改进的SLTP方法在掌纹识别中的应用

对掌纹识别进行研究,提出了基于改进的软直方图局部三值模式（SLTP）的掌纹识别方法。该方法先对掌纹训练样本进行能量函数的构造,然后用梯度下降法对能量函数进行优化,得到最佳的模糊隶属度函数,进而对掌纹的特征进行提取,最后用Chi概率统计的相似度度量方法进行匹配识别。在PolyU掌纹数据库和IITD掌纹数据库中进行实验验证,结果表明,在相同的训练样本下,改进的SLTP方法相比于SLTP方法,识别率得到提高。从而证明了该方法的有效性。     

下击暴流区域特征提取和识别算法

下击暴流是一种局部性的下沉气流现象,会对航空以及人们的生命财产安全造成灾难性后果。由于下击暴流具有范围小、强度大、变化快等特点,对它的自动识别是个颇具挑战性的任务。当前对下击暴流的分析是根据多普勒雷达图像数据进行的,图像上下击暴流表现为两个模糊区域间的相互作用,与周边的风速风强关系密切,有明显的特征。提出了一种图像区域分析算法对多普勒雷达图像的下击暴流区域进行自动识别,基于对历史数据集的特征提取,通过特征识别确定下击暴流区域的位置。使用Visual C++ 6.0实现了算法,结果表明算法的精度达到专家肉眼识别水平,能发现较隐蔽的可疑区域,提高了对恶劣天气的预报水平。     

面向情感语音识别的非线性几何特征提取算法

针对现有时域、频域属性特征在区分情感状态上存在的局限性,提出一种基于相空间重构理论的非线性几何特征提取方法。首先,通过分析情感语音信号的最小延迟时间和嵌入维数来实现相空间重构;其次,在重构相空间下分析并提取基于轨迹描述轮廓的五种非线性几何特征;最后,结合韵律特征、MFCC特征和混沌特征,设计实验方案验证所提特征区分情感状态的能力并通过特征选择获得情感信息完整的最优特征集合。选用德语柏林语音库中的五种情感（高兴、悲伤、中性、愤怒、害怕）作为实验数据来源,支持向量机作为识别网络。实验结果表明：与韵律特征、MFCC特征和混沌特征相比,所提特征不仅可以有效地表征语音信号中的情感差异性,也能够弥补现有特征在刻画情感状态上的不足。     

面向语音情感识别的语谱特征提取算法研究

语音情感识别的精度很大程度上取决于不同情感间的特征差异性。从分析语音的时频特性入手,结合人类的听觉选择性注意机制,提出一种基于语谱特征的语音情感识别算法。算法首先模拟人耳的听觉选择性注意机制,对情感语谱信号进行时域和频域上的分割提取,从而形成语音情感显著图。然后,基于显著图,提出采用Hu不变矩特征、纹理特征和部分语谱特征作为情感识别的主要特征。最后,基于支持向量机算法对语音情感进行识别。在语音情感数据库上的识别实验显示,提出的算法具有较高的语音情感识别率和鲁棒性,尤其对于实用的烦躁情感的识别最为明显。此外,不同情感特征间的主向量分析显示,所选情感特征间的差异性大,实用性强。     

基于多尺度特征提取的交通模式识别算法

针对普适交通模式的场景感知功耗高、场景复杂的问题,提出一种融合残差网络(ResNet)和带孔卷积的交通模式识别算法.首先,使用快速傅里叶变换(FFT)将一维传感器数据转换为二维频谱图像;然后,使用主成分分析(PCA)算法对频谱图像降采样;最后,使用ResNet挖掘交通模式的局部特征,使用带孔卷积挖掘交通模式的全局特征,...     

SVM-based feature extraction for face recognition

The primary goal of linear discriminant analysis (LDA) in face feature extraction is to find an effective subspace for identity discrimination. The introduction of kernel trick has extended the LDA to nonlinear decision hypersurface. However, there remained inherent limitations for the nonlinear LDA to deal with physical applications under complex environmental factors. These limitations include the use of a common covariance function among each class, and the limited dimensionality inherent to the definition of the between-class scatter. Since these problems are inherently caused by the definition of the Fisher's criterion itself, they may not be solvable under the conventional LDA framework. This paper proposes to adopt a margin-based between-class scatter and a regularization process to resolve the issue. Essentially, we redesign the between-class scatter matrix based on the SVM margins to facilitate an effective and reliable feature extraction. This is followed by a regularization of the within-class scatter matrix. Extensive empirical experiments are performed to compare the proposed method with several other variants of the LDA method using the FERET, AR, and CMU-PIE databases.     

