Facial expression recognition algorithm using LGC based on horizontal and diagonal prior principle

The traditional Local Binary Pattern (LBP) algorithm can analyze the center pixel and neighboring pixels of the gray relationship, using in facial expression recognition, but you cannot consider the eyes, mouth, forehead and other areas in the expression feature different trends in the gradient direction. Firstly, we propose the Local Gradient Coding (LGC) algorithm, though the binary encoding to the horizontal, vertical and diagonal gradients respectively, to produce the fusion characteristic, then this can fully describe the facial muscles texture, wrinkles and other local deformation of contains the expression information. On the other hand, in order to reduce the computational complexity, and to remove the redundant, while not lose the main information contained in the face texture expression. This paper proposes and optimizes a new LGC operator based on horizontal and diagonal gradient prior principle (LGC-HD). The experimental results from JAFFE database show that, LGC-HD algorithm is more quickly and effectively to extract facial expression feature than LGC algorithm. Comparing to the traditional LBP algorithm, LBP uniform pattern and Gabor filtering, this LGC-HD algorithm has a significant advantage in the recognition accuracy and run time.     

基于数字图像处理技术的人脸检测算法研究

为了提高人脸检测的准确性及检测速度,需要对基于数字图像处理技术的人脸检测算法进行研究。使用当前方法进行人脸检测时,需要提取脸部特征数目较多、检测速度过慢,降低人脸检测效率。为此,提出一种基于数字图像处理技术的人脸检测算法。该方法首先获取人脸数字图像,通过拉开数字图像的灰度间距,使数字图像灰度均匀分布,进而提高数字图像对比度,使图像更加清晰,再通过Wiener维纳滤算法对处理后的数字图像进行图像平滑去噪,在此基础上使用Robert边缘检测算子方法对数字图像人脸边缘每个像素点检测,得到数字图像中人脸边缘的基本图像,将其输入到计算机数字图像处理系统中进行识别检测。实验仿真证明,所提算法在检测速度及准确性等方面具有明显的优势。     

Robust automatic facial expression detection method based on sparse representation plus LBP map

Recently the sparse representation based classification (SRC) is successfully used to automatically recognize facial expression, well-known for its ability to solve occlusion and corruption problems. The results of those methods which using different features conjunction with SRC framework show state of the art performance on clean or noised facial expression images. Therefore, the role of feature extraction for SRC framework will greatly affect the success of facial expression recognition (FER). In this paper, we select a new feature which called LBP map. This feature is generated using local binary pattern (LBP) operator. It is not only robust to gray-scale variation, but also extracts sufficient texture information for SRC to deal with FER problem. Then we proposed a new method using the LBP map conjunction with the SRC framework. Firstly, we compared our method with state of the art published work. Then experiments on the Cohn–Kanade database show that the LBP map + SRC can reach the highest accuracy with the lowest time-consuming on clean face images than those methods which use different features such as raw image, Downsample image, Eigenfaces, Laplacianfaces and Gabor conjunction with SRC. We also experiment the LBP map + SRC to recognize face image with partial occluded and corrupted, the result shows that this method is more robust to occlusion and corruption than existing methods based on SRC framework.     

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.     

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.     

‘Symmetrical face’ based improved LPP method for face recognition

As one of the most important branches of pattern recognition and computer vision, face recognition has more and more become the focus of researches. In real word applications, the face image might have various changes owing to varying illumination, facial expression and poses, so we need sufficient training samples to convey these possible changes. However, most face recognition systems cannot capture many face images of every user for training, non-sufficient training samples have become one bottleneck of face recognition. In this paper, we propose to exploit the symmetry of the face to generate ‘symmetrical face’ samples and use an improved LPP method to perform classification. Experimental results show that our method can get a high accuracy.     

Hybrid Binary Joint Transform Correlator For Adaptive Real－time Pattern Recognition

ＨｙｂｒｉｄＢｉｎａｒｙＪｏｉｎｔＴｒａｎｓｆｏｒｍＣｏｒｒｅｌａｔｏｒＦｏｒＡｄａｐｔｉｖｅＲｅａｌ－ｔｉｍｅＰａｔｔｅｒｎＲｅｃｏｇｎｉｔｉｏｎ￥ＷＡＮＧＤａｙｏｎｇ；ＸＩＥＷｅｉｘｉｎＷＡＮＧＤａｙｏｎｇ；ＸＩＥＷｅｉｘｉｎ（Ｄｅｐａｒｔｍｅｎ...     

