检索结果-内蒙古大学图书馆

IEEE International Conference on Cloud computing and Intelligence Systems (CCIS)

作者： Xiaohua Wang Wei Huang Chao Jin Min Hu Fuji Ren School of Computer and Information Hefei University of Technology Anhui China Affective Computing and Advanced Intelligent Machines Anhui Key Laboratory The University of Tokushima Japan

ISBN: (纸本)9781467369541

In order to overcome the existing fruit recognition method only for single feature recognition which leads the problem of lower recognition rate, this paper proposes a recognition method based on multi-feature and multi-decision. Firstly, we preprocess the fruit image which is to be classified, separating foreground and background, and then we divide the target area. Secondly, in order to take full advantage of multi-independence and complementarity between features, we extract the color, shape and texture of fruits image and put these features into the BP neural network to classify. Finally, the results of different features are put into the decision-making mechanisms to obtain a final recognition result. The experiment results on object library and self-built library that is built by ourselves show that the method has good identification ability to fruit recognition and achieve the goal to identify different fruit.

关键词： machine vision Image recognition Image segmentation Image color analysis Shape Image resolution

来源：评论

学校读者我要写书评

暂无评论

Adaptive facial expression recognition method based on MBP and HMOG feature

Adaptive facial expression recognition method based on MBP a...

引用

IEEE International Conference on Cloud computing and Intelligence Systems (CCIS)

作者： Min Hu Xiaoyin Huang Xiaohua Wang Kun Li Fuji Ren Liangfeng Xu School of Computer and Information Hefei University of Technology Anhui China Affective Computing and Advanced Intelligent Machines Anhui Key Laboratory The University of Tokushima Japan

ISBN: (纸本)9781467369541

Because of the limitation of Monogenic waves' extraction from expression texture, this thesis proposes an adaptive facial expression feature fusion method based on MBP (monogenic binary pattern) and Histogram of HMOG (monogenic orientated gradients). To begin with our method, we get information of orientation, phase and magnitude component from filtered image by monogenic waves, besides, extract and fuse texture information from orientation and magnitude component to recognize facial expression. However single texture feature have some inadequacies for facial expression recognition. First of all, this paper describes a new kind of HMOG feature inspired by thoughts of HOG (histogram of oriented gradients) to indicate shape information of facial image. Secondly, acquiring best adaptive weights of expression block through information entropy. Finally, we classify the expression image using Nearest Neighbor to get the final result of effect of proposed method. In order to verify the efficiency of the methods above, we do a large number of experiments and it turns out our methods have great ability to explain expression feature.

关键词： Feature extraction Face Entropy Information filters Databases Computers

来源：评论

学校读者我要写书评

暂无评论

Age estimation and gender classification of facial images based on Local Directional Pattern

Age estimation and gender classification of facial images ba...

引用

IEEE International Conference on Cloud computing and Intelligence Systems (CCIS)

作者： Min Hu Yaona Zheng Fuji Ren He Jiang School of Computer and Information Hefei University of Technology Anhui China Affective Computing and Advanced Intelligent Machines Anhui Key Laboratory The University of Tokushima Japan

ISBN: (纸本)9781467369541

In order to improve shortage of Local Binary Pattern (LBP) algorithm in the field of facial feature extraction, this paper uses Local Directional Pattern (LDP) algorithm to extract the facial features about age estimation and gender classification. Because gradient information is more stable than gray information, LDP algorithm is not affected easily by noise. After preprocessing images, we use block strategy to represent facial features more fully. And then, we extract features of each block with LDP algorithm, storing the LDP histogram. Finally, we obtain age and gender identification results by Support Vector machine (SVM). Experimental results on FG-NET face database show that this method has a good effect on age estimation and gender classification.

关键词： Face Feature extraction Estimation Interference Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Face recognition based on adaptive weighting and fuzzy fusion with single training sample

Face recognition based on adaptive weighting and fuzzy fusio...

