A real time implementation of a pose invariant face recognition engine with a novel face segmentation algorithm

In this paper we propose a fast and efficient algorithm for segmenting a face suitable for recognition from a video sequence. We first obtain a coarse face region using skin color, then using dynamic template matching the face is efficiently segmented at varying scale and pose in real time. We have also developed and tested some heuristics which localizes only the face region, even when subjects are wearing skin color dress. The segmented face is then handed over to a recognition algorithm based on principal component analysis and linear discriminant analysis. The on-line face detection, segmentation and recognition algorithm takes an average of 0.06 sec on a 3.2 GHz P4 machine.     

Quaternion-based improved LPP method for color face recognition

In recent years, pattern recognition and computer vision have increasingly become the focus of research. Locality preserving projection (LPP) is a very important learning method in these two fields and has been widely used. Using LPP to perform face recognition, we usually can get a high accuracy. However, the face recognition application of LPP suffers from a number of problems and the small sample size is the most famous one. Moreover, though the face image is usually a color image, LPP cannot sufficiently exploit the color and we should first convert the color image into the gray image and then apply LPP to it. Transforming the color image into the gray image will cause a serious loss of image information. In this paper, we first use the quaternion to represent the color pixel. As a result, an original training or test sample can be denoted as a quaternion vector. Then we apply LPP to the quaternion vectors to perform feature extraction for the original training and test samples. The devised quaternion-based improved LPP method is presented in detail. Experimental results show that our method can get a higher classification accuracy than other methods.     

云计算环境下人脸表情智能识别改进技术研究

随着人脸识别技术的开发,对于如何提高人脸表情智能识别改进技术的研究也越来越多;如何提高人脸识别的准确度和完整度是当前发展的主要需要,而计算机云计算功能在人脸识别中的应用在一定程度上解决了此问题;通过改进细菌觅食算法,再将其应用到主要成分分析算法对图像基本特征进行提取分析;通过以上的算法输入计算机网络云储存当中,实现云计算技术在人脸识别中的应用;文章将通过对于算法部署函数的办法进行图片解析工作,并且利用智能人脸识别软件对图像进行抽丝、分类、匹配等工作进行功能状态进行测试;实验结果表明利用云计算技术通过连接网络云计算系统可以对目前的人脸识别以及分类做到更高的准确性和适应性。     

基于核独立成分分析的人脸识别

研究一种基于核独立成分分析的人脸识别方法。利用支持向量机的核函数思想,将原始人脸图像向量映射到高维特征空间,然后在高维特征空间中进行独立成分分析(ICA),提取非线性独立成分作为特征向量进行分类识别。实验结果表明该方法要比常规的基于ICA和PCA的人脸识别算法的识别率要高。     

一种自适应的Gabor图像特征抽取和权重选择的人脸识别方法

 为了克服光照、表情变化等因素对人脸识别的影响,本文提出了一种自适应的Gabor图像特征抽取和权重选择的人脸识别方法.该方法首先把每幅人脸图像经过Gabor小波变换后得到的40个不同尺度和方向下的图像都看作是独立的样本,再把不同人脸中的同一尺度和方向的变换结果进行特征重组,得到40个独立地新特征矩阵.为了增强对光照、表情变化的鲁棒性,每一新特征矩阵的识别贡献被本文所提出的自适应权重方法计算得到.其次,对每一新特征矩阵采用离散余弦变化进行降维,并采用了鉴别力量分析方法来选取最有鉴别力的离散余弦变换系数作为特征向量.最后,抽取线性鉴别分析特征进行识别.大量的实验证明了本文所提方法的有效性.     

基于多变量鉴别分析的光学畸变不变性图像识别

提出一种基于鉴别分析的光学畸变不变性图像识别方法：对包含各种畸变的训练图像集采用主成分分析得到若干本征图像,作为参考模式与测试图像做光学相关,利用本民输入图像的相关结果作为识别特征,采用最佳鉴别分析做了训练和识别,即可实现对输入图像的畸变为性快速识别。采用非相干光相关器为光学实现硬件,给出了实验结果。     

Color component 3D Arnold transform for polychromatic pattern recognition

We propose a novel method for polychromatic pattern recognition based on color component 3D Arnold transform. Three color components (for example RGB) are first transformed into three chaotic images by the use of 3D Arnold transform. And then any one of the chaotic images is chosen as the input image of the JTC to be recognized. As a result, strong color discrimination capability is achieved and common color images as well as some special color images can be recognized, while still preserving compact system and easier analysis of the output. Numerical results demonstrate the feasibility and effectiveness of the proposed method.     

Polychromatic pattern recognition based on color component chaos encoding

In order to overcome the disadvantages which the single-channel system and the multichannel system suffer from some special cases, such as, when there exists a linear relationship between the corresponding color components of the target image and the reference image, a novel method for color pattern recognition is proposed based on color component chaos encoding. In this approach, the color components are first encoded into chaos images and then the encoded images serve as the input images of the single-channel (or multichannel) system. As a result, the color difference resulting from the linear relationship between the corresponding color components of the target image and the reference image can be recognized. Computer simulations prove that this method is valid.     

