会议论文集名称:
2010 International Conference on Signal and Information Processing(2010年IEEE信号与信息处理国际会议 ICSIP2010)论文集
关键词:
agriculture water consumption;BP neural network;particle swarm optimization;forecast
摘要:
Forecasting agriculture water consumption is an important task in configuration of water resources. In order to forecast agriculture water consumption, this paper presents an improved BP neural network. The proposed approach employs a novel particle swarm algorithm for training weights in BP. Experimental results show that our proposed method IPSO-BP provides more accurate prediction ability than original BP algorithm and BP based on genetic algorithm (GA-BP).
期刊:
PROCEEDINGS OF THE 2010 INTERNATIONAL CONFERENCE ON WAVELET ANALYSIS AND PATTERN RECOGNITION,2010年:170-175
通讯作者:
Ning, Liangshuo
作者机构:
[Ning, Liangshuo] Hubei Univ, Fac Math & Comp Sci, Wuhan, Peoples R China.;[Ning, Liangshuo; Zhou, Long; You, Xinge] Wuhan Polytech Univ, Elect & Informat Engn Dept, Wuhan, Peoples R China.;[He, Zhengyu; You, Xinge; Du, Liang] Huazhong Univ Sci & Technol, Elect & Informat Engn Dept, Wuhan, Peoples R China.;[He, Zhengyu] Harbin Inst Technol, Shenzhen Grad Sch, Dept Comp Sci & Technol, Shenzhen, Peoples R China.
通讯机构:
[Ning, Liangshuo] H;Hubei Univ, Fac Math & Comp Sci, Wuhan, Peoples R China.
会议名称:
2010 International Conference on Wavelet Analysis and Pattern Recognition
会议时间:
JUL 11-14, 2010
会议地点:
Qingdao, PEOPLES R CHINA
会议主办单位:
[Ning, Liangshuo] Hubei Univ, Fac Math & Comp Sci, Wuhan, Peoples R China.^[Ning, Liangshuo;Zhou, Long;You, Xinge] Wuhan Polytech Univ, Elect & Informat Engn Dept, Wuhan, Peoples R China.^[You, Xinge;Du, Liang;He, Zhengyu] Huazhong Univ Sci & Technol, Elect & Informat Engn Dept, Wuhan, Peoples R China.^[He, Zhengyu] Harbin Inst Technol, Shenzhen Grad Sch, Dept Comp Sci & Technol, Shenzhen, Peoples R China.
会议论文集名称:
International Conference on Wavelet Analysis and Pattern Recognition
摘要:
Writer identification recently has been considerably studied due to its various applications in forensic and commercial sections. Because offline, text-independent writer identification has limited requirements in writing sample collection, it has wider applications and meanwhile more difficult to handle. By considering handwriting images as visually distinctive textures, we propose a new method for offline, text-independent writer identification based on multiscale version of Gaussian Markov Random Fields (GMRF) model. The handwriting features are extracted in wavelet domain of handwriting textures in which global texture feature (such as directional information) from handwriting can be detected. In addition, GMRF is investigated to capture different local spatial structures of graphemes (character-shape) written by different people. The experimental results demonstrate that the proposed method outperforms both 2-D Gabor model and wavelet-based GGD method.
摘要:
Writer identification is an important and active branch of biometrics, which means the methods for uniquely recognizing humans based upon their intrinsic physical or behavioral traits. In this paper, we propose one new method for off-line, text-independent writer identification by using the fractal dimension of wavelet subbands in Gabor domain of the handwriting images. In this method, the handwriting images are firstly decomposed into a series of Gabor subbands at different orientations and frequencies. Every Gabor subband is extended into one data sequence. Then, every sequence is decomposed into a series of wavelet subpatterns by wavelet transform. Afterwards, the mesh fractal dimensions of every wavelet subpattern are extracted as the feature for writer identification. Compared to the traditional Gabor method for off-line, text-independent writer identification, our method can extract more effective features to distinguish the handwritings, and hence achieve much better identification results.
