2015 IEEE 14th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)最新文献_第4页

A machine learning approach to detect occluded faces in unconstrained crowd scene 无约束人群场景中遮挡人脸的机器学习检测方法

2015 IEEE 14th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2015-07-06 DOI: 10.1109/ICCI-CC.2015.7259379

Shazia Gul, Humera Farooq

{"title":"A machine learning approach to detect occluded faces in unconstrained crowd scene","authors":"Shazia Gul, Humera Farooq","doi":"10.1109/ICCI-CC.2015.7259379","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2015.7259379","url":null,"abstract":"The face verification systems gained significant attention in the last few years due to the increased security concern in public and private places. Face detection is the most important and initial stage in the automatic face verification system. It helps to determine the existence of faces in an image and return the position and location of the face. The face verification system's accuracy depends on face detection. The human faces are not always frontal and have many variations, therefore, face detection is challenging in unconstrained scenarios. One main challenge of face detection is occlusion. The proposed work is an attempt to illustrate the cognitive informatics approach using machine learning and present an occluded face detection method. The proposed method uses Adaboost[1] machine learning approach. The Viola-Jones[2] algorithm along with free rectangular features[3] has been adopted in the proposed approach in order to detect faces. the machine learning methods require two operation namely training and testing. Two cascade classifiers are used in which one is trained on holistic faces and the second is trained on half occluded faces; both of the classifiers are used in parallel to work in unconfined scene. Additionally, for improvement the correctness and adeptness of the system, the skin color models are applied which are used for removing of the false positive detection. The experiment has been performed on FDDB[4] dataset. The results shows that the proposed method achieve desirable results in the detection of half occluded faces.","PeriodicalId":328695,"journal":{"name":"2015 IEEE 14th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123277526","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

Human activity recognition with HMM-DNN model 基于HMM-DNN模型的人类活动识别

2015 IEEE 14th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2015-07-06 DOI: 10.1109/ICCI-CC.2015.7259385

Licheng Zhang, Xihong Wu, D. Luo

{"title":"Human activity recognition with HMM-DNN model","authors":"Licheng Zhang, Xihong Wu, D. Luo","doi":"10.1109/ICCI-CC.2015.7259385","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2015.7259385","url":null,"abstract":"Activity recognition commonly made use of hidden Markov models (HMMs) to exploit temporal dependencies between activities. The emission distribution of HMMs could be represented by generative models, such as Gaussian mixture models (GMMs), or discriminative models, such as random forest (RF). These models, especially discriminative ones, needed to manually extract features from the sensor data, which relied on the experience of the researchers, and usually was a time-consuming task when complicated features are extracted. Furthermore, with these methods, the process of quantization of the sensor data, i.e., manual feature extraction, might lose much useful information and thus led to a performance debasement. In this paper, we recommend deep neural networks (DNNs) for modeling the emission distribution of HMMs, which automatically learn features suitable for classification from the raw sensor data and then estimate the posterior probabilities of the HMM states. We collected a dataset of daily activities and based on which experiments were performed to compare our HMM-DNN model with both HMM-GMM and HMM-RF. The results illustrated that HMM-DNN outperformed both HMM-GMM and HMM-RF.","PeriodicalId":328695,"journal":{"name":"2015 IEEE 14th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117291915","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: 41

The detection of under-eye bags on the facial image 面部图像上眼袋的检测

2015 IEEE 14th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2015-07-06 DOI: 10.1109/ICCI-CC.2015.7259405

Xiao Jiang, Yong Chai, Wei Xiong, Yi Zhao

{"title":"The detection of under-eye bags on the facial image","authors":"Xiao Jiang, Yong Chai, Wei Xiong, Yi Zhao","doi":"10.1109/ICCI-CC.2015.7259405","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2015.7259405","url":null,"abstract":"In this paper, we propose a novel approach to detect the under-eye bags on the human facial image. The existence and exacerbation of the under-eye bags is one of the significant marks of the facial aging. Once the under-eye bags appear, it not only plays an important impact on the human looks but also gives the impression of the emaciation and senescence. Our experiments and algorithms are based on the image gallery built on our own. The image gallery consists of 8132 facial images of 230 different males which are from different age. The decision of the presence of the under-eye bags in the image is made with the help of the experienced oculists. In the analysis of the facial images, we find several significant features of the under-eye bags in the captured images and design some effective methods to detect them. Base on the our reasonable detection methods, we have designed the under-eye bags classifier. Then we use the whole gallery to evaluate the performance of the classifier. The experiments show that the under-eye bags in the facial image can be well detected with a relatively high accuracy although both the forms of the under-eye bags and the illumination of the image acquisition condition are various.","PeriodicalId":328695,"journal":{"name":"2015 IEEE 14th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"9 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116928452","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