自适应Gabor特征的协同表示人脸识别算法

为了解决人脸识别应用中针对人脸姿态的变化,光照等外部环境变化导致识别率不高,且稀疏表示应用于人脸识别收敛速度慢的情况,提出了一种基于多分量的Gabor特征提取和自适应权重选择的协同表示人脸识别算法(GAW-CRC).特征提取阶段,将Gabor变换的所有特征分量中鉴别能力较差的分量淘汰,剩余分量构建特征字典,分别协同表示对应测试样本的特征分量,将所有剩余分量的识别结果,按照自适应的权重函数加权融合得出最终分类结果.实验证明:算法应用于AR,FERET与Extended Yale B人脸库中,当对应的样本存在人脸角度变化,表情变化和光照条件变化等情况时,能够得到更高的识别率.     

Stockwell transform based palm-print recognition

This paper proposes a novel technique to extract palm-print features based on instantaneous-phase difference obtained using Stockwell transform of overlapping circular-strips. The hand images are acquired using a low cost scanner. A procedure is proposed to classify hand images into either right or left hand based on their inherent characteristics and then the palm-print region from the hand image is extracted accordingly. This palm-print region is found to be robust to translation and rotation on the scanner. The proposed system is tested on IITK database of 549 images, CASIA database of 5239 images and PolyU database of 7751 images. The system performs with 100% correct recognition rate (CRR) and equal error rate (EER) less than 1% for all the databases.     

A novel geometric feature extraction method for ear recognition

The discriminative ability of geometric features can be well supported by empirical studies in ear recognition. Recently, a number of methods have been suggested for geometric feature extraction from ear images. However, these methods usually have relatively high feature dimension or are sensitive to rotation and scale variations. In this paper, we propose a novel geometric feature extraction method to address these issues. First, our studies show that the minimum Ear Height Line (EHL) is also helpful to characterize the contour of outer helix, and the combination of maximal EHL and minimum EHL can achieve better recognition performance. Second, we further extract three ratio-based features which are robust to scale variation. Our method has the feature dimension of six, and thus is efficient in matching for real-time ear recognition. Experimental results on two popular databases, i.e. USTB subset1 and IIT Delhi, show that the proposed approach can achieve promising recognition rates of 98.33% and 99.60%, respectively.     

一种加权的多重分形特征提取算法

为解决多重分形维数不能够很好地反映图像强度信息和对图像尺度有强依赖的问题,在研究q 阶广义维数D（q）基础上,提出两种改进方法。通过分析影响生长概率的因子,提出一种结合强度信息的加权子数计算方法,提出一种基于网格强度与均值的二维分形维数计算方法。实验表明改进的多重分形算法提了特征区分度,计算特征更加鲁棒和有效,将改进方法用于血细胞识别系统,改善了白细胞分类准确性。     

一种广义的主成分分析特征提取方法

提出了一种广义的PCA特征提取方法。该方法先将图像矩阵进行重组,根据重组的图像矩阵构造出总体散布矩阵,然后求出最佳投影向量进行特征提取。它是2DPCA和模块2DPCA的进一步推广,可以建立任意维数的散布矩阵,得到任意维数的投影向量。实验表明,随着总体散布矩阵维数的减小,广义PCA的特征提取能力更强,特征提取的速度也更快。     

Gabor filters-based feature extraction for character recognition

A new method using Gabor filters for character recognition in gray-scale images is proposed in this paper. Features are extracted directly from gray-scale character images by Gabor filters which are specially designed from statistical information of character structures. An adaptive sigmoid function is applied to the outputs of Gabor filters to achieve better performance on low-quality images. In order to enhance the discriminability of the extracted features, the positive and the negative real parts of the outputs from the Gabor filters are used separately to construct histogram features. Experiments show us that the proposed method has excellent performance on both low-quality machine-printed character recognition and cursive handwritten character recognition.     

Towards collaborative feature extraction for face recognition

Principal components analysis has become a popular preprocessing method to avoid the small sample size problem for most of the supervised graph embedding methods. Nevertheless, there is potential loss of relevant information when projecting the data onto the space defined by the principal Eigenfaces when the number of individuals in the gallery is large. This paper introduces a new collaborative feature extraction method based on projection pursuit, as a robust preprocessing for supervised embedding methods. A previously proposed projection index was adopted as a measure of interestingness, based on a weighted sum of six state of the art indices. We compare our collaborative feature extraction technique against principal component analysis as preprocessing stage for Laplacianfaces. For completeness, results for Eigenfaces and Fisherfaces are included. Experimental results to demonstrate the robustness of our approach against changes in facial expression and lighting are presented.     