基于红外与近红外光谱的烟叶部位识别

以烟叶样品的红外及近红外光谱为基础,采用基于主成分分析的马氏距离判别模型,研究了不同类型仪器、建模区间、模型参数及光谱预处理方式对烟叶部位识别准确率的影响。结果表明根据红外和近红外光谱均可对烟叶部位进行良好识别,近红外光谱因包含的样品信息更为丰富,可以得到比红外光谱更好的识别效果。其中仪器A的二阶导数光谱给出的烟叶部位识别准确率最高,可达94.11%;仪器B的一阶导数及SNV光谱给出的烟叶部位识别准确率次之,为88.24%;Nicolet公司的Antaris360傅里叶红外仪的一阶导数光谱给出的烟叶部位识别准确率为82.35%。对于同一仪器,最佳建模区间及主成分个数随样本情况及光谱预处理方式而变。     

Simulation and experiment research of face recognition with modified multi-method morphological correlation algorithm

Morphological definition of similarity degree of gray-scale image and general definition of morphological correlation (GMC) are proposed. Hardware and software design for a compact joint transform correlator are presented in order to implement GMC. Two kinds of modified general morphological correlation algorithm are proposed. The gray-scale image is decomposed into a set of binary image slices in certain decomposition method. In the first algorithm, the edge of each binary joint image slice is detected, width adjustability of which is investigated, and the joint power spectrum of the edge is summed. In the second algorithm, the joint power spectrum of each pair is binarized or thinned and then summed in one situation, and the summation of the joint power spectrums of these pairs is binarized or thinned in the other situation. Computer-simulation results and real face image recognition results indicate that the modified algorithm can improve the discrimination capabilities with respect to the gray-scale face images of high similarity.     

Genetic optical design for a compressive sensing task

We present a sophisticated optical design method for reducing the number of photodetectors for a specific sensing task. The chosen design parameter is the point spread function, and the selected task is object recognition. The point spread function is optimized iteratively with a genetic algorithm for object recognition based on a neural network. In the experimental demonstration, binary classification of face and non-face datasets was performed with a single measurement using two photodetectors. A spatial light modulator operating in the amplitude modulation mode was provided in the imaging optics and was used to modulate the point spread function. In each generation of the genetic algorithm, the classification accuracy with a pattern displayed on the spatial light modulator was fed-back to the next generation to find better patterns. The proposed method increased the accuracy by about 30 % compared with a conventional imaging system in which the point spread function was the delta function. This approach is practically useful for compressing the cost, size, and observation time of optical sensors in specific applications, and robust for imperfections in optical elements.     

基于改进梯度幅值的包装缺陷检测算法研究及应用

针对包装质量检测精度易受外界光照影响的问题，在已有基于梯度幅值相似性的缺陷检测算法基础上，将局部二值模式算子引入到该算法中，提出了一种基于改进梯度幅值相似性的缺陷检测算法。该算法利用局部二值模式算子的旋转不变性和灰度不变性的特点，并将其与图像的梯度幅值特征进行融合后用于包装的缺陷检测中，提升了缺陷检测算法对光照的鲁棒性。实验结果表明，相比传统梯度幅值缺陷检测算法，该算法具有更好的抗光照影响能力，并且对于不同光照情况下的包装缺陷，该算法的检测准确率可达96.57%。因而，该算法能够被广泛地用于包装缺陷检测中，提高缺陷检测的精度。     

Face recognition based on PCA and logistic regression analysis

Face recognition is an important research hotspot. More and more new methods have been proposed in recent years. In this paper, we propose a novel face recognition method which is based on PCA and logistic regression. PCA is one of the most important methods in pattern recognition. Therefore, in our method, PCA is used to extract feature and reduce the dimensions of process data. Afterwards, we present a novel classification algorithm and use logistic regression as the classifier for face recognition. The experimental results on two different face databases are presented to illustrate the efficacy of our proposed method.     

