190 results about "Hausdorff distance" patented technology

System and method for the indexing and retrieval of semantically annotated information units from a collection of semantically annotated indexed information units in response to a query using an ontology-based IR model. The retrieval method comprises: receiving a semantically annotated query with semantic annotations to individuals or classes within a determined populated base ontology; embedding, as a set of weighted-mentions to individuals or classes within the populated base ontology, the semantically annotated query in a semantic representation space of an ontology-based metric space IR model; obtaining the representation in the semantic representation space for every indexed information unit; computing the Hausdorff distance between the space representation of the query and the space representation of all the indexed information units of the collection; retrieving and ranking, the relevant information units based on the computed Hausdorff distance.

The present invention provides a method for the recognition of objects in an image, where the objects may consist of an arbitrary number of parts that are allowed to move with respect to each other. In the offline phase the invention automatically learns the relative movements of the single object parts from a sequence of example images and builds a hierarchical model that incorporates a description of the single object parts, the relations between the parts, and an efficient search strategy. This is done by analyzing the pose variations (e.g., variations in position, orientation, and scale) of the single object parts in the example images. The poses can be obtained by an arbitrary similarity measure for object recognition, e.g., normalized cross correlation, Hausdorff distance, generalized Hough transform, the modification of the generalized Hough transform, or the similarity measure. In the online phase the invention uses the hierarchical model to efficiently find the entire object in the search image. During the online phase only valid instances of the object are found, i.e., the object parts are not searched for in the entire image but only in a restricted portion of parameter space that is defined by the relations between the object parts within the hierarchical model, what facilitates an efficient search and makes a subsequent validation step unnecessary.

The invention provides a fingerprint and finger vein bimodal recognition decision level fusion method. Two modules, namely a fingerprint module and a vein module are included. The fingerprint module and the vein module read fingerprint images and vein images; the read fingerprint images and vein images are subjected to image quality evaluation according to respective image characteristics to acquire quality scores; the fingerprint images and vein images are preprocessed and recognized, wherein the fingerprint recognition adopts a minutiae-based matching method and the vein recognition adopts an improved Hausdorff distance mode, and respective recognition results are obtained; and finally, a weight is designed according to image quality scores of the two modes, and the recognition results are subjected to decision level fusion according to the weight and a final recognition result is obtained. Based on the fact that the performance of the system after fusion is superior to that of a single fingerprint recognition or finger vein recognition system, the method has strong practicability.

The present invention provides a Satellite-bone camera space image distortion correction method based on the stellar map matching, the stellar point on the image is used as referecen point, achieving the distortion correction, including following steps: (1)image segmentation, extracting the stellar facula in the image; (2) calculating areal coordinates of each facula by the centroid method, as a real coordinate; (3) processing pre-correction according to the deformation parameter obtained by the ground standardization of the camera; (4) processing stellar map matching by single frame or multiple frames Hausdorff distance stellar map matching method, calculating academic coordinate corresponding to the practical coordinate; (5) calculating deformation parameter of the image by the corresponding relation between the practical coordinate and the academic coordinate; (6) obtaining corrected image by the three steps fitting of a polynomial and interpolation method. In addition, the invention aiming at correctoon impact of the camera plain shaft point system error, provides a adaptive compensation method. The invention has small operation, evident image correcting effect, and effectively preventing the impact of the correction caused by the image noise and the input system error.

The invention provides a secondary classification fusion identification method for fingerprint and finger vein bimodal identification. A fingerprint module and a vein module are used as primary classifiers, and a secondary decision module is used as a secondary classifier. The method comprises the following steps of: reading a fingerprint image and a vein image through the fingerprint module and the vein module; pre-processing the read images respectively and extracting characteristic point sets of the both; performing identification on the images respectively to obtain respective identification results, wherein the fingerprint identification adopts a detail point match-based method, and the vein identification uses an improved Hausdorff distance mode to perform identification; forming a new characteristic vector by using the extracted fingerprint and vein characteristic point sets in a characteristic series mode through the secondary decision module so as to form the secondary classifier and obtain an identification result; and finally, performing decision-level fusion on the three identification results. The method has the advantages of making full use of identification information of fingerprints and finger veins, and effectively improving the accuracy of an identification system, along with high identification rate.

The invention discloses a tracking and recording method for a single moving target track by adopting a computer program, which aims to overcome the problem that the tracking and recording of a moving target track occupies large storage space. The method adopts the steps of installing a hardware system, extracting a target contour, making template matching and track recording to the target contour. Extracting a target contour is to adopt a tth frame image, a (t-1)th frame image and a (t+1)th frame image of a target video; the steps such as three-frame differencing operation, 'AND' operation, median value filtering and extracting an actual contour and so on, are made. Making template matching and track recording to the target contour adopts to find the centroid position of a target and store the centroid position; the stored information of the centroid position is made a distance transformation and is matched with Hausdorff distance; the actual shape of the target is stored; then the (t+1)th frame image is extracted, the steps such as matching and storage and so on, are made according to the flow of extracting the target contour and the method of making template matching and track recording to the target contour; the steps are circularly made.

The invention discloses an image matching algorithm of bonding point characteristic and line characteristic descriptors. The method comprises the following steps: (1) carrying out angle point extraction on a template drawing and a real-time drawing under multiscale; (2) acquiring an edge set surrounding angle points of the real-time drawing and the template drawing; (3) calculating a class ORB point characteristic descriptor of real-time drawing and template drawing angle points which are acquired from the step 1 and are selected finally; (4) using a minimum cut square Hausdorff distance to describe a matching similarity of the real-time drawing and template drawing edge set acquired from the step 2; (5) calculating a matching similarity of the class ORB point characteristic descriptor of the real-time drawing and template drawing angle points, wherein the characteristic descriptor is acquired from the step 3; (6) matching result integration. In the method of the invention, firstly, a stable point characteristic is used to carry out primary selection on the angle points so as to acquire a candidate point set and a correct position is included; then a global line characteristic is used to screen the candidate point set so that a repetition mode can be reduced and a correct rate is increased.

The invention provides a transformer excitation inrush current and fault differential current recognition method based on a Hausdorff distance algorithm. The transformer excitation inrush current and fault differential current recognition method comprises the steps of: acquiring secondary currents of current transformers at two differential protection sides of a transformer on each cyclic wave N point, and form a differential current signal sequence I; judging whether a value of the differential current signal sequence I exceeds a setting valve of a differential protection starting component, and starting a criterