78results about How to "Accurate feature extraction" patented technology

The invention discloses a monocular vision AGV (Automated Guided Vehicle) accurate positioning method and system based on multi-window real-time range finding. The method comprises according to a camera slanting installation mode, calibrating and measuring camera parameters and establishing a visual system real-time measuring model; setting a circular color lump on the ground to be used as the reference substance for parking positioning, identifying the circular color lump through the efficient algorithm of the visual system, and accurately extracting central position information; and in a view filed, setting a plurality of windows to process images a far-end window is used for an AGV to predetermine ground information so as to gradually decelerate; an intermediate window is used as a coarse positioning window, and used for adjusting poses; and a near-end window is used for accurate range finding and parking. The method allows an AGV to sense depth information, and has the advantages of high characteristic recognition rate, excellent arithmetic instantaneity, low cost and great extendibility. The horizontal distance deviation of AGV parking is stabilized at +-1 mm, the angle deviation is stabilized at +-1 DEG, and the parking error is stabilized at +- 2mm.

The invention provides a vehicle license character feature extracting and classifying method using projection symmetry as the precondition for judgment. The method comprises the following steps: firstly extracting character feature to 26 letters and 10 numbers which may appear in vehicle license characters by using projection symmetry as precondition to divide into four classes, namely vertical projection class, horizontal projection class, central point projection class and dissymmetric property class and realize the coarse classifications of vehicle license characters; and fining, performing normalization transformation, then extracting features of points and rings and completing the fine classification of vehicle license characters. The invention combines the projection symmetry with the feature extraction method of points and rings to set a vehicle license character classifier, thus laying the foundation of realizing the identification of vehicle license characters finally. The method has better identification effect on confusable characters, such as '0' and 'D', '8' and 'B', '7' and 'T' and the like, thus increasing the identification speed and accuracy of vehicle license characters.

The invention discloses a mobile payment verification method based on palmprint recognition. The mobile payment verification method includes two stages of registration and identification. In the registration stage, palm images of a user can be acquired by a rear camera of a smart phone, palmprint information of the user is extracted via four steps of palm image partitioning, palmprint preprocessing, minimalized processing of palmprint images and palmprint characteristic extraction, personal marking information and palmprint information of the user can be uploaded to a verification server via the mobile internet, and the information of the user is stored to database of the verification server. In the verification stage, the rear camera of the smart phone acquires palm images of the user, the palm images are processed by a serial of same algorithms to obtain palm information of the user and transmitted to the verification sever, then the palm information is matched with that stored in the database in the registration stage so as to judge whether the user can pay or not.

The invention provides a method for identifying a hyperspectral material. First a standard light source spectrum database is established, a spectral material standard database is established, and standard light source spectra are obtained through a difference method and a control variable method; spectral data information is shot for a material needing to be identified; through preprocessing and intrinsic material information extraction, spectral characteristics of the material are obtained, and then the spectral characteristics are matched with data in the spectral material standard database, so as to perform high-precision identification of the material. According to the method, the interference to spectral information of the material caused by complex factors such as different illumination conditions and material shape changes and the like can be resisted, the problems of metamerism and homogeneity and heterochrome which cannot be solved through conventional red green blue (RGB) and RGBD cameras are solved, and the identification precision rate is high.

The invention discloses an image multi-subtitle automatic generation method based on a multiscale hierarchical residual network, and adopts an improved funnel network to capture multiscale target information. Firstly, when a funnel framework network is constructed, a densely connected polymerization residual block is put forward, and residual LSTM (Long Short Term Memory) is further put forward inorder to solve the problems of gradient vanishing and gradient explosion. By use of the method, high experiment performance is obtained, and the method has an obvious advantage on multi-subtitle taskacquisition.