引用

IEEE International Conference on Cloud computing and Intelligence Systems (CCIS)

作者： Xiaohua Wang Chao Jin Wei Liu Min Hu Fuji Ren School of Computer and Information Hefei University of Technology Anhui China Affective Computing and Advanced Intelligent Machines Anhui Key Laboratory The University of Tokushima Japan

In order to solve the robustness issues for single training sample face recognition under occlusion conditions, this paper presents a recognition method based on adaptive weighting and fuzzy fusion. In our method, the information entropy expansion mode is introduced in sub-mode method and via adaptively assigning the weights corresponding to each sub-model can reduce the impact of occluded region. In addition, through summing the similar blocks in face images can make up for the defect of the sub-model which ignores the integrity of face. Finally, the method based on fuzzy comprehensive evaluation is utilized for decision-level fusion to the outputs by these two ways of classification. Experimental results on AR face database show that this method has state-of-the-art classification accuracy and also robustness to occlusion.

关键词： Robustness Testing

来源：评论

学校读者我要写书评

暂无评论

Dynamic facial expression recognition based on K-order emotional intensity model

Dynamic facial expression recognition based on K-order emoti...

引用

IEEE International Conference on Robotics and Biomimetics

作者： Changqin Quan Yao Qian Fuji Ren Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of Technology Hefei China P.R. The Japan Federation of Engineering Societies University of Tokushima Shinkura-cho Tokushima Japan

ISBN: (纸本)9781479973989

With the development of artificial intelligence and pattern recognition, facial expression recognition plays a more and more important role in intelligent human-computer interaction. In this paper, we present a model named K-order emotional intensity model (K-EIM) which is based on K-Means clustering. Different from other related works, the proposed approach can quantify emotional intensity in an unsupervised way. And then the output from K-EIM is encoded. The coding results are used for the dynamic facial expression recognition. The experiment is conducted on Cohn-Kanade facial expression database and the support vector machine classifier is used for facial expression classification. This method achieved a dynamic facial expression recognition accuracy of 88.32% which suggest that the proposed method shows better performance and proves its validity. Moreover, effect of different segments of emotional intensity is also discussed in the paper.

关键词： Face recognition Encoding Accuracy Emotion recognition Principal component analysis Training Feature extraction

来源：评论

学校读者我要写书评

暂无评论

On the α-universal multiple I restriction method for general fuzzy reasoning

On the α-universal multiple I restriction method for genera...

引用

IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

作者： Yiming Tang Xiaomei Li Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of Technology Hefei P. R. China School of Computer and Information Hefei University of Technology Hefei P. R. China

Based on the differently implicational idea, the a-universal multiple I restriction method is put forward for general fuzzy reasoning, which contains the a-multiple I restriction method as its specific case. First of all, we give the a-universal multiple I restriction principle, which improves the previous restriction principle, and then provide the existing condition of the solutions of the new method. Furthermore, we obtain the optimal solution of the new method for the fuzzy implications with residual pair, the R-implications, as well as some particular fuzzy implications. Finally, it is found that the new method is more reasonable by contrast with the a-multiple I restriction method.

关键词： Fuzzy reasoning Fuzzy systems Educational institutions Bismuth Conferences Abstracts Laboratories

来源：评论

学校读者我要写书评

暂无评论

Chinese Microblog Sentiment Classification Based on Deep Belief Nets with Extended Multi-Modality Features

Chinese Microblog Sentiment Classification Based on Deep Bel...

引用

IEEE International Conference on Data Mining Workshops (ICDM Workshops)

作者： Xiao Sun Chengcheng Li Wanyi Xu Fuji Ren Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of Technology Hefei China School of Information Science and Engineering Southeast University Shanghai China Faculty of Engineering University of Tokushima Tokushima Japan

ISBN: (纸本)9781479942732

This paper presents a DBN (deep belief nets) model and a multi-modality feature extraction method to extend features' dimensionalities of short text for Chinese micro blogging sentiment classification. Besides traditional features sets for document classification, comments for certain posts are also extracted as part of the micro blogging features according to the relationship between commenters and posters though constructing micro blogging social network as input information. Then, the integration of the above modality features is combined and represented as input vector for DBN. In this paper, a DBN model, which is stacked with several layers of RBM (Restricted Boltzmann machine), is implemented to initialize the structure of neural network. The RBM layers can take probability distribution samples of original data to learn hidden structures for better feature representation. A Class RBM (Classification RBM) layer, which is stacked on top of several RBM layers, is adapted to achieve the final sentiment classification. The results demonstrate that, with proper structure and parameter, the performance of the proposed deep learning method on sentiment classification is better than state of the art surface learning models such as SVM or NB, which proves that DBN is suitable for short-length document classification with the proposed feature dimensionality extension method.