A two-phase face recognition method in frequency domain

In this paper, we propose a two-phase face recognition method in frequency domain using discrete cosine transform (DCT) and discrete Fourier transform (DFT). The absolute values of DCT coefficients or DFT amplitude spectra are used to represent the face image, i.e. the transformed image. Then a two-phase face classification method is applied to the transformed images. This method is as follows: its first phase uses the Euclidean distance formula to calculate the distance between a test sample and each sample in the training sets, and then exploits the Euclidean distance of each training sample to determine K nearest neighbors for the test sample. Its second phase represents the test sample as a linear combination of the determined K nearest neighbors and uses the representation result to perform classification. In addition, we use various numbers of DCT coefficients and DFT amplitude spectra to test the effect on our algorithms. The experimental results show that our method outperforms the two-phase face recognition method based on space domain of face images.     

Nonparametric subspace analysis fused to 2DPCA for face recognition

Two-dimensional principal component analysis (2DPCA) is one of the representative techniques for image representation and recognition. However, keen storage requirements and computational complexity consist in 2DPCA. Meanwhile, the performance of 2DPCA is delicate in illumination variations. Nonparametric subspace analysis (NSA) is a subspace learning method that can reduce dimensionality and identify local information for discrimination, so that it can make 2DPCA perform well in illumination. Motivated by above facts, 2DPCA fused with NSA is implemented for face recognition, which can reduce dimensions of the 2DPCA feature vectors and enhance the contribution of principal components to face recognition. Experiments carried out on ORL, Yale B, and FERET facial databases show that valid recognition rates can be achieved by the proposed method compared to 2DPCA, 2DPCA plus PCA, LDA methods and demonstrate promising abilities against illumination variations.     

可见-近红外高光谱成像结合化学计量学分辨人面部信息

人的面部信息与指纹和虹膜一样可以用于人的身份鉴别,并且相比之下更容易实现远距离的分辨和识别。利用高光谱成像技术可以应用到人脸识别领域并获取丰富的信息和庞大的成像数据量,需要采用化学计量学方法才能充分提取其中包含的有效信息,并为计算机识别奠定基础。研究了可见-近红外高光谱成像技术对人的面部信息进行分析的可行性。结果表明,多元曲线分辨-交替最小二乘方法不同于主成分分析,能够通过主成分纯光谱和相对浓度等具有具体物理化学意义的数据表征人的面部信息,而且可以方便地根据成像数据的特点施加运算中的约束。另外,采用偏最小二乘判别分析的方法实现了对不同肤色的皮肤信号光谱进行分类。白种人和黄种人的面部高光谱信息特征相似,分类难度高于深色皮肤人种。     

基于高光谱技术融合图像信息的脱绒棉种品种分类检测研究

开展种子品种的识别研究是保证种子质量的重要手段。利用高光谱图像技术融合图像特征信息对脱绒棉种的品种进行判别分析。采集4个品种共240粒脱绒棉种样本的高光谱图像数据(400～1 000 nm),提取样本的光谱信息及长、宽、面积、圆形度、等12个形态特征。采用连续投影算法(SPA)选出11个特征波段作为输入结合偏最小二乘判别分析法(PLS-DA)、软独立模式识别法(SIMCA)、最邻近节点算法(KNN)、主成分分析结合线性判别(PCA-LDA)及二次判别(PCA-QDA)进行建模分析,得出PLS-DA建模集和预测集的总体识别率分别为93%和90%。利用图像信息进行建模分析,模型整体的识别率均不高,说明单独使用高光谱图像的形态特征进行分类效果不佳。将特征波段的光谱和形态特征信息进行融合作为输入,建立基于PLS-DA,SIMCA,KNN,PCA-LDA及PCA-QDA的信息融合模型,其精度均比基于光谱或形态信息模型高,其中PLS-DA模型识别效果最好,建模集和预测集总体识别率分别为98%和97%。表明融合高光谱图像的光谱与图像信息可以在少量波段情况下有效的提高脱绒棉种品种的分类检测精度。     

Semi-supervised Discriminant Analysis and Sparse Representation-based self-training for Face Recognition

In this paper, we consider the problem of automatic face recognition with limited manually labeled training data. We propose a new semi-supervised self-training approach which is used to automatically augment the manually labeled training set with new unlabeled data. Semi-supervised Discriminant Analysis is used in each iteration of self-training for discriminative dimensionality reduction by making use of both labeled and unlabeled training data. Sparse representation is applied for classification. Experimental results on four independent databases show that our algorithm outperforms other face recognition methods under 3 different configurations, namely transductive, semi-supervised and single training image.     