The invention provides a crop image recognition method photographed by an unmanned aerial vehicle. The invention relates to a crop image recognition method photographed by an unmanned aerial vehicle (UAV), which is characterized in that the method comprises the following steps: (1) constructing attribute information of the crop image photographed by the UAV and performing preprocessing to obtain acrop image data set; S2. the convolution neural network model is pre-trained with the idea of transfer learning; S3, fine-tuning the convolution neural network pre-trained in the step S2 by using thecrop image data set obtained in the step S1, extracting features of different layers of the convolution neural network model, and combining the features to obtain image feature representations; S4, classifying the image features obtained in the step S3 by using the SVM classifier, completing the crop image classification, obtaining the classification result, and finally inputting the crop image captured by the unmanned aerial vehicle into the convolution neural network model in the step S3 for recognition. The invention can more effectively identify the target image data by using the labeledsample of the target image under the condition that the image data set is limited.

The invention relates to a method for extracting incomplete data symmetry characteristics based on an extended Gaussian ball and M estimation, belonging to the field of computer vision. The method disclosed by the invention comprises the following steps of: (1), scanning a defect facial model by adopting a method based on a three-dimensional scanner so as to obtain initial mirror image data; (2), establishing a spatial topological relationship between a point and a point by adopting a topological structure based on spatial rasterization so as to eliminate noise point cloud, performing K neighbourhood searching, and then, establishing the extended Gaussian ball through normal information so as to find out a corresponding point; (3), roughly aligning the corresponding point based on a principle axis; (4), finely aligning in combination with an M estimation ICP algorithm; and (5), performing least square fitting of a point set in the corresponding point to calculate a central symmetry surface. According to the method disclosed by the invention, the extended Gaussian ball and advantages of an improved ICP algorithm are combined; therefore, characteristic extraction can be carried out more precisely; and more characteristic extraction complex conditions can be satisfied.

The invention discloses a high-resistance grounding fault detection method based on a flexible DC distribution network. The high-resistance grounding fault detection method comprises the steps of: firstly, extracting a feature model IMF1 component of a transient zero-mode current by adopting a complementary ensemble empirical mode decomposition algorithm, performing first-order differentiate operation on the IMF1to obtain a sudden change singular point, calculating a cumulative slope sum in the vicinity of the singular point, and distinguishing a faulty state and a normal state through comparing a slope sum value with a starting threshold value; and secondly, adopting a Prony algorithm for carrying out parameter identification on the IMF1 component to obtain a feature frequency component and a direct current component in the IMF1 component, calculating an energy ratio of the feature frequency component to the direct current component, and further distinguishing different states according to the difference of the energy ratio numerical values. Compared with the existing methods, the high-resistance grounding fault detection method can adapt to accurate feature extraction under a strong noise environment, has the advantages of self-adaptability, convenient application and high detection precision in the feature extraction process, can determine the operating state of the distribution network system incisively, and increases the calculation speed.

The invention discloses an analysis method for recognizing attack behaviors of group-housed pigs through employing the machine vision technology. The method comprises the steps: extracting an attack key frame sequence from a downward view group-housed pig video, and locating an attacking pig; taking the attacking pig as the whole body for the extraction of the acceleration characteristics; carrying out the training of the acceleration data, obtaining an acceleration threshold value, and dividing the key frame into a high-level frame, a middle-level frame and a non-attack frame according to thethreshold value; finally setting a minimum unit of the attack recognition, and classifying the group-housed pigs into high-level, middle-level and non-attack group-housed pigs according to the proportion of the attack frame in the unit. The method is used for the recognition of attack behaviors of the group-housed pigs through the machine vision technology, does not causes any impact on the group-housed pigs, provides a theoretical basis for the exploration of the attack rule, the evaluation of the damage level and the determination of manual intervention, and also provides reference for thedetection of abnormal behaviors of other livestock based on the accelerated movement.

The invention belongs to the field of image classification, and relates to a super-large image classification method based on a graph neural network. Different sub-image screening methods can be adopted for different super-large images, and the feature extraction network is further adjusted, so that feature extraction of the sub-images is more accurate; a super-large image is constructed into image data; a differentiable pooling operation is introduced into a traditional graph convolutional neural network; and global information of the super-large image can be mined, feature information of a hidden layer can be mined in the training process through micro-pooling operation, the relevance of all the sub-images in the feature space is fully analyzed, and the super-large image can be classified more accurately.

