243 results about "Image vector" patented technology

An embodiment of the invention provides a method and apparatus for registering two medical images with one another. A first medical image including a representation of a biological organ of a subject or for a population is obtained and the surface of the organ is identified in the first medical image. The identified surface is then used to construct a 3D geometric surface model of the organ. The geometric model is used to derive a motion model that incorporates information on the physical material properties of the organ and external forces that cause the organ to move and deform. A second medical image including a representation of the organ of the subject (or another subject, in the case that the first medical image is an atlas image) is obtained and an alignment is determined between a first surface normal vector field for the organ surface, derived from the geometric model, and a second surface normal vector field for the organ surface, derived by filtering the second medical image. The alignment accommodates deformation of the geometric model in accordance with the motion predicted by the motion model. The first and second medical images can then be registered with one another based on said determined model-to-image vector alignment (MIVA).

Systems and methods for image pattern recognition comprise digital image capture and encoding using vector quantization (“VQ”) of the image. A vocabulary of vectors is built by segmenting images into kernels and creating vectors corresponding to each kernel. Images are encoded by creating a vector index file having indices that point to the vectors stored in the vocabulary. The vector index file can be used to reconstruct an image by looking up vectors stored in the vocabulary. Pattern recognition of candidate regions of images can be accomplished by correlating image vectors to a pre-trained vocabulary of vector sets comprising vectors that correlate with particular image characteristics. In virtual microscopy, the systems and methods are suitable for rare-event finding, such as detection of micrometastasis clusters, tissue identification, such as locating regions of analysis for immunohistochemical assays, and rapid screening of tissue samples, such as histology sections arranged as tissue microarrays (TMAs).

An image processing apparatus classifies a variation of a target object included in an image from a specific state as one of a plurality of types of attributes, and holds, for each variation attribute, a correction parameter for spatial transformation that corrects the target object to the specific state. The image processing apparatus generates an input image vector by vectorizing at least a partial region of the input image, and determines a variation attribute by detecting a variation of the target object from the specific state in the input image. Then, the image processing apparatus generates a transformed image vector by performing the spatial transformation on the input image vector, using a correction parameter selected based on the determined variation attribute from among the correction parameters held for respective variation attributes.

The invention discloses a no-reference structural sharpness image quality evaluation method, which comprises the following steps of: acquiring an original image input in a computer; preprocessing the original image, removing influence of isolated noise points on the sharpness of the original image and acquiring an original image to be evaluated; constructing a reference image for the original image to be evaluated through a low pass filter; respectively performing gradient calculation on the original image to be evaluated and the reference image, and extracting sub-image vectors with rich texture information; calculating the structural similarity between corresponding sub-image vectors so as to obtain structural similarity results of the sub-image vectors; and calculating no-reference structural sharpness by using the obtained structural similarity results of the sub-image vectors so as to obtain quality evaluation index no-reference structural sharpness of the original image. The reference image is constructed through an imaging model, no-reference image quality evaluation is performed by a reference image quality evaluation method aiming at image blurring, and the method is applied to the fields of imaging quality detection and control of an imaging system, evaluation of an image processing algorithm, and the like.

A system and a method for multimedia data analysis. The system includes a computing device. The computer device includes a processor and a storage device storing computer executable code. The computer executable code, when executed at the processor, is configured to: encode task description and task meta info into concatenated task vectors; encode context text and context meta info into concatenated context text vectors; encode context image and the context meta info into concatenated context image vectors; perform dual coattention on the concatenated task vectors and the concatenated context text and image vectors to obtain attended task vectors and attended context vectors; perform BiLSTM on the attended task vectors and the attended context vectors to obtain task encoding and context encoding; and decode the task encoding and the context encoding to obtain an answer to the task.

What is disclosed is a system and method for image reconstruction using a compressed sensing framework to increase the number of wavelength bands in hyperspectral video systems. The present method utilizes a restricted representation matrix and sampling matrix to reconstruct bands to a very large number without losing information content. Reference multi-band image vectors are created and those vectors are processed in a block-wise form to obtain custom orthonormal representation matrices. A sampling matrix is also constructed offline in the factory. The compressed sensing protocol is applied using a l1-norm optimization (or relaxation) algorithm to reconstruct large number of wavelength bands with each band being interspersed within the band of interest that are not imaged. The teaching hereof leads to very large number of bands without increasing the hardware cost.