一种去冗余的SIFT特征提取方法

基于SIFT特征点的配准是图像配准领域里常采用的一种方法。但是,在复杂背景下,图像SIFT特征点通常量大且冗余,这会带来浪费存储空间、容易误配、配准耗时多等问题。针对这些缺点,提出了一种去冗余的SIFT特征提取算法。首先提取出SIFT特征点,然后根据特征点周边梯度情况,判断特征点是否落于目标区域,进而保留目标区域特征点,删除背景区域特征点,减少特征点数量的同时也实现了去冗余。提取所得的特征点质量好坏由落入目标区域的点数和落入背景区域的点数比例判断。实验结果表明,本算法减少了复杂背景下大量的干扰特征点。这将为后续的配准工作提高精度和效率。     

Example image-based feature extraction for face recognition

This paper proposes a novel method for recognizing facial images based on the relative distances between an input image and example images. Example facial images can be easily collected online, and a large example database can span new possible facial variations not sufficiently learned during the learning phase. We first extract facial features using a baseline classifier that has a certain degree of accuracy. To achieve a better performance of the proposed method, we divide the collected examples into groups using a clustering method (e.g., k-means), where each clustered group contains examples with similar characteristics. We then hierarchically partition a group formed in the previous level into other groups to analyze more specific facial characteristics, which represent an example pyramid. To describe the characteristics of a group using the clustered examples, we divide the example group into a number of sub-groups. We calculate the averages of the sub-groups and select an example most similar to the average in each sub-group because we assume that the averages of the sub-groups can directly represent their characteristics. Using the selected examples, we build example code words for a novel feature extraction. The example code words are used to measure the distances to an input image and serve as anchors to analyze a facial image in the example domain. The distance values are normalized for each group at all pyramid levels, and are concatenated to form novel features for face recognition. We verified the effectiveness of the proposed example pyramid framework using well-known proposed features, including LBP, HOG, Gabor, and the deep learning method, on the LFW database, and showed that it can yield significant improvements in recognition performance.     

A novel stroke-based feature extraction for handwritten Chinese character recognition

A stroke-based approach to extract skeletons and structural features for handwritten Chinese character recognition is proposed. We first determine stroke directions based on the directional run-length information of binary character patterns. According to the stroke directions and their adjacent relationships, we split strokes into stroke and fork segments, and then extract the skeletons of the stroke segments called skeleton segments. After all skeleton segments are extracted, fork segments are processed to find the fork points and fork degrees. Skeleton segments that touch a fork segment are connected at the fork point, and all connected skeleton segments form the character skeleton. According to the extracted skeletons and fork points, we can extract primitive strokes and stroke direction maps for recognition. A simple classifier based on the stroke direction map is presented to recognize regular and rotated characters to verify the ability of the proposed feature extraction for handwritten Chinese character recognition. Several experiments are carried out, and the experimental results show that the proposed approach can easily and effectively extract skeletons and structural features, and works well for handwritten Chinese character recognition.     

A physiognomy based method for facial feature extraction and recognition

This paper proposes a novel calculation method of personality based on Chinese physiognomy. The proposed solution combines ancient and modern physiognomy to understand the relationship between personality and facial features and to model a baseline to shape facial features. We compute a histogram of image by searching for threshold values to create a binary image in an adaptive way. The two-pass connected component method indicates the feature's region. We encode the binary image to remove the noise point, so that the new connected image can provide a better result. According to our analysis of contours, we can locate facial features and classify them by means of a calculation method. The number of clusters is decided by a model and the facial feature contours are classified by using the k-means method. The validity of our method was tested on a face database and demonstrated by a comparative experiment.     

鲁棒特征提取算法

特征提取技术的应用依赖于数据的固有属性,研究了当前流行的特征提取技术,并针对这些特征提取技术所存在的弱点,提出了一种新颖的特征提取算法-鲁棒特征提取算法.该算法分为两个阶段,以同时最大化不同类之间的距离与最小化类内距离为目标.实验结果表明,在对现实世界数据集进行特征提取时,鲁棒特征提取算法表现出的性能在分类精度与效率的指标上均能达到最优.对这些实验结果进行了解释,并给出了进一步研究的方向.     

A data-driven intermediate level feature extraction algorithm

An algorithm is presented that is based on the regression updating theory for fitting linearly parameterizable curves without prior classification of edge data. An initial estimate of a hypothesized curve is first obtained by a statistical windowing technique. A search region is determined and iteratively grown. Edge points in the search region are tested for their goodness-of-fit to the previous estimate. The estimate is iteratively updated with the edge points that have favorable goodness-of-fit measures. The edge points having poor goodness-of-fit measures are rejected as outliers. The algorithm drives the estimate to converge to a final solution. By repeatedly applying this procedure to the edge data excluded from the previous fitting, all the underlying curves are reconstructed. The major feature that distinguishes this approach from that of others is that classifying the edge data prior to fitting is not required. Advantages of this algorithm are: (1) the fitting procedure achieves higher robustness and accuracy by dynamically analyzing the data consistency; (2) the computational complexity increases only linearly with the number of edge data; (3) the algorithm readily extends to reconstruct surfaces from range data. Thus the algorithm provides a powerful technique enabling a data-driven intermediate-level vision module to extract parametric features needed for higher-level processing