The study on associated knowledge flow using OWL based mechnism 基于OWL机制的关联知识流研究

2015 IEEE 14th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2015-07-06 DOI: 10.1109/ICCI-CC.2015.7259398

Zheng Xu, Shunxiang Zhang, Haiyan Chen

引用次数: 0

An improved multicarrier based waveform design for cognitive radio communication 基于多载波的认知无线电通信改进波形设计

2015 IEEE 14th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2015-07-06 DOI: 10.1109/ICCI-CC.2015.7259375

Meng Lin, Yunzhou Li, Limin Xiao, J. Wang, Xibin Xu

引用次数: 1

High precision uplink time and frequency calibration in cognitive space communications 认知空间通信中的高精度上行时频标定

2015 IEEE 14th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2015-07-06 DOI: 10.1109/ICCI-CC.2015.7259372

Menglu Wang, X. Chen, Wenyun Gao

引用次数: 3

Towards hierarchical fuzzy rule interpolation 面向层次模糊规则插值

2015 IEEE 14th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2015-07-06 DOI: 10.1109/ICCI-CC.2015.7259396

Shangzhu Jin, Jun Peng

{"title":"Towards hierarchical fuzzy rule interpolation","authors":"Shangzhu Jin, Jun Peng","doi":"10.1109/ICCI-CC.2015.7259396","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2015.7259396","url":null,"abstract":"Fuzzy rule interpolation offers a useful means for enhancing the robustness of fuzzy models by making inference possible in systems of only a sparse rule base. However in practical applications, as the application domain of fuzzy systems expand to more complex ones, the “curse of dimensionality” problem of the conventional fuzzy systems became apparent, which makes the already challenging tasks such as inference and interpolation even more difficult. An initial idea of hierarchical fuzzy interpolation is presented in this paper. The proposed approach combines hierarchical fuzzy systems and fuzzy rule interpolation, to overcome the “curse of dimensionality” problem and the sparse rule base problem simultaneously. Hierarchical fuzzy interpolation is applicable to situations where a multiple multi-antecedent rules system needs to be reconstructed to a multi-layer fuzzy system and the sub-layer rules base is sparse. This approach is based on fuzzy rule interpolative reasoning that utilities scale and move transformation. Illustrative example and experimental scenario are provided to demonstrate the potential of this approach.","PeriodicalId":328695,"journal":{"name":"2015 IEEE 14th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125620609","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: 6

Fine-grained Differential Harmony Search algorithm 细粒度差分和谐搜索算法

2015 IEEE 14th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2015-07-06 DOI: 10.1109/ICCI-CC.2015.7259366

Xiaoyu Lin, Yiwen Zhong, Yingxu Wang

引用次数: 0

A fast multi-objective differential evolutionary algorithm based on sorting of non-dominated solutions 基于非支配解排序的快速多目标差分进化算法

2015 IEEE 14th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2015-07-06 DOI: 10.1109/ICCI-CC.2015.7259386

Yulong Xu, Lingdong Zhao

引用次数: 1

Big Data tool integration in physical design process find hidden patterns, predictive analysis and classifying Big Data 大数据工具集成在物理设计过程中发现隐藏模式，预测分析和分类大数据

2015 IEEE 14th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC) Pub Date : 2015-07-06 DOI: 10.1109/ICCI-CC.2015.7259408

Waseem Ahmed, L. Fan

{"title":"Big Data tool integration in physical design process find hidden patterns, predictive analysis and classifying Big Data","authors":"Waseem Ahmed, L. Fan","doi":"10.1109/ICCI-CC.2015.7259408","DOIUrl":"https://doi.org/10.1109/ICCI-CC.2015.7259408","url":null,"abstract":"Physical Design (PD) Big Data tool is designed primarily to assist chip design engineers in achieving design optimization. It uses data mining techniques to handle the existing unstructured data repository. The tool extracts the relevant data and loads it into a well-structured database. It also has an archive mechanism that initially creates and then keeps updating an archive repository on a daily basis. The original input to the PD tool is a completely unstructured datasource which are read by the tool using regular expression based data extraction methodology. By doing this, PD tool converts the input data into the structured tables. This undergoes the data cleansing process before being fed into the operational DB. By maintaining an archive repository of this, PD tool also ensures data integrity and data validity. PD tool helps the design engineers to compare, correlate and inter-relate the results of their existing work with the ones done in the past which gives them a clear picture of the progress made and deviations that occurred. Data analysis can be done using various features offered by the tool such as graphical and statistical representation.","PeriodicalId":328695,"journal":{"name":"2015 IEEE 14th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114648535","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