The invention discloses a sensitive-image identification method and a system, and belongs to the technical field of image identification. The sensitive-image identification method and the system are characterized in that the following steps are comprised: a step 1, grid dividing characteristic extraction fused with skin color detection is carried out, and original bag-of-words expressing vectors of images are obtained through a bag-of-words model; a step 2, image characteristic optimization is carried out, and dimension-reduced optimization image vector expressions are obtained through the utilization of a random forest; a step 3, identification model training is carried out, that is to say through the utilization of a one-class support vector machine, a one class classifier is trained in optimization vector space; and a step 4, image identification is carried out, i.e., if the images completely do not contain skin color pixels in the pretreatment process of the step 1, the images are directly determined to be normal images; and otherwise, optimization characteristic expressions are obtained after processing, and the optimization characteristic expressions enter the one-class classification model obtained through the training, so that identification results of the images are finally obtained. According to the invention, a one-class classification algorithm is utilized to solve sensitive-image identification problem, and a plurality of techniques are fused in the processing process, and the characteristic optimization processing is carried out, so that the accuracy and the efficiency of the sensitive-image identification are improved.

The invention discloses a sparse representation face recognition method based on an intra-class variation dictionary and a training image, for solving the problems of limitation of the existing method in the aspects of small sample, uneven illumination, face shielded and expression variation and increasing the face recognition accuracy. The method comprises the following implementation steps of: (1) extracting image characteristics from a training image set and a test face image so as to form a training image matrix and a test image vector, and respectively normalizing the training image matrix and the test image vector; (2) collecting image texture differences of the same face in different external environments from a face database so as to form the intra-class variation dictionary of the face; (3) representing the test image as a linear combination of the training image matrix and the intra-class variation dictionary, and acquiring the optimal sparse representation coefficient through the L1 norm minimization criterion; and (4) acquiring a residual between the original test image and a recombination image recombined from each type of the training image and the intra-class variation dictionary, and substituting the residual into a type judgment formula so as to acquire a recognition result.

The invention discloses a method for clustering data in an image retrieval system, belonging to the technical field of information processing. The method comprises an off-line process and an on-line process, wherein the off-line process is characterized by extracting an SIFT (Scale Invariant Feature Transform) characteristic for a standard image, then the SIFT characteristic is subjected to off-line clustering processing, and a standard image vector is built by virtue of vectorization processing on the basis of the off-line clustering result; in the on-line process, the SIFT characteristic ofthe image to be retrieved is extracted; then, on the basis of the off-line clustering result, an image vector to be retrieved is obtained by virtue of the vectorization processing; and the image vector to be retrieved is subjected to similarity search in a standard image vector. By utilizing the method, the characteristics of strong representativeness and distinguishable capability in large-scaledata can be quickly obtained, the clustering of the large-scale data is achieved, and newly-added image data is subjected to quick incremental quantity and clustering on the basis of effectively reusing the clustering result of the original image data, thereby finally realizing a high-efficient image retrieval task.

A method of extracting feature vectors of an image by using local linear transformation functions, and a method and apparatus for image recognition employing the extracting method. The method of extracting feature vectors by using local linear transformation functions includes: dividing learning images formed with a first predetermined number of classes, into a second predetermined number of local groups, generating and storing a mean vector and a set of local linear transformation functions for each of the divided local groups comparing input image vectors with the mean vector of each local group and allocating one of the local groups to the input image; and extracting feature vectors by vector-projecting the local linear transformation functions of the allocated local group on the input image. According to the method, the data structure that has many modality distributions because of a great degree of variance with respect to poses or illumination is divided into a predetermined number of local groups, and a local linear transformation function for each local group is obtained through learning. Then, by using the local linear transformation functions, feature vectors of registered images and recognized images are extracted such that the images can be recognized with higher accuracy.

