2017 4th IAPR Asian Conference on Pattern Recognition (ACPR)最新文献_第6页

Multi-task Deep Learning for Fast Online Multiple Object Tracking 快速在线多目标跟踪的多任务深度学习

2017 4th IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2017-11-01 DOI: 10.1109/ACPR.2017.58

Yuqi Zhang, Yongzhen Huang, Liang Wang

引用次数: 8

An Integrated LSTM Prediction Method Based on Multi-scale Trajectory Space 基于多尺度轨迹空间的综合LSTM预测方法

2017 4th IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2017-11-01 DOI: 10.1109/ACPR.2017.19

Ming He, Gongda Qiu, Jian Shen, Yuting Cao, Chamath Dilshan Gunasekara

引用次数: 0

General-to-Specialized Analysis Based on Deep Belief Network 基于深度信念网络的通用性分析

2017 4th IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2017-11-01 DOI: 10.1109/ACPR.2017.116

Renjie Hu, Lianghua He, Yuqin Wang, D. Hu

{"title":"General-to-Specialized Analysis Based on Deep Belief Network","authors":"Renjie Hu, Lianghua He, Yuqin Wang, D. Hu","doi":"10.1109/ACPR.2017.116","DOIUrl":"https://doi.org/10.1109/ACPR.2017.116","url":null,"abstract":"Recently, the deep neural network has achieved great performance in many areas. During analysis, all learned features are used at once, some of which could bring negative affect to specific classes. Recently, cognitive studies show that a human visual cognition process is hierarchical and dynamic, i.e., when meeting different targets, human brain intends to pay attention to different parts. Therefore, in this paper, we introduce this kind of mechanism into deep belief network (DBN) and propose a new general-to-specialized algorithm. Firstly, hierarchical knowledge networks are constructed based on the original learned DBN through pruning and retraining. Because these networks are learned for different discriminate ability, we call them as the general network and the specialized network separately. Secondly, a general-to-specialized analysis method is proposed which is proved theoretically. When predicting the class of an input sample, we select the corresponding specialized networks according to the preliminary analysis result and then make in-depth analysis. Experiments on four benchmark datasets are performed to test the proposed algorithm. The results show that our algorithm is feasible, valid and robust.","PeriodicalId":426561,"journal":{"name":"2017 4th IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130410016","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Fabric Defect Detection Algorithm Based on Convolution Neural Network and Low-Rank Representation 基于卷积神经网络和低秩表示的织物缺陷检测算法

2017 4th IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2017-11-01 DOI: 10.1109/ACPR.2017.34

Zhoufeng Liu, Baorui Wang, Chunlei Li, Bicao Li, Xianghui Liu

引用次数: 5

Real-Time Traffic Sign Classification Using Combined Convolutional Neural Networks 基于组合卷积神经网络的实时交通标志分类

2017 4th IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2017-11-01 DOI: 10.1109/ACPR.2017.12

Lingying Chen, Guanghui Zhao, Junwei Zhou, Li Kuang

{"title":"Real-Time Traffic Sign Classification Using Combined Convolutional Neural Networks","authors":"Lingying Chen, Guanghui Zhao, Junwei Zhou, Li Kuang","doi":"10.1109/ACPR.2017.12","DOIUrl":"https://doi.org/10.1109/ACPR.2017.12","url":null,"abstract":"The traffic sign recognition system inside the vehicle plays an important role and could guarantee the safety of human life on the road since it feedbacks road information to the driver in time. Benefited from learning features of the traffic sign, the convolutional neural network (CNN) has been widely used in traffic sign recognition with a high accuracy. However, the different kinds of traffic signs appear to distinctive features. A deep and high complexity neural network with a larger number of parameters is usually required to adapt the distinctive features, while it tends to be time-consuming and can not meet real-time requirement. In this paper, we firstly divide traffic signs into hierarchal structure according to the types of features, and then use a combined CNNs (CCNN) to adapt the hierarchical traffic signs, where the probabilities of superclass and subclass the sign belongs to are calculated using two CNNs with a simple network. Finally, classifying of the sign can be achieved by the weighted output of the two CNNs, and a low complexity sign recognition system could be obtained. Simulation results on the GTSRB database show that the proposed method achieves comparable accuracy and less time-consuming to the state-of-the-art methods.","PeriodicalId":426561,"journal":{"name":"2017 4th IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129123271","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 9

Integrating Bidirectional LSTM with Inception for Text Classification 集成双向LSTM和Inception的文本分类

2017 4th IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2017-11-01 DOI: 10.1109/ACPR.2017.113

