37 results about "Kernel Fisher discriminant analysis" patented technology

A image verification method, medium, and apparatus using a local binary pattern (LBP) discriminant technique. The verification method includes generating a kernel fisher discriminant analysis (KFDA) basis vector by using the LBP feature of an input image, obtaining a Chi square inner product by using the LBP feature of an image registered in advance and a kernel LBP feature and projecting to a KFDA basis vector, obtaining a Chi square inner product by using the LBP feature of a query image and a kernel LBP feature and projecting to a KFDA basis vector, and obtaining the similarity degree of the target image and the query image that are obtained as Chi square inner product results, and projected to the KFDA basis vector. According to the method, medium, and apparatus, the KFDA based LBP shows superior performance over conventional LBP, KFDA, and biometric experimentation environment (BEE) baseline algorithms.

The invention discloses a building seismic damage analysis method, and relates to the field of seismic damage assessment. The method comprises the following steps of: setting a contour sampling interval, extracting a point cloud set of different height of a building, then, obtaining a contour section profile line through a convex hull algorithm, and converting three-dimensional point cloud of the building into a two-dimensional contour polygon sequence; extracting shape discrete parameters of the building; and calculating standard deviation of building shape parameters, and through a Fisher discriminant analysis, performing statistics on the standard deviation obtained in a step S22 or a step S23, thereby obtaining a discrimination function corresponding to three types of degree of damage of the building. According to the invention, edge extraction, shape clustering and discriminant analysis are fused, and problems in building contour polygon sequence extraction, shape discrete parameter calculation, irregular building block segmentation and damage analysis are solved effectively.

The invention provides a gait recognition method based on multi-linear mean component analysis. The gait recognition method comprises a training stage and a recognition stage. The training stage refers to performing dimension reduction processing on a half-cycle gait sequence image subjected to linear interpolation through the following algorithms, and training to obtain a projection conversion matrix of the algorithms: projecting the half-cycle gait sequence image into a low-dimension multi-linear subspace through general tensor discriminant analysis; performing further feature extraction by adopting the multi-linear mean component analysis; enabling a training tensor sample to be finally projected into a low-dimension vector space by adopting linear discriminant analysis. According to the recognition stage, conversion matrixes obtained through training the to-be-recognized half-cycle gait sequence image sample with the general tensor discriminant analysis and multi-linear mean component analysis algorithms are subjected to twice projection in a tensor space, the conversion matrix obtained through training the to-be-recognized half-cycle gait sequence image sample with the linear discriminant analysis algorithm is projected in the vector space, and a nearest neighbor classifier is adopted in the vector space during recognition. The gait recognition method can be used for improving the accuracy of gait recognition and has high robustness under different environments.

The present invention provides a method for extracting the difference feature of taste sensory signals based on nuclear linear discriminant analysis. The method includes: using an electronic tongue to detect tea samples to obtain sensor response time series signals; according to the response time series signals, using principal component residuals and The Mahalanobis distance method is used to analyze and eliminate abnormal samples; the parameters of the kernel linear discriminant analysis method are optimized, and the parameters of the kernel linear discriminant analysis method are selected based on the correct recognition rate of the quality grade of Longjing tea; The response signal is extracted with nonlinear features to obtain the taste characteristics of the tea samples; the taste characteristics of the tea samples are input into the classifier to judge the tea quality grade. Remove outliers from tea samples, and use the kernel linear discriminant analysis method after optimizing parameters to better characterize the nonlinear characteristics of tea samples of different grades, and improve the signal difference of samples after nonlinear mapping in high-dimensional feature space .

The invention provides a method for rapidly identifying the charcoal carbonization temperature based on spectrum analysis. The method comprises the following steps: (1) establishing a charcoal spectrum database; (2) carrying out principal component analysis (PCA) on the spectrum database, and extracting front q principal components with the highest contribution rates according to the size of the variance contribution rate; (3) carrying out mode identification on the charcoal carbonization temperature by virtue of a Fisher linear discriminant analysis (FLD) method according to front q principal components Z1, Z2, ..., Zq obtained through PCA analysis of a sample; (4) scanning a to-be-identified sample spectrum; (5) carrying out same principal component analysis on the to-be-identified sample spectrum, and extracting front q principal components Z1, Z2, ..., Zq with the highest contribution rates according to the size of the variance contribution rate; and (6) classifying to-be-identified samples into a corresponding charcoal carbonization temperature category according to an established FLD model, so as to finish the rapid identification of the charcoal carbonization temperature.

The invention discloses an electronic nose signal feature selection optimization method based on multi-kernel Fisher discriminant analysis. Firstly, a sample feature matrix is ​​obtained, parameters are initialized and basic kernel functions are constructed according to the parameters, and then a composite kernel matrix is ​​calculated based on the basic kernel matrix, and a composite kernel function is calculated. The projection of the kernel matrix in the high-level feature space, and then send the projection to the classifier for pattern recognition, determine the kernel function with the highest recognition rate, and finally calculate the projection of the new sample matrix in the feature space based on the kernel function and use it as an electronic nose The signal is used as the input of the classifier for pattern recognition. Its remarkable effect is: it overcomes the problem of poor data discrimination after the single kernel function method realizes high-dimensional projection, solves the redundancy between sensors, optimizes the sensor array and reduces the data dimensionality, and improves the accuracy of the electronic nose signal. recognition rate, thus providing useful guidance for doctors to choose appropriate treatment methods.

The present invention provides a SAR image target feature extraction and recognition method based on KFDA (Kernel Fisher Discriminant Analysis) and SVM (Support Vector Machine), comprising the following steps: performing training target samples of known categories and testing target samples of unknown categories Amplitude data normalization processing; using the KFDA criterion to perform feature extraction on the normalized known categories of training target samples and unknown categories of test target samples; The SVM classifier is trained to generate the optimal classification surface; finally, the features of the unknown category of test target samples extracted by the KFDA criterion are identified through the optimal classification surface; the present invention reduces the requirements for the preprocessing process and overcomes the The azimuth sensitivity of SAR images compresses the dimensionality of sample features and obtains a high target recognition rate, which has good generalization.