The invention discloses a guided filter and auto-encoder-based SAR target recognition algorithm. Aiming at the problem that the time is consumed as the recognition carried out on synthetic aperture radar (SAR) image targets via neural networks pursues high recognition rate and complex structures are designed, the algorithm applies a rapid image fusion technology to feature extraction of an SAR recognition technology, and uses a weighted guided filter (GF) to carry out two-scale fusion on the SAR images so as to generate one-dimensional image vectors, uses an auto-encoder to carry out low-dimensional feature reconstruction on the images, and uses a softmax classifier to carry out classification; and an image fusion technology of the weighted guided filter and feature extraction are combinedthrough experimental simulation and verification, so that the target recognition precision is improved, the quantity of hidden layer neurons of the auto-encoder is greatly decreased and the calculation complexity is greatly reduced.

Automatic face recognition. In a first example embodiment, a method for automatic face recognition includes several acts. First, a face pattern and two eye patterns are detected. Then, the face pattern is normalized. Next, the normalized face pattern is transformed into a normalized face feature vector of Gabor feature representations. Then, a difference image vector is calculated. Next, the difference image vector is projected to a lower-dimensional intra-subject subspace extracted from a pre-collected training face database. Then, a square function is applied to each component of the projection. Next, a weighted summation of the squared projection is calculated. Then, the previous four acts are repeated for each normalized gallery image feature vector. Finally, the face pattern in the probe digital image is classified as belonging to the gallery image with the highest calculated weighted summation where the highest calculated weighted summation is above a predefined threshold.

The invention discloses an image classification method based on a category correlated codebook and a classifier voting strategy. The method comprises the following steps of: expressing an image as a set of local salient region image blocks by an image data set pre-processing module; generating category correlated codebooks by a category correlated codebook generating module; expressing the image as an image vector by an image vectoring module, and training a classifier between two random categories by selecting the trained image vector and a category tag corresponding to the trained image through a category correlated classifier training module; and finally, determining the category tag of the tested image according to voting results by a classifier-voting-strategy-based tested image classifying module. The category correlated codebook generating module effectively solves the contradiction of dimension disaster caused by over large codebooks and judgment insufficiency caused by over small codebooks; and meanwhile, the category correlated classifier training module also gets rid of the problems caused by sample unbalance in multi-category classification, and the classification performance is improved.

The invention provides a similar video processing method and device based on artificial intelligence, electronic equipment and a computer readable storage medium. The invention relates to the big datatechnology in the field of cloud technology. The method comprises the following steps: carrying out multi-dimensional feature extraction processing on an image in a video, and carrying out fusion processing on extracted multi-dimensional feature vectors to obtain an image vector of the image; performing feature extraction processing on the audio in the video to obtain an audio vector; performingfeature extraction processing on the text in the video to obtain a text vector; performing fusion processing on the image vector, the audio vector and the text vector to obtain a video representationvector of the video; taking the vector similarity between the video representation vectors of any two videos as the video similarity between the two videos; and processing the two videos according tothe video similarity. According to the invention, the video processing precision can be improved.

The invention relates to the field of digital image measurement, and proposes a plant three-dimensional measurement method and system based on PTZ camera system parameters and video frames. The method comprises the steps: S1, the calibration of PTZ camera system parameters: an axial image distance, image space and object space corresponding coefficients, an image shift rate pitching value fitting equation and coefficients; S2, a corresponding image point rectification model: an inter-frame image vector conversion model, an optical axis movement vector, a corresponding image point two-dimensional rectification matrix, and differential optimization verification; S3, point cloud world coordinate algorithm: a corresponding image point three-dimensional matrix, an inter-frame double-optical-system vector projection relation model, a PTZ camera system movement vector measurement model, three-dimensional point cloud coordinate obtaining, and a gray scale material correction factor; S4, plant local measurement method. The system comprises the following parts: S1, a PTZ camera system parameter obtaining module; S2, a corresponding image point rectification module; S3, a three-dimensional measurement module; S4, a plant local measurement module. Compared with other digital mapping technologies, the method does not need an object space control point, is strong in environmental adaptation, is high in equipment compatibility, and reduces the cost.