Wei Jiang, Zhong Jin

引用次数: 5

Fingerprint Indexing Based on Minutia-Centred Deep Convolutional Features 基于细节中心深度卷积特征的指纹索引

2017 4th IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2017-11-01 DOI: 10.1109/ACPR.2017.18

Dehua Song, Yao Tang, Jufu Feng

引用次数: 5

Deep Convolutional Neural Network Based Hidden Markov Model for Offline Handwritten Chinese Text Recognition 基于深度卷积神经网络的隐马尔可夫模型离线手写中文文本识别

2017 4th IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2017-11-01 DOI: 10.1109/ACPR.2017.65

Zirui Wang, Jun Du, Jinshui Hu, Yulong Hu

{"title":"Deep Convolutional Neural Network Based Hidden Markov Model for Offline Handwritten Chinese Text Recognition","authors":"Zirui Wang, Jun Du, Jinshui Hu, Yulong Hu","doi":"10.1109/ACPR.2017.65","DOIUrl":"https://doi.org/10.1109/ACPR.2017.65","url":null,"abstract":"Recently, an effective segmentation-free approach via deep neural network based hidden Markov model (DNN-HMM) was proposed and successfully applied to offline handwritten Chinese text recognition. In this study, to further improve the modeling capability, we adopt deep convolutional neural networks (DCNN) to calculate the HMM state posteriors. First, on the frame basis, the DCNN-HMM can automatically learn the features from the raw image of the handwritten text line via the convolutional architecture rather than the handcrafted gradient features using in the DNN-HMM. Second, we examine several important factors of DCNN to the recognition performance, namely the kernel size, the number of blocks and convolutional layers. We also improve the language modeling by using more text data and high-order N-gram. Tested on ICDAR 2013 competition task of CASIA-HWDB database, the proposed DCNN-HMM could achieve a character error rate (CER) of 4.07%, yielding a relative CER reduction of 30.8% over the DNN-HMM approach. To the best of our knowledge, this is the best published result of the segmentation-free approaches. Furthermore, we explain why DCNN-HMM is more effective than DNN-HMM via the visualization of feature learning and the error pattern analysis.","PeriodicalId":426561,"journal":{"name":"2017 4th IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115368499","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Automatic Labanotation Generation from Motion-Captured Data Based on Hidden Markov Models 基于隐马尔可夫模型的运动捕获数据自动标记生成

2017 4th IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2017-11-01 DOI: 10.1109/ACPR.2017.55

Min Li, Z. Miao, Cong Ma

引用次数: 11

Classification of Depressive Disorder Based on RS-fMRI Using Multivariate Pattern Analysis with Multiple Features 基于RS-fMRI多特征多变量模式分析的抑郁症分类

2017 4th IAPR Asian Conference on Pattern Recognition (ACPR) Pub Date : 2017-11-01 DOI: 10.1109/ACPR.2017.29

Lishu Gu, Linlin Huang, Fei Yin, Yuqi Cheng

{"title":"Classification of Depressive Disorder Based on RS-fMRI Using Multivariate Pattern Analysis with Multiple Features","authors":"Lishu Gu, Linlin Huang, Fei Yin, Yuqi Cheng","doi":"10.1109/ACPR.2017.29","DOIUrl":"https://doi.org/10.1109/ACPR.2017.29","url":null,"abstract":"Resting-state functional Magnetic Resonance Image (RS-fMRI) can be very useful to discriminate depressive disorder (DD) from healthy controls (HCs) in terms of diagnosis objectivity. Due to the lack of biomarkers, high dimension features of RS-fMRI and the unobservable alterations reflecting in RS-fMRI, it is still a major clinical challenge. Multivariate pattern analysis (MVPA) can be an effective method in feature selection and evaluation, especially at individual level, which can help us find more reliable biomarkers of DD. In this paper, we employ MVPA to discriminate depressive disorder (DD) from healthy controls (HCs). Four basic feature selection algorithms were used in MVPA to compare the discriminative ability of five major features extracted from RS-fMRI to find better feature for finding reliable biomarkers. For improving the accuracy of classification of DD, a weighted voting classifier was applied to fuse classification results based on single feature. The experimental results demonstrate Regional Homogeneity (ReHo) showed best discriminative and generalization ability than other features and a significant improvement of classification accuracy that 90.22% of the subjects were correctly classified by leave-one-out cross-validation (LOOCV) via voting classifier compared to 81.52% the best accuracy of classification using single feature.","PeriodicalId":426561,"journal":{"name":"2017 4th IAPR Asian Conference on Pattern Recognition (ACPR)","volume":"8 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124357335","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5