Blood oxygenation level dependent magnetic resonance imaging and diffusion weighted MRI imaging for benign and malignant breast cancer discrimination

PurposeThe purpose of this study is to assess Blood oxygenation level dependent Magnetic Resonance Imaging (BOLD-MRI) and Diffusion Weighted Magnetic Resonance Imaging (DW-MRI) in the differentiation of benign and malignant breast lesions.MethodsFifty-nine breast lesions (26 benign and 33 malignant lesions) pathologically proven in 59 patients were included in this retrospective study. As BOLD parameters were estimated basal signal S₀ and the relaxation rate R2*, diffusion and perfusion parameters were derived by DWI (pseudo-diffusion coefficient (Dp), perfusion fraction (fp) and tissue diffusivity (Dt)). Wilcoxon-Mann-Whitney U test and Receiver operating characteristic (ROC) analyses were calculated and area under ROC curve (AUC) was obtained. Moreover, pattern recognition approaches (linear discrimination analysis (LDA), support vector machine, k-nearest neighbours, decision tree) with least absolute shrinkage and selection operator (LASSO) method and leave one out cross validation approach were considered.ResultsA significant discrimination was obtained by the standard deviation value of S0, as BOLD parameter, that reached an AUC of 0.76 with a sensitivity of 65%, a specificity of 85% and an accuracy of 76%. No significant discrimination was obtained considering diffusion and perfusion parameters. Considering LASSO results, the features to use as predictors were all extracted parameters except that the mean value of R2* and the best result was obtained by a LDA that obtained an AUC = 0.83, with a sensitivity of 88%, a specificity of 77% and an accuracy of 83%.ConclusionsGood performance to discriminate benign and malignant lesions could be obtained using BOLD and DWI derived parameters with a LDA classification approach. However, these findings should be proven on larger and several dataset with different MR scanners.     

A New Method for Rotation and Brightness Invariant Pattern Recognition Based on Modified Multiple Circular Harmonic Expansions

A new method for rotation and brightness invariant pattern recognition was proposed by applying multiple circular harmonic expansions to the joint transform correlator. The amplitudes of the multiple orders of circular harmonic expansions made from a detecting image were synthetically modified to respond to the same auto-correlation peaks. These modified circular harmonic expansions were arranged in the input plane as reference patterns together with an arbitrary target pattern, and the correlation signals between them were calculated in the subtracted joint transform correlator. The fraction of the correlation-peak intensities between the target and the references were extracted as a new discrimination parameter. This new parameter performs pattern recognition under rotation and brightness invariance with good discriminability. Its high discriminability has been proved in computer simulations using the face image patterns of many individuals.     

A hierarchical structure with improved OMP sparse representation used with face recognition

With the rapid development of the face recognition technology, more and more optical products are applied in people's real life. The recognition accuracy can be improved by increasing the number of training samples, but the colossal training samples will result in the increase of computational complexity. In recent years, sparse representation method becomes a research hot spot on face recognition. In this paper we propose an energy constrain orthogonal matching pursuit (ECOMP) algorithm for sparse representation to select the few training samples and a hierarchical structure for face recognition. We filter the training samples with ECOMP algorithm and then we compute the weights by all selected training samples. At last we find the closest recovery sample to the test sample. Simultaneously the experimental results in AR, ORL and FERET database also show that our proposed method has better recognition performance than the LRC and SRC_OMP method.     

A Highly Accurate Face Recognition System Using Filtering Correlation

The authors previously constructed a highly accurate fast face recognition optical correlator (FARCO) [E. Watanabe and K. Kodate: Opt. Rev. 12 (2005) 460], and subsequently developed an improved, super high-speed FARCO (S-FARCO), which is able to process several hundred thousand frames per second. The principal advantage of our new system is its wide applicability to any correlation scheme. Three different configurations were proposed, each depending on correlation speed. This paper describes and evaluates a software correlation filter. The face recognition function proved highly accurate, seeing that a low-resolution facial image size (64 × 64 pixels) has been successfully implemented. An operation speed of less than 10 ms was achieved using a personal computer with a central processing unit (CPU) of 3 GHz and 2 GB memory. When we applied the software correlation filter to a high-security cellular phone face recognition system, experiments on 30 female students over a period of three months yielded low error rates: 0% false acceptance rate and 2% false rejection rate. Therefore, the filtering correlation works effectively when applied to low resolution images such as web-based images or faces captured by a monitoring camera.     