The invention discloses an improved empirical mode decomposition method for fault diagnosis of ship electric propulsion system, which comprises the following steps: obtaining fault data of ship electric propulsion system; improved empirical mode decomposition (EMD) being used to obtain the intrinsic mode function (IMF) data from the fault data; RBF neural network being used to analyze the intrinsic mode function data of different parts and the fault reason is obtained. The improved Empirical Mode Decomposition (EMD) process is as follows: signal input; determining an initialization parameter Tby using the cosine window definition; the original data are extended by genetic algorithm. Windowing the data to improve the endpoint effect; Empirical Mode Decomposition for Eliminating Modal Aliasing of Data; The intrinsic mode function data are intercepted. An improved empirical mode decomposition (EMD) method for fault diagnosis of ship electric propulsion system is disclosed, which is suitable for non-stationary, non-linear and multi-component signal characteristics of ship propulsion system fault, so as to improve fault signal analysis capability.

The invention relates to the technical field of computers, and provides a variable binning method, a variable binning device, terminal equipment and a storage medium. The variable binning method comprises the steps of acquiring sample data; according to preset variable configuration, determining nominal variables to be binned and feature values corresponding to the nominal variables from the sample data; storing the feature values into a preset feature value set; aiming at each feature value in the feature value set, diving the nominal variables into two bins by using the feature value as a test split point, and computing an associated index value corresponding to each feature value; using the feature value corresponding to the maximum in the associated index values as a target split pointto execute a binning operation; and removing the feature value from the feature value set; and when a binning result reaches a preset bin number threshold, stopping binning, and otherwise, continuously executing the binning operation. According to the technical scheme provided by the invention, the binning operation is automatically performed on the nominal variables based on the associated indexvalues, manual intervention and consumed time are reduced, and the binning efficiency of the binning operation is improved.

The invention relates to an image recognition method and device, computer equipment and a storage medium. The method comprises: acquiring a to-be-processed image through the computer equipment; carrying out feature extraction on the to-be-processed image by adopting a preset identification model to obtain an identification vector, wherein the recognition model is a model obtained by training by adopting an attention mechanism and adopting a dense loss function, and the recognition vector is used for representing a plurality of local features of the to-be-processed image; and performing image recognition on the recognition vector to obtain a recognition result. With the adoption of the method, the accuracy of image recognition under the conditions of shielding or large-angle shooting and the like is greatly improved.

The invention discloses a feature extraction method for motor imagery electroencephalography signals. The method includes the steps that the optimal time period for feature extraction of motor imageryelectroencephalography signals is determined according to the average power spectrum, then, four-layer double-tree complex wavelet decomposition is performed on the motor imagery electroencephalography signals within the time period, signal reconstruction is performed with the complex wavelet coefficient of each sub-band, and the average energy feature of data in the optimal time period of the reconstructed signals is calculated to serve as the time-frequency feature of the motor imagery electroencephalography signals; an IL-MVU algorithm is proposed to perform dimensionality reduction on thedata in the optimal time period of the reconstructed electroencephalography signals, low-dimensional vectors obtained after dimensionality reduction are taken as nonlinear features of the motor imagery electroencephalography signals, and finally standardization and feature fusion are performed on the time-frequency feature and nonlinear features of the motor imagery electroencephalography signalsin the optimal time period to obtain feature vectors of the motor imagery electroencephalography signals. The method greatly reduces the time consumption of the algorithm and improves the classification accuracy of the MI-EEG signals.