The present invention provides a method for distinguishing one-dimensional distance image of non-library target which belongs to field of radar target recognition. Pretreatment with training vector of radar target one-dimensional distance image, subtracting equal value; determining kernel function, kernel matrix and nonlinear characteristics subspace combined by front q eigenvectors corresponding to most nonzero eigenvalue and nonlinear mapping of training one-dimensional image; determining projection of radar target one-dimensional distance image vector in nonlinear characteristics subspace and total library target template; determining judgement threshold of non-library target according to estimation of conditional mean and conditional root mean square difference of smallest distance of training target supposement; according to least Euclidean distance between target library template vector and projection of radar target one-dimensional distance image in nonlinear characteristics subspace to determine whether the input radar target one-dimensional distance image is belong to non-library target, if not belong to, the sort of input radar target one-dimensional distance image is determined. The present invention makes the one-dimensional distance image recognizer distinguish input is a non-library target and build training library actively.

The embodiment of the invention discloses a small sample learning method and device, electronic equipment and a storage medium. The small sample learning method comprises the following steps: encoding an image training sample set according to an image representation model to obtain an image matrix formed by image vector representation of each image training sample; encoding labels of the image training sample set according to a label preprocessing model to obtain a label matrix formed by label vector representation of each image training sample label; and performing back propagation according to the loss values of the image matrix and the label matrix to perform parameter optimization on the image representation model and the label preprocessing model so as to obtain a trained image representation model and a trained label preprocessing model. According to the invention, knowledge in a natural language task is introduced into a feature recognition task of an image, fusion of different task knowledge is realized, learning of image features under the condition of a small sample data set is accelerated, and efficiency and accuracy of image feature learning under the condition of the small sample data set are improved.

The invention provides an unmanned aerial vehicle path planning method and system, computer equipment and a readable storage medium. The method comprises the following steps of: obtaining a depth image in the preset space range of the current position of an unmanned aerial vehicle and the real-time flight attitude feature image vector of the unmanned aerial vehicle; extracting a feature image vector in the depth image through a target convolutional neural network model; carrying out fusion processing on the real-time flight attitude feature image vector and the feature image vector so as to obtain the fusion information of the unmanned aerial vehicle and an object contained in the depth image; inputting the fusion information into a target strategy network to obtain the target motion information of the unmanned aerial vehicle; and sending the target motion information to a flight control to realize the process of the path replanning of the unmanned aerial vehicle through the flight control. According to the method, the re-planned path information of the unmanned aerial vehicle for avoiding obstacles can be obtained at a time through the two-layer neural network model, so that the process of the re-planning the path of the unmanned aerial vehicle is realized, and the time of re-planning the path and the period of autonomous obstacle avoidance are shortened.

The invention discloses a face identification method based on a fuzzy rule. The face identification method is a novel feature extraction method and belongs to the field of face identification. The method comprises the steps that a face image is divided; sub-image variance and information entropy are calculated as the output of a fuzzy controller, so as to acquire the fuzzy weight of a corresponding sub-image; and LBP extraction is carried out on the sub-image to acquire a histogram vector and PCA dimensionality reduction is carried out on a sub-image vector after LBP extraction. The fuzzy weight has a significant feature for the image identification rate. Through PCA dimensionality reduction, the computation time of an algorithm is saved, and the timeliness of the algorithm is improved.

The invention relates to a medical X-ray device 5 arrangement for producing three-dimensional information of an object 4 in a medical X-ray imaging medical X-ray device arrangement comprising an X-ray source 2 for X-radiating the object from different directions and a detector 6 for detecting the X-radiation to form projection data of the object 4. The medical X-ray device 5 arrangement comprises: means 15 for modelling the object 4 mathematically independently of X-ray imaging and means 15 for utilizing said projection data and said mathematical modelling of the object in Bayesian inversion based on Bayes' formula p⁢(⁢x⁢m)=ppr⁡(x)⁢p(m⁢x)p⁡(m)to produce three-dimensional information of the object, the prior distribution ppr(x) representing mathematical modelling of the object, the object image vector x, which comprise values of the X-ray attenuation coefficient inside the object, m representing projection data, the likelihood distribution p(m|x) representing the X-radiation attenuation model between the object image vector x and projection data m, p(m) being a normalization constant and the posteriori distribution p(x|m) representing the three-dimensional information of the object 4.