基于多尺度特征提取与多元回归分析的人脸识别

为提高人脸识别的正确率,提出了一种改进的特征提取及分类算法。首先采用Contour-let变换对人脸图像进行多尺度分解,然后由低频子带和各尺度各方向的高频子带得到人脸的特征值,并将它们组合成多尺度特征向量,再应用多元回归分析方法进行人脸识别。由于多尺度特征向量不仅反映了整幅图像的全局特征,还反映了图像各种尺度下的边缘、纹理等奇异特征,因此具有更多的鉴别信息;多元回归分析则充分考虑了同一总体的各样本间的强线性关系。在ORL人脸库上的实验显示人脸识别率达97．78％,优于其他的方法。     

Face recognition based on PCA image reconstruction and LDA

Face recognition has become a research hotspot in the field of pattern recognition and artificial intelligence. Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) are two traditional methods in pattern recognition. In this paper, we propose a novel method based on PCA image reconstruction and LDA for face recognition. First, the inner-classes covariance matrix for feature extraction is used as generating matrix and then eigenvectors from each person is obtained, then we obtain the reconstructed images. Moreover, the residual images are computed by subtracting reconstructed images from original face images. Furthermore, the residual images are applied by LDA to obtain the coefficient matrices. Finally, the features are utilized to train and test SVMs for face recognition. The simulation experiments illustrate the effectivity of this method on the ORL face database.     

Color component marking and convolution-based encoding for polychromatic pattern recognition

A novel method for polychromatic pattern recognition is proposed based on color component marking and convolution-based encoding. Three random phase functions are first chosen as marks to multiply with the three color components of the input images. Then the three marked color components are combined into one image using convolution-based encoding. Finally, the combined images are served as the input images of the JTC to be recognized. The feasibility and effectiveness of the proposed method are demonstrated by numerical results.     

高光谱图像和叶绿素含量的水稻纹枯病早期检测识别

基于高光谱成像技术和化学计量方法,实现了对水稻纹枯病病害的早期检测识别。以幼苗时期的水稻植株为研究对象,对其进行纹枯病病菌侵染,获得染病植株,采集358～1 021 nm波段范围的高光谱图像,三次实验共240个样本,包括染病植株120个样本和健康植株120个样本。根据高光谱图像的光谱维,对染病水稻叶片和健康水稻叶片提取感兴趣区域（ROI）,利用感兴趣区域的光谱数据,对其进行Savitzky-Golay（SG）平滑、Savitzky-Golay（SG）一阶求导、Savitzky-Golay（SG）二阶求导、变量标准化（SNV）和多元散射校正（MSC）预处理,建立线性判别分析（LDA）和支持向量机（SVM）分类模型,结果表明：采用SG二阶求导预处理后的线性判别分析（LDA）模型取得了较好的性能,正确识别率在建模集达98.3%,在预测集达95%;利用载荷系数法（x-loading weights, x-LW）对原始光谱和5种预处理的光谱数据进行特征波长提取,然后根据选取的特征波长建立线性判别分析（LDA）和支持向量机（SVM）分类模型,其中采用SG二阶求导预处理后提取的12个特征波长的线性判别分析（LDA）模型取得了较好的性能,其正确识别率在建模集达97.8%,在预测集达95%,而且基于载荷系数法建立的模型性能与全波段相当,可以通过载荷系数法减少数据量对水稻纹枯病病害进行识别;根据高光谱图像的图像维,研究了基于图像主成分分析、基于概率滤波和基于二阶概率滤波的图像特征提取方法,利用提取的特征变量建立反向传播神经网络(BPNN)和支持向量机（SVM）分类模型,其中基于图像主成分分析的反向传播神经网络（BPNN）模型取得了较好的性能,建模集准确识别率达90.6%,预测集的准确识别率达83.3%;根据高光谱图像光谱维和图像维的最优模型,特将叶绿素含量作为建模的另一个特征,分别与光谱特征、图像特征组合,建立反向传播神经网络（BPNN）和线性判别分析（LDA）模型,提出基于光谱特征加叶绿素含量、图像特征加叶绿素含量和光谱、图像特征加叶绿素含量三种组合方式,其中,光谱特征和图像特征分别与叶绿素组合的方式比之前单独的光谱和图像特征建模性能都有所提升,而且三种组合方式中光谱特征加叶绿素含量的反向传播神经网络（BPNN）建模方式取得本研究所有建模方式中较优的性能,其准确识别率在建模集达100%,在预测集达96.7%。以上研究表明,基于高光谱图像和叶绿素含量对水稻纹枯病病害进行早期识别是可行的,为水稻病害的早期识别提供了一种新方法。     

Application of the new pattern recognition system in the new e-nose to detecting Chinese spirits

We present a new pattern recognition system based on moving average and linear discriminant analysis （LDA）, which can be used to process the original signal of the new polymer quartz piezoelectric crystal air-sensitive sensor system we designed, called the new e-nose. Using the new e-nose, we obtain the template datum of Chinese spirits via a new pattern recognition system. To verify the effectiveness of the new pattern recognition system, we select three kinds of Chinese spirits to test, our results confirm that the new pattern recognition system can perfectly identify and distinguish between the Chinese spirits.     

彩色图像的非相干光相关识别

提出一种用非相干光系统识别彩色图像的方法,将脸色图像分解成三个单色像处理,设计一可实现的仅相位光学传递函数,对其进行带能优化,人而提高信噪比并使相关峰锐化,通过一对滤波器来合成该光学传递函数,获得了采色图像相关识别的实验结果。