The invention provides a three-dimensional point cloud scene segmentation method and system fusing image features, relates to the technical field of computer vision, and can realize effective fusion of a two-dimensional image and a three-dimensional point cloud and accurate segmentation of a three-dimensional scene. The method comprises the following steps: S1, acquiring two-dimensional data, point cloud data and depth data including an image, and calculating an association relationship between a scene image and a point cloud according to the acquired data; s2, performing feature extraction on the two-dimensional data to obtain a high-dimensional to-be-fused feature map; s3, fusing the to-be-fused feature map and the point cloud data according to a fusion strategy to obtain fused point cloud data; the fusion strategy comprises the following steps: by searching for a pixel adjacent to a certain point cloud data, warping a feature corresponding to the pixel to the point cloud data; and S4, inputting the fused point cloud data into the three-dimensional segmentation network for feature extraction, thereby obtaining required global and local semantic information. The technical scheme provided by the invention is suitable for a three-dimensional point cloud processing process.

The invention provides a vibration type flow meter characteristic signal extraction method based on improved assemble average empirical mode decomposition. The method includes the steps of conducting end continuation processing on a collected vibration type flow meter flow vibration signal through a waveform-matched self-adaption end continuation method, conducting envelope line fitting on the collected vibration signal through a cubic B-spline method, conducting MEEMD decomposition to obtain a plurality of IMF components, conducting relevance analysis on the IMF components and the original signal, selecting the useful IMF components, conducting HHT conversion on the IMF components, and obtaining the Hilbert time-frequency spectrum and the marginal spectrum of the flow signal, wherein the Hilbert time-frequency spectrum and the marginal spectrum are the signal characteristics of the vibration type flow meter flow vibration signal. The method is suitable for accurately and rapidly metering the pipe network fluid flow in the industrial field.

The invention provides a face image processing method, which comprises the following steps that: a first face image and a second face image of the face of the same person are received, wherein the first face image comprises a first face part and a first background part, and the second face image comprises a second face part and a second background part; the first face image and the second face image are stored in an image database; the first face part is extracted from the first face image, and the second face part is extracted from the second face image; a first face feature vector of the first face part and a second face feature vector of the second face part are extracted; and a face owner of the face contained in the first face image and the second face image is judged according to the first face feature vector and the second face feature vector. The pertinence and the accuracy of the face recognition and detection are effectively enhanced.

The invention discloses a three-dimensional point cloud head posture estimation system and method based on ordered regression and soft labels. The system comprises a feature learning network module which is used for the layered feature extraction of point cloud data; the prediction network module is used for mapping the features obtained by the feature learning network module to a head attitude angle to obtain an angle prediction value, and substituting the angle prediction value and the head attitude angle serving as a label into a first loss function; the sorting network module is used for carrying out dimension division on the head attitude angle to form a plurality of subtasks, generating a soft label according to the relationship between the head attitude angle serving as a label andthe subtasks, carrying out value prediction on the features obtained by the feature learning network module, and substituting the value prediction of the point cloud data and the soft label into a second loss function; network updating module. The loss of the sorting network module and the loss of the prediction network module are combined to introduce the sorting network so as to guide the learning of the prediction network, so that the feature extraction is more accurate, and the precision of the prediction network is improved.

The present invention provides a method and a device for feature extraction for voice replay detection. The method comprises the steps of: performing 1.5 dimension spectrum estimation of obtained voice signals, and obtaining 1.5 dimension spectrum features of the voice signals; employing a warping function to perform subsection normalization of an energy distribution function of a frequency domainspace of the voice signals, and obtaining energy distribution features of the voice signals after normalization; and performing fusion of 1.5 dimension spectrum features of the voice signals and energy distribution features after normalization, and obtaining 1.5-SFED (1.5 Spectrum Fuse Energy Distribution). The method and the device for feature extraction for voice replay detection can improve the accuracy of voice replay detection.

The invention provides a behavior recognition method based on graph convolution and a capsule neural network. The method comprises the following steps: obtaining space coordinates of a human body articulation point in each frame of a human body continuous action image through manual marking, and further constructing space coordinate vectors of the human body articulation point; mapping the space coordinate vectors into high-dimensional feature vectors through a multi-layer perceptron, and constructing an articulation point adjacency matrix in combination with an action association principle; constructing a speed space vector of the articulation point according to the space coordinates, and further constructing an acceleration space vector of the articulation point; using a convolutional neural network to extract features, using a capsule neural network for action classification, and constructing a capsule convolutional neural network through series connection of the convolutional neural network and the capsule neural network; and repeating multi-generation training on a training set to obtain a trained capsule convolutional neural network. The method conforms to the features of actual motion, propagation of the features on the graph better conforms to the actual situation, the features can be effectively reserved for classification, and the recognition capability of the model is improved.