The invention relates to a method and a device for examining money. The method for examining money comprises the following steps: training a single-class support vector model: according to a collected money image vector, carrying out algorithm training to obtain a single-class support vector and a vector model; scanning money images: scanning the images for preliminarily-examined money; extracting an image characteristic vector: processing a money image pixel characteristic into a standard matrix conforming to the input of the support vector machine, and extracting the money image characteristic vector; and identifying by a single-class classifier: calculating the extracted money image characteristic vector by the single-class support vector model, and judging the fact or fiction of the money according to a calculation result. According to the method and the device for examining money, the money is examined and identified by the single-class support vector model. Money examining technology with high precision and high reliability can be realized by the method and the device for examining money.

An age-converting method of human face based on average face and ageing scale map includes dividing human face to be shape vector and vein vector based on dense feature presentation, applying human face cartoon synthetic technique to finalize young conversion of specific human face by calculating difference between specific human face to average human face, combining human face image vector modeling with human face image ageing conversion for realizing human face image ageing analog in accordance with physiological feature.

A motion information recognition system takes time-series images of an object in motion and generates image vectors that are analyzed to produce a plurality of eigenvectors that are then stored. Inner product operations are performed between image vectors of a recognized object and a plurality of the stored eigenvectors for obtaining the motion information of the recognized object based on the result of said inner product operations to provide high-speed and easy motion information recognition at reduced computing cost.

The invention discloses a human face image age changing method based on average face and aging scale map, comprising the steps of: dividing the human face to be shape vector and vein vector with dense feature presentation; using a human face cartoon synthetic technique to complete young changing of specific human face by calculating difference between the specific human face and the average human face and further reducing the difference; and combining human face image vector modeling with human face image ageing changing for realizing human face image ageing analog in accordance with physiological feature. According to the changing of human face shape feature caused by aging, some feature line of the human face shape is modified so as to realize shape ageing analog; and for the change of vein feature, an aging scale map is prepared in a way of scale map, according to vein mapping, the vein feature aging analog of the human face shape is realized. The method fully considers the unified change of the shape and the vein when human face age changes, thereby greatly increasing the third dimension of synthetic image.

The embodiment of the invention provides a video-oriented super-resolution method and device, equipment and a storage medium. The video-oriented super-resolution method comprises the following steps:extracting a super-image based on continuous frame images in an original video; inputting the super-image vector corresponding to the super-image into a residual convolutional neural network to obtainan output result of the residual convolutional neural network; and inputting an output result of the residual convolutional neural network into a spatial upsampling network to obtain a super-resolution video frame, the super-resolution video of the original video comprising a plurality of video frames. According to the method provided by the embodiment of the invention, the time domain information in the original video is reserved on the basis of the super-image formed by the continuous frame images, and the residual convolutional neural network and the spatial sampling network are used for modeling the original video, so that the video super-resolution effect can be greatly improved under the calculation complexity of the same magnitude as that of the image super-resolution network.

The invention discloses a user profile vector generation method and device. The method comprises the steps of obtaining video information watched by a user according to a video click history of the user; searching a video description vector corresponding to a video according to the acquired video information, the video description vector being generated by analyzing an image contained in the video; and generating a user profile vector based on the found video description vector. Therefore, the image content description of the video is vectorized, and the user image vector is constructed basedon the watching history of the user, so that the description of the user profile can be quickly realized according to the watching behavior of the user. Furthermore, the user profile vector can be updated in real time in different modes according to the accumulation of the watching history, so that the description of the user profile is more accurate, and the generation and updating processes arelighter.

The invention discloses a hyperspectral remote sensing image vector C-V model segmentation method based on wave band selection. Firstly, according to a spectral curve, wave bands high in contrast ratio between a target and the background are selected, further, according to relevant coefficients of the wave bands, the wave bands high in relevancy are removed so that a new wave band combination can be formed, and therefore according to the determined wave band assembly, a hyperspectral image vector matrix is established; on the basis, a vector C-V segmentation model based on the vector matrix is constructed, the edge guiding function based on gradient is introduced into the model, on the basis that a traditional C-V model is reserved to perform image segmentation based on area information, the capacity for capturing the target boundary in heterogeneous areas and under complex background conditions is enhanced through edge detail information of images, segmentation precision of the hyperspectral remote sensing images is improved, segmentation speed of the hyperspectral remote sensing images is increased.