作者机构:
[牟怿; 刘纯利] Engineering School, Anhui Science and Technology University, Fengyang 233100, Anhui, China;[周龙] Department of Electrical and Information Engineering, Wuhan Polytechnic University, Wuhan 430023, China
通讯机构:
Engineering School, Anhui Science and Technology University, China
作者机构:
[尤新革; 周龙] Department of Electrical and Information Engineering, Wuhan Polytechnic University, Wuhan 430023, China;[牟怿] School of Engineering, Anhui Science and Technology University, Fengyang 233100, Anhui, China
通讯机构:
Department of Electrical and Information Engineering, Wuhan Polytechnic University, China
摘要:
Images often contain noise due to the capturing devices, environment and even human errors. For the image further processing, compression, fractal and so on, the image denoising is necessary. Wavelet analysis plays a very important role in the image denoising. In this paper, we improve the wavelet thresholding method by using multi-scale thresholds and a new thresholding function. Also, in case of large noise, a median filter is suggested to be used at last. Based on Lipschitz exponent and wavelet transform, we theoretically give the multi-scale thresholds. In order to obtain a better denoising result, We also present a new thresholding function instead of the hard or soft thresholding function. Experiment results show that our improved method gives a higher PSNR and has less visual artifacts compared with other methods.
摘要:
This paper proposes a new feature of fingerprint, called corner-cue. It is based on the curvature of fingerprint ridges. To extract the corner-cue, we first compute the curvature of fingerprint ridges and find the local maximum curvature points. Without regard to the high curvature points near minutiae, corner-cues are obtained. Corner-cues are further utilized in the matching stage to enhance the system's performance. Since high curvature points are important features of a fingerprint, the proposed method can obtain better results than conventional solely minutiae-based methods. Experimental results illustrate its effectiveness.
期刊:
Proceedings - International Conference on Pattern Recognition,2010年:1489-1492 ISSN:1051-4651
通讯作者:
Peng, Q.
作者机构:
Department of Electronics and Information Engineering, Huazhong University of Science and Technology, Wuhan, China;Department of Electrical and Information Engineering, Wuhan Polytechnic University, Wuhan, China;Department of Computer Science, Hong Kong Baptist University, Hong Kong, Hong Kong
通讯机构:
Department of Electronics and Information Engineering, Huazhong University of Science and Technology, China
作者机构:
[牟怿; 周龙] Department of Electrical and Information Engineering, Wuhan Polytechnic University, Wuhan 430023, China;[黄凌霄] School of Mathematics and Computer Science, Ningxia University, Yinchuan 750021, China
通讯机构:
Department of Electrical and Information Engineering, Wuhan Polytechnic University, China
会议名称:
2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)
会议时间:
2008-07-12
会议地点:
昆明
会议论文集名称:
2008 International Conference on Machine Learning and Cybernetics(2008机器学习与控制论国际会议)论文集
关键词:
Image of pests in stored grain;Wavelet transform;Edge detection
摘要:
The detection method of pests in stored grain is always investigated. The method of based on image recognition is often discussed.The wavelet transform is the localization analysis of time and frequency, and it can multi-scale refine the signal by calculating of flex and transition. This paper presents a method of using the wavelet transform to detect the image of pests in stored grain edge based on the multi-scale analysis of the wavelet transform in the image processing field. The method acquires the information of the image edge by detecting the image local maxima of the two-dimension wavelet transform. The examples show that the method can obtain better edge detection.
作者机构:
[周龙] Department of Electrical and Information Engineering, Wuhan Polytechnic University, Wuhan 430023, China;[陈绵云] Department of Control Science and Information Engineering, Huazhong University of Science and Technology, Wuhan 430074, China
通讯机构:
Department of Electrical and Information Engineering, Wuhan Polytechnic University, China