关键词： Feature extraction Semantics Visualization Training Social network services Blogs Educational institutions

来源：评论

学校读者我要写书评

暂无评论

Face recognition based on double complementary space and multi-decision classification

Face recognition based on double complementary space and mul...

引用

IEEE International Conference on Cloud computing and Intelligence Systems (CCIS)

作者： Fuji Ren Yanqiu Li Liangfeng Xu Min Hu Xiaohua Wang School of Computer and Information Hefei University of Technology Anhui China Affective Computing and Advanced Intelligent Machines Anhui Key Laboratory Faculty of Engineering The University of Tokushima Tokushima Japan

ISBN: (纸本)9781467369541

In order to overcome the one-sidedness and limitations of a single subspace in feature extraction and classification, we propose a face recognition method that extracts features in double complementary space and utilize multi-decision for classification. In the feature extraction stage, we use ICA and LPE algorithm as the first layer in complementary space to extract global and local features of the face images. Then, for the purpose of solving the problem that features extracted by ICA are lack of classification information, we further extract classification information from the independent features extracted by ICA on the condition that the FLDA and DCV algorithm are used as the second layer in the complementary space. In the classification stage, the test samples are firstly projected to the independent subspace. After that, projected the samples which are difficult to identify to the LPE space and reclassified them. Finally, the results are been determined comprehensively. Experimental results on ORL database show that the proposed method can effectively improve the recognition rate.

关键词： Feature extraction Classification algorithms Face recognition Face Data mining Entropy Databases

来源：评论

学校读者我要写书评

暂无评论

Finding Emotional Focus for Emotion Recognition at Sentence Level

引用

电子学报(英文版) 2013年第1期22卷 99-103页

作者： QUAN Changqin REN Fuji Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine Hefei University of Technology Hefei 230009 China Faculty of Engineering The University of Tokushima Tokushima Japan

Emotion recognition at sentence level is one of the fundamental problems of textual emotion un- derstanding. Based on the observation that sentence emo- tional focus can be expressed by some clauses in this sen- tence, this paper proposes to find the emotional focus for sentence emotion recognition. For the sake of breaking through the problems brought about by depending on emo- tion lexicons, we first recognize word emotions in a sen- tence based on Maximum entropy model. And then homo- geneous Markov model is built for clause emotion recogni- tion; After that, a strategy based on emotion selection is proposed for a sentence with multiple clauses, and genetic algorithm is used for clause selection by textual feature weighting. The experimental results show that, comparing with the baseline, there are 9.1% and 3.6% improvement respectively for two different evaluations. It is demon- strated that finding emotional focus by clause selection is able to improve the performance of sentence emotion recognition significantly.

关键词：情感识别句子层面聚焦马尔可夫模型最大熵模型特征加权遗传算法

来源：评论

学校读者我要写书评

暂无评论

MINING THE IMPACT OF SOCIAL NEWS ON THE EMOTIONS OF USERS BASED ON DEEP MODEL

MINING THE IMPACT OF SOCIAL NEWS ON THE EMOTIONS OF USERS BA...

引用

2014 IEEE 3rd International Conference on Cloud computing and Intelligence Systems

作者： Xiao Sun Fei Gao Fuji Ren Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computer and InformationHefei University of Technology Faculty of Engineering University of Tokushima2-1 Minami-JosanjimaTokushima 770-8506Japan

ISBN: (纸本)9781467369541

In this paper,Deep Belief Nets(DBN) model and Support Vector machine(SVM) are used to mine the features hidden in social news,which can influence the emotions of *** feature selection methods for text modeling are used to build the input vectors of DBN,with the purpose of keeping the text information to the greatest *** take advantage of the deep features abstracted by DBN to build social news text *** the same time,three optimal models are used as inputs of SVM to train and classify the social *** get a conclusion that DBN not only reduces the dimension of original features,but also makes the abstracted features with more text information and shows better performance in determining the influence on people' s emotions by social news.

关键词： Deep Belief Network(DBN) Restricted Boltzmann machine(RBM) Impacts on Emotion Social News

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：