The invention provides an Open Pose-based monocular camera gesture language recognition method comprising the steps of collecting video data of gesture language of a presenter with a video camera; inputting the collected video data to an OpenPose system and primarily extracting three-dimensional characteristic data containing x-axis coordinates, y-axis coordinates and the confidence coefficient; selecting primarily extracted characteristic points, rebuilding a coordinate system with the neck as the origin, performing normalization in the x-axis direction and the y-axis direction to obtain final characteristic data; scanning the characteristic data by using three different granularities to obtain expansion characteristic data; inputting the expansion characteristic data to a deep forest model for multi-layer meaning recognition and obtaining recognition results of final meaning through an extreme classifier from the output of the last layer. The method has the capability of monocular vision recognition of gesture language, does not need big sample data and has the advantages of accurate characteristic extraction, simple process and high meaning recognition accuracy.

The invention discloses a pulse wave signal processing method based on the Kings' pulse theory and a lung cancer detection system. The pulse wave signal processing method comprises the steps that original pulse wave signals are preprocessed, wherein the original pulse wave signal at the position of the wrist radial artery are collected by using a Kings' pulse theory pulse meter, the collected signal is subjected to processing and data analysis in the time and frequency domains, and then the high-frequency noise parts of the signals are removed by using a Gaussian filter; the pulse wave signals are segmented periodically, wherein the baseline drift of the processed pulse wave signals is removed by using an iterative sliding window algorithm, and the continuous periodic signals are segmented into singly periodic pulse wave signals; the features of the pulse wave signals are extracted, wherein the pulse wave features are extracted from the obtained singly periodic pulse wave signals based on the Kings' pulse theory; the pulse wave signals are classified, wherein a CSVM is taken as a classifier, and the normal or abnormal or invalid pulse wave signals are distinguished based on the extracted pulse wave features. In the pulse wave signal processing method, the ISW algorithm is beneficial to the classification of the CSVM classifier, and the classification accuracy is improved.

The invention discloses a model training method and a device, a point cloud missing completion method and a device, electronic equipment and a computer readable storage medium. The model training method comprises the steps of obtaining training missing point cloud data; inputting the training missing point cloud data into an initial model to obtain training repair point cloud data, and adjusting parameters of the initial model based on the training repair point cloud data and original point cloud data corresponding to the training missing point cloud data; if it is detected that the training completion condition is met, determining that the initial model is a point cloud completion model; wherein the initial model comprises a target reconstruction network and an initial generation network, the target reconstruction network comprises a target coding network, the target coding network uses training missing point cloud data to carry out comparative learning, the training missing point cloud data is input into the target coding network to obtain input features, the input features are input into the initial generation network to obtain missing point cloud data, the missing point cloud data is used for generating training repair point cloud data; and the accuracy of the processed point cloud data after completion processing is improved.

The invention belongs to the technical field of digital image processing, and discloses a dual-Gabor palm print ROI matching method based on specific expanded eight neighborhoods. The dual-Gabor palm print ROI matching method comprises inputting an ROI image of a palm print to be matched and an ROI image of a template palm print, and carting out dual-Gabor filtering; carrying out orientation coding processing and obtaining coded images; carrying out normalized coding on the variation degree of the coded images, and screening out a point the variation degree of which is highest; carrying out image pyramid calculation on the two coded images to obtain 1, 1 / 2 scale transformation images; obtaining the offset of a sampling point of the image in each scale, and finding out the position of the sampling point after offset; obtaining a preliminary matching score by calculating relative positions between the sampling points and the relative positions between the sampling points after offset; calculating the overlap ratio of the two palm prints which are subjected to variation degree normalized coding, and obtaining a final matching score by combining with the preliminary matching score; and judging whether the matching is true by means of a set fixed threshold. The dual-Gabor palm print ROI matching method based on specific expanded eight neighborhoods can carry put palm print image ROI matching accurately.

