检索结果-内蒙古大学图书馆

A Face Detection Method Based on Skin Color Model and Improved adaboost algorithm

TRAITEMENT DU SIGNAL 2020年第6期37卷 929-937页

作者： Yang, Xiaoying Liang, Nannan Zhou, Wei Lu, Hongmei Suzhou Univ Sch Informat Engn Suzhou 234000 Peoples R China

This paper integrates skin color model and improved adaboost into a face detection method for high-resolution images with complex backgrounds. Firstly, the skin color areas were detected in a multi-color space. Each image was subject to adaptive brightness compensation, and converted into the YCbCr space, and a skin color model was established to solve face similarity. After eliminating the background interference by morphological method, the skin color areas were segmented to obtain the candidate face areas. Next, the inertia weight control factors and random search factor were introduced to optimize the global search ability of particle swami optimization (PSO). The improved PSO was adopted to optimize the initial connection weights and output thresholds of the neural network. After that, a strong adaboost classifier was designed based on optimized weak BPNN classifiers, and the weight distribution strategy of adaboost was further improved. Finally, the improved adaboost was employed to detect the final face areas among the candidate areas. Simulation results show that our face detection method achieved high detection rate at a fast speed, and lowered false detection rate and missed detection rate.

关键词： face detection image processing skin color model adaboost algorithm

来源：评论

学校读者我要写书评

暂无评论

Parameter Identification and Model Optimization of Cold Rolled Strip Based on GRA-AHP and adaboost-SA algorithm 24

Parameter Identification and Model Optimization of Cold Roll...

引用

2024 International Conference on Mathematics and Machine Learning, ICMML 2024

作者： Wang, Chuanxu Yan, Tingting Zhang, Yuchan Xue, Shenghe School of Mechanical Engineering Shenyang Jianzhu University Liaoning Shenyang China School of Science Shenyang Jianzhu University Liaoning Shenyang China School of Municipal and Environmental Engineering Shenyang Jianzhu University Liaoning Shenyang China

ISBN: (纸本)9798400711657

In this paper, Entropy Weight Method (EWM), Grey Relational Analysis method (GRA), and Analytic Hierarchy Process (AHP) are innovatively combined to construct a comprehensive evaluation system, namely GRA-AHP model. This model is used to quantify and identify the key parameters of mechanical properties of cold rolled strip steel. Aiming at the problem of hardness optimization in cold rolled strip production, this paper provides a method of combining polynomial fitting and integrated algorithm. Then an on-line monitoring model of strip hardness based on adaboost algorithm is established. The adaboost algorithm is incorporated into the detection regression model, and the expression of on-line monitoring of strip quality ensemble regression model is given. Through the analysis of feature importance, the prediction ability of the model is further optimized. The high precision and stability of the model are ensured. This paper aims to transform the research results into practical industrial applications, broaden the scope of application of the model, and improve its adaptability and efficiency under different production conditions. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： adaboost algorithm Analytic Hierarchy Process Entropy Weight Method Grey Relational Analysis Polynomial fitting and integrated algorithm

来源：评论

学校读者我要写书评

暂无评论

Face Detection Technology Based on Combining Skin Color Model with Improved adaboost algorithm 4

Face Detection Technology Based on Combining Skin Color Mode...

引用

4th IEEE International Conference on Signal and Image Processing (ICSIP)

作者： Li, Zhi-Zhen Zeng, Qing-Hua Li, Xiang-Dong Yang-Yu Nanjing Univ Aeronaut & Astronaut Sch Automat Nanjing Peoples R China Jiangsu Univ Technol Sch Elect & Informat Engn Changzhou Jiangsu Peoples R China

ISBN: (纸本)9781728136608

In order to improve the accuracy of face detection, this paper proposes a method based on combination of skin color model and improved adaboost algorithm. Using skin color model with YCbCr color space to detect the skin color, obtain the area to be detected, and then we can locate accurately the face position with the adaboost face detection algorithm. Because the traditional adaboost face detection algorithm needs a long time training and can not effectively distinguish feature values which are aggregated distribution, we have improved adaboost algorithm based on two-threshold and a new method about suppression of weights updating which which prevents excessive weight gain and avoids the phenomenon of degradation during training in adaboost.

