Description: 本文的题目是基于分形和遗传算法的人脸识别方法，对有限人群提出一种采用分形特征和遗传聚类的识别方法: 将图像分成很多小区域, 分别计算各个区域的分形特征, 以充分利用图像二维信息 同一个模式有多个样本, 通过遗传算法进行聚类以得到最优解实现不变性识别. 最后采用ORL 人脸图像库的一组图像对比了新方法、本征脸法和自联想神经网络方法, 结果表明该方法的识别率, 与本征脸法相似, 比自联想神经网络高.-The title of this article is based on fractal and genetic algorithms for face recognition method, a crowd of limited use of fractal characteristics and the identification of genetic clustering methods: the image is divided into many small regions, each region were calculated fractal characteristics, to take full advantage of two-dimensional image information with a model for a number of samples, through the genetic clustering algorithm in order to obtain the optimal solution to achieve invariant recognition. Finally, using ORL face image database of a group of image contrast of the new methods, eigenface law and auto-associative neural network methods, results show that the method of recognition rate, with the eigenface method is similar to auto-associative neural network than high. Platform: |
Size: 380928 |
Author:阳关 |
Hits:
Description: High information redundancy and correlation in face images result in efficiencies when such images are used directly for recognition. In this paper, discrete cosine transforms are used to reduce image information redundancy because only a subset of the transform coefficients are necessary to preserve the most important facial features such as hair outline, eyes and mouth. We demonstrate experimentally that when DCT coefficients are fed into a backpropagation neural network for classification, a high recognition rate can be achieved by using a very small proportion of transform coefficients. This makes DCT-based face recognition much faster than other approaches.-High information redundancy and correlation in face images result in inefficiencies when such images are used directly for recognition. In this paper, discrete cosine transforms are used to reduce image information redundancy because only a subset of the transform coefficients are necessary to preserve the most important facial features such as hair outline, eyes and mouth. We demonstrate experimentally that when DCT coefficients are fed into a backpropagation neural network for classification, a high recognition rate can be achieved by using a very small proportion of transform coefficients. This makes DCT-based face recognition much faster than other approaches. Platform: |
Size: 25600 |
Author:mhm |
Hits:
Description: Wavelet transforms are used to reduce image information redundancy because only a subset of the transform coefficients are necessary to preserve the most important facial features such as hair outline, eyes and mouth. We demonstrate experimentally that when Wavelet coefficients are fed into a backpropagation neural network for classification, a high recognition rate can be achieved by using a very small proportion of transform coefficients. This makes Wavelet-based face recognition much more accurate than other approaches.
Platform: |
Size: 21504 |
Author:mhm |
Hits:
Description: 毕业设计中 用VC++写的基于神经网络的人脸识别程序 优秀毕业设计 可供毕业设计学生和相关研究人员参考-Graduation written using VC++ face recognition program based on neural network design for outstanding graduate students and graduate design research Reference Platform: |
Size: 3359744 |
Author:yaxuan |
Hits:
Description: The purpose of this work is to identify a given face image using main features of face. The dimensionality of face image is reduced by the Principal component analysis (PCA, using eigenfaces method) and the recognition is done by the Back propagation Neural Network (BPNN). Platform: |
Size: 3113984 |
Author:amine |
Hits:
Description: 基于BP神经网络的人脸识别系统的研究 采用的是PCA和BP网络-Based on BP neural network face recognition system using PCA and BP Neural Network Platform: |
Size: 221184 |
Author:张正峰 |
Hits:
Description: 基于BP神经网络的人脸识别算法的MALAB实现。采用了抽样-全样训练的方式。-BP neural network-based face recognition algorithm MALAB. Using a sample- the whole kind of training methods. Platform: |
Size: 8530944 |
Author:刘娇月 |
Hits:
Description: 人脸识别论文
An Efficient Method for Face Feature Extraction and
Recognition based on Contourlet Transform and Principal
Component Analysis using Neural Network -An Efficient Method for Face Feature Extraction and
Recognition based on Contourlet Transform and Principal
Component Analysis using Neural Network Platform: |
Size: 232448 |
Author:胡冲 |
Hits:
Description: 本课题研究的步骤如下：先提取人脸的特征向量；产生训练样本和测试样本；再用LVQ创建神经网络模型，该模型用训练样本进行训练调整权值；用测试样本对建立的人脸朝向识别模型进行验证，要求有较高的识别率。
本课题要求使用LVQ神经网络的算法进行Matlab仿真，对人脸朝向进行有效的判断和识别。
-This study is the following steps: first extract facial feature vector generate training and testing samples reuse create LVQ neural network model, which is trained using training samples to adjust the weights using the test sample towards the establishment of a human face recognition model validated requires a higher recognition rate. This topic requires the use of LVQ neural network algorithm Matlab simulation, the human face towards effective judgment and identification. Platform: |
Size: 132096 |
Author:吴军 |
Hits:
Description: 用神经网络进行人脸识别啊，效果特别好Face recognition using neural network, effect is very good-Face recognition using neural network, effect is very good Platform: |
Size: 5601280 |
Author:李波 |
Hits:
Search - face recognition using neural network