The invention provides a localized face recognition method to reduce the complexity of face recognition. According to the method, processing of face recognition data and feature extraction of face texture information can be accurately realized, various defects in the prior art are overcome, and the algorithm is relatively simple and easy to realize.

To reduce the complexity of a face recognition algorithm, the invention provides a quick face recognition system based on personalized features especially lip images. The system reads face image dataof a person. Lip images at the same angle are collected at first, and then identification is conducted on the basis of a lip in the lip images and image data of other parts.

The invention discloses a rock image retrieval method which comprises: acquiring image data in real time, and inputting the image data into a trained deep learning network model to obtain a retrievalresult graph. The training process of the deep learning network model comprises: constructing a rock image data set by utilizing collected image data; inputting the data set into a network, and enabling the network to actively convert feature mapping in space after the data set is processed by a space transfer module; and inputting the processed data into a multi-granularity network, calculating atotal loss function and an mAP value of the model, and after multiple calculations, when the loss function tends to be stable and the mAP value reaches a peak value, completing training of the deep learning network model. The situation that only representation is used for classifying the rock images is avoided, meanwhile, the fine-grained characteristics of the rock images are extracted more accurately, and the retrieval accuracy of the rock images can be improved under the conditions that sundries are shielded, the number of samples is small, the quality is low, and information is lost.

The invention relates to a micro-expression recognition financial risk control method. The method comprises: obtaining and preprocessing image frames of a video; detecting the preprocessed image frameto obtain a micro-expression frame sequence in the image frame; extracting the detected micro-expression frame sequence to obtain micro-expression features; inputting the obtained micro-expression features into a trained convolutional neural network for classification; and performing psychological analysis on a classification result of the convolutional neural network, and estimating a fraud riskvalue. The invention further relates to a micro-expression recognition financial risk control system. According to the method, the potential fraud risk of the lending user is judged in a mode of combining micro-expression recognition and psychology, a more accurate financial fraud recognition method can be provided for a cash lending company, and the economic loss of the cash lending company is reduced.

The present invention discloses a method and a system for smog recognition based on a LBP (Local Binary Patterns) Gaussian pyramid. Suspected smog area images are subjected to graying and then twice Gaussian smoothing and sampling to obtain grey-scale maps with 1 / 4 and 1 / 16 sizes, and the grey-scale maps with 1 / 4 and 1 / 16 sizes are combined with an original image grey-scale maps to form three layers of pyramid images; LBP operators of P being equal to 8 and R being equal to 1 are employed for the three layers of Gaussian pyramid grey-scale maps to calculate and obtain binary system LBP codes of the three layers of Gaussian pyramid grey-scale maps, a rotation invariant mode and an equivalent mode are employed to perform dimension reduction of each layer of LBP codes, nine types of LBP codemodes are obtained, and statistics of the number of each type of LBP codes are employed to take the number of each type of LBP codes as one feature value; and AdaBoost input vectors are formed by employing 27 feature values of the three layers of LBP Gaussian pyramids for discrimination of smog and false smog interference. The method provided by the invention has good robustness and high recognition rate.

The embodiment of the invention provides a banknote authenticity identification method and device. The method comprises the steps that the characteristic area including the denomination number is cutfrom the banknote grayscale image obtained through infrared scanning; the boundary information of the included denomination number in the characteristic area is determined; the projection informationof the characteristic area is obtained according to the boundary information; and the banknote authenticity is determined according to the projection information. With application of the technical scheme, characteristic extraction of the characteristic area can be accurately performed through the determined boundary information and then the banknote authenticity can be determined according to theprojection information of the boundary information so that the accuracy of banknote authenticity identification can be greatly enhanced.