关键词： face detection skin color model adaboost algorithm two-threshold suppression of weights updating

来源：评论

学校读者我要写书评

暂无评论

Mapping the risk of forest fires in Peru's Amazon and Andean forest regions using the adaboost algorithm and Geographic Information Systems 25

Mapping the risk of forest fires in Peru's Amazon and Andean...

引用

25th IEEE International Conference on Electronics, Electrical Engineering and Computing (INTERCON)

作者： Bax, Vincent Univ Ciencias & Humanidades Ctr Interdisciplinary Sci & Soc Studies Av Univ 5175 Lima Peru

ISBN: (纸本)9781538654903

The use of fires represents one of the principal methods to convert tropical forest ecosystems into other land-uses. To better target forest fire management and regulation policies, a better understanding of the areas prone to forest fires is needed. This study focuses on forest fires in the Peruvian Amazon and tropical Andes regions. First, the areas where forest fires are most prevalent are identified using Kernel Density Analysis. Second, the risk on fire within two forest fire hotspot locations is assessed using the adaboost algorithm. The results of this study show that forest fire is most extensive in the departments of Ucayali/Huanuco and San Martin. Furthermore, forest fire risk maps show that most of the highly to very highly susceptible areas in Ucayali/Huanuco are clustered within a single region, while in San Martin, susceptible areas are more widely scattered throughout the department. The fire risk maps generated in this study could contribute to forest fire management and research efforts in the Peruvian Amazon and tropical Andes regions.

关键词： Forest fires Geographic Information Systems adaboost algorithm

来源：评论

学校读者我要写书评

暂无评论

An Optimized Face Detection Based on adaboost algorithm

An Optimized Face Detection Based on Adaboost Algorithm

引用

International Conference on Information Systems and Computer Aided Education (ICISCAE)

作者： Zeng Hao Qin Feng Lin Kaidong Chongqing Univ Posts & Telecommun Sch Commun & Informat Engn Chongqing Peoples R China

ISBN: (纸本)9781538657386

In the real face detection, adaboost based algorithm usually has a higher false positive rate and loss rate. But it faces with the problem of long training time, susceptible to face deflection, obstruction and other factors. In view of the above problems, an improved face detection algorithm is proposed, which can reduce the training time and improve the training speed by using the feature processing, and the detection rate is improved by introducing the skin color detection based on YCgCr color space. Through experimental testing, the proposed algorithm can solve the occlusion, angle, light and other problems to a certain extent.

关键词： adaboost algorithm face detection feature processing skin color detection

来源：评论

学校读者我要写书评

暂无评论

Power Network Vulnerability Detection Based on Improved adaboost algorithm 4th

Power Network Vulnerability Detection Based on Improved Adab...

引用

4th International Conference on Cloud Computing and Security (ICCCS)

作者： Tao, Wenwei Liu, Song Su, Yang Hu, Chao CSG Power Dispatching Control Ctr Guangzhou 510670 Guangdong Peoples R China NARI Informat & Commun Technol Co Ltd Nanjing 210033 Jiangsu Peoples R China

ISBN: (纸本)9783030000127;9783030000110

The impact of the Internet on the power industry is increasing, the detection of power network vulnerability becomes more and more important. Traditional power network vulnerabilities detection methods are relatively labor-intensive and inefficient, so, the power network vulnerability detection algorithm based on improved adaboost is proposed in this paper. It is a kind of machine learning algorithm, which select C4.5 decision tree as weak classifier to integrate a strong classifier. Compared with neural network, KNN and other methods, the proposed algorithm is more efficient in power network vulnerability detection.

关键词： Machine learning Power network vulnerability detection adaboost algorithm

来源：评论

学校读者我要写书评

暂无评论

Eye Detection Based on Improved adaboost algorithm 6

Eye Detection Based on Improved AdaBoost Algorithm

引用

International Conference on Audio, Language and Image Processing (ICALIP)

作者： Li, Yang Shanghai Jianqiao Univ Coll Informat Technol Shanghai 201306 Peoples R China

ISBN: (纸本)9781538651957

Focused on the issue that the detection error rate of the current eye detection method is relatively high, and when the adaboost algorithm is used to train the classifier, it is easy to appear the phenomenon of weight imbalance. A new eye detection method based on the improved adaboost algorithm is proposed. First, the adaboost algorithm is applied to the detection of human eyes. Then the reason for the imbalance of weights in training of adaboost algorithm is analyzed, and the concept of missing detection rate is introduced to improve the weight updating process of adaboost algorithm. The experimental results show that the improved adaboost algorithm ensured the sample weight distribution balance and improve the accuracy in the training process;eye detection based on the improved adaboost algorithm effectively maintains a high detection rate and inhibits the detection error rate, makes detection more accurate.