基于波形叠加极限学习机的近红外光谱药品鉴别

近红外光谱药品鉴别作为识别假冒伪劣药品的一种有效技术手段,已被广泛应用到各大医疗行业和药品监督管理机构,并结合模式识别建模方法在基层药品打假中得到较好的推广。由于传统建模方法很难满足药品鉴别中大规模、多分类、快速建模等问题,因此采用一种基于波形叠加极限学习机(SWELM(CS))分类方法对光谱数据进行鉴别。通过选用极限学习机(ELM)作为光谱药品分类器,使得分类模型具有快速学习能力以及对训练样本不敏感的特点;由于极限学习机的连接权值和隐层神经元阈值是随机生成导致网络稳定性差,因此结合布谷鸟搜索算法优化分类模型参数;采用反双曲线正弦函数与Morlet小波函数叠加的激励函数代替ELM原有的单一激励函数改善了分类模型的收敛速度和稳健性。通过上述改进方法使得SWELM(CS)具有对训练样本不敏感性,布谷鸟参数优化的分类稳定性、波形叠加函数的强收敛性与信号特征提取能力。该方法为核函数提供的信号特征提取及拟合的思想,可推广到其他学习算法中以获取更高的分类准确度及稳定性。该实验选定西安杨森制药厂生产的249个近红外光谱药品样本作为研究的主要对象,重点研究光谱药品的二分类和多分类实验,实验证明SWELM(CS)分类器相比BP神经网络、标准ELM以及粒子群优化ELM等传统分类器算法具有更高的分类准确度、分类稳定性及更小的训练样本敏感性。     

A sparse representation method based on kernel and virtual samples for face recognition

To improve the classification accuracy of face recognition, a sparse representation method based on kernel and virtual samples is proposed in this paper. The proposed method has the following basic idea: first, it extends the training samples by copying the left side of the original training samples to the right side to form virtual training samples. Then the virtual training samples and the original training samples make up a new training set and we use a kernel-induced distance to determine M nearest neighbors of the test sample from the new training set. Second, it expresses the test sample as a linear combination of the selected M nearest training samples and finally exploits the determined linear combination to perform classification of the test sample. A large number of face recognition experiments on different face databases illustrate that the error ratios obtained by our method are always lower more or less than face recognition methods including the method mentioned in Xu and Zhu [21], the method proposed in Xu and Zhu [39], sparse representation method based on virtual samples (SRMVS), collaborative representation based classification with regularized least square (CRC_RLS), two-phase test sample sparse representation (TPTSSR), and the feature space-based representation method.     

Facial expression recognition based on two-stage features extraction

Facial expression recognition plays an important role in a variety of real-world applications such as human–computer interaction, robot control, smart meeting, and visual surveillance. One critical step for facial expression recognition is to accurately extract emotional features. In this article, a facial expression recognition approach based on two-stage local facial textures extraction is proposed. At the first stage, we use the threshold local binary pattern to transform a facial image into a feature image. We then extract the most discriminate features from the feature image by using the block-based center-symmetric local binary pattern. Finally, these features are classified by the support vector machine. Experimental results are provided to illustrate the proposed approach is an effective method, compared to other similar methods.     

远程采集模糊无人机图像的特征识别方法研究

地面对空中无人机的视觉识别中,由于无人机的飞行速度、角度呈现非线性变化。使得采集的疑似图像存在特征模糊、衰退等问题,传统的模式识别方法无法提取无人机图像的主要特征,极大程度上降低了图像的识别概率。提出一种引入球面谐波基图像特征细分的无人机识别算法,建立球面谐波基图像识别模型,利用无人机图像的球面谐波基图像近似率,对模糊图像的差异特征进行依次识别。实验结果表明,利用改进算法建立的模糊无人机图像差异特征识别模型,具有一定的优越性,提高了无人机识别的准确率。