA/D-SR, MOEA/D-CDP, C-MOEA/D and NSGA-II-CDP on a set of benchmark CMOPs. The experimental results show that the PPS-M2M is significantly better than the other six algorithms. Copyright © 2019, The Authors. All rights reserved.

关键词： Constraint handling

Modified radius-vector function for shape contour description

学校读者我要写书评

暂无评论

Modified radius-vector function for shape contour descriptio...

International Conference on Computational Science and its Applications, ICCSA 2004

作者： Kang, Sung Kwan Ahmad, Muhammad Bilal Chun, Jong Hun Kim, Pan Koo Park, Jong An Dept. of Information and Communications Engineering Chosun University Gwangju Korea Republic of Signal and Image Processing Lab Dept. of Mechatronics Kwangju Institute of Science and Technology Gwangju Korea Republic of Provincial College of Namdo Korea Republic of College of Electronics and Information Engineering Chosun University Gwangju Korea Republic of

ISBN: (纸本)3540220607

Shape is one of the salient features of visual content and can be used in visual information retrieval. Radius vector function for star-shaped objects is available. A modified radius-vector function for both types of shapes-star shaped, and non-star shaped is presented. The center of gravity is selected as the reference point. The corner points are marked as the nodes. Normalized vectors are calculated from the reference point to the corner nodes. The normalized vectors are arranged in ascending order, and the Euclidean distance of the query object with database objects is used for shape matching criteria. © Springer-Verlag Berlin Heidelberg 2004.

关键词： Vectors

Motion compensation optimization of H.264 decoder based on DSP hardware platform

学校读者我要写书评

暂无评论

Nanjing Youdian Daxue Xuebao (Ziran Kexue Ban)/Journal of Nanjing University of Posts and Telecommunications (Natural Science) 2007年第2期27卷 80-84页

作者： Gan, Zong-Liang Wang, Kai Zhu, Xiu-Chang Jiangsu Province Key Lab on Image Processing and Image Communication Nanjing University of Posts and Telecommunications Nanjing 210003 China

The H.264 video coding standard has a significant performance benefit versus former standards. However, motion compensation decoding process takes up a significant decoding time due to the advanced coding features. In this paper, the theory of motion compensation decoding in H.264 is given at first. Then the improved method is proposed by motion compensation fast decoding algorithm and optimization based on ADI Blackfin533 hardware platform. Both PC and ADI Blackfin533 experimental results show that the proposed optimization strategy can substantially improve the efficiency of real-time H.264 decoder.

关键词： Digital signal processor Direct memory access H.264 Motion compensation decoding

Wavelet-Energy-Weighted Local Binary Pattern Analysis for Tire Tread Pattern Classification

学校读者我要写书评

暂无评论

Wavelet-Energy-Weighted Local Binary Pattern Analysis for Ti...

International Conference on Imaging, Signal processing and Communication (ICISPC)

作者： Ying Liu Shuai Zhang Fuping Wang Kengpang Lim Qiqi Liu Yanbo Lei Yanchao Gong Jin Lu National Key Lab. of Electronic Information Processing for Applications in Crime Scene Investigation Ministry of Public Security China Center for Image and Information Processing Xi'an University of Posts and Telecommunications China

Tire tread pattern image classification plays an important role in crime scene and traffic accident investigation. Due to the lack of standard test dataset, there is little work done in this area. For efficient texture feature description, inherent characteristic of tire patterns need to be considered. Leveraging on the directionality characteristics of tread patterns, a novel texture feature extraction algorithm is proposed based on adaptive weighted feature fusion with the weights defined by sub-band energy ratio. The proposed approach consists of: (1) discrete wavelet decomposition of tire tread image to obtain low frequency, horizontal, vertical and diagonal sub-bands; (2) extraction of rotation-invariant uniform local binary pattern features from the sub-band images; (3) concatenating the tread pattern directional features, weighted by their corresponding sub-band energies. Applying SVM for tire tread pattern classification, experimental results on real-world tire tread patterns show that the proposed texture feature extraction algorithm is outperforms other prior methods.

关键词： Tires Feature extraction Discrete wavelet transforms Information processing Telecommunications image reconstruction Support vector machines