关键词： eye detection adaboost algorithm cascade classifier Haar featur intergal image

来源：评论

学校读者我要写书评

暂无评论

Boosting scores fusion approach using Front-End Diversity and adaboost algorithm, for speaker verification

引用

COMPUTERS & ELECTRICAL ENGINEERING 2017年 62卷 648-662页

作者： Asbai, Nassim Amrouche, Abderrahmane USTHB Fac Elect & Comp Sci Speech Com & Signal Proc Lab Bab Ezzouar 16111 Algeria El Bachir El Ibrahimi Univ Bordj Bou Arreridj Algeria

A new speech feature extraction method called Mel Modified Group Delay coefficients (MMGDCs) is presented in this paper. In this method, the modified group delay spectrum detects the high formants frequencies, while the Mel filters select these desired formants in the high frequency regions. Also in this paper, a scores fusion approach is proposed between MMGDCs, Mel coefficients (MFCCs) and their extensions using the asymmetric tappers. The adaboost algorithm is used as strategy of this fusion. The performances evaluation of the proposed features and their extended variants are carried out on NIST 2000 corpus, and tested in both clean and simulated noisy conditions, using different noise categories extracted from the NOISEX-92 database. The obtained results show the superiority of the proposed MMGDCs against MFCCs in terms of error reduction, and the power of adaboost algorithm to make the fusion between MMGDCs and MFCCs better, especially under noisy environments. (C) 2017 Elsevier Ltd. All rights reserved.

关键词： Speaker verification Modified group delay spectra Mel filter MMGDCs MFCC adaboost algorithm Scores fusion Noisy conditions

来源：评论

学校读者我要写书评

暂无评论

Application of adaboost algorithm and Immune algorithm in Telecommunication Fraud Detection

Application of Adaboost Algorithm and Immune Algorithm in Te...

引用

2018 International Conference on Network, Communication, Computer Engineering (NCCE 2018)

作者： Bing Wu Mengtao Li Chunlai Zhou School of Communication University of China

ISBN: (纸本)9781510871076

Fraud detection is one of the biggest challenges facing the telecommunication industry now and,in the future,the fight against fraud and anti-fraud has also reached a new *** a time-sensitive fraud detection method is an important way for operators to solve this *** this article,to solve the low accuracy of the general algorithm,an adaptive improvement algorithm is *** common algorithms are combined and enhanced,which greatly improves the accuracy of the detection *** we take the artificial immune algorithm as an *** main application is combining machine learning and immune algorithm to apply to telecommunication fraud *** combination of the two is more conducive to pushing research on telecommunication fraud to a new stage for the future telecommunication industry.

关键词： adaboost algorithm Artificial immune algorithm Fraud detection

来源：评论

学校读者我要写书评

暂无评论

Multi-View Face Detection Based on Improved adaboost algorithm

Multi-View Face Detection Based on Improved Adaboost Algorit...

引用

2018 2nd International Conference on Computer Science and Intelligent Communication(CSIC 2018)

作者： Han Zishuo Wang Chunping Shijiazhuang Campus Army Engineering University

Aiming at the problem of the traditional adaboost algorithm with fast detection but low accuracy in multi-view face detection, a modified adaboost algorithm for face detection was proposed in this ***,in order to excluding the interference of most non-face regions, the whole image area is detected with skin color segmentation algorithm,then we use cascade structure classifier trained by adaboost algorithm which addes the extended Haar features to classify the human face candidate regions, thereby the human face can be posited. Experimental results show that the algorithm of this paper can not only effectively improve the human face detection rate and detection speed, but also reduce the false detection rate of multi-view face, in short, the algorithm has a good practical value.

关键词： Face Detection adaboost algorithm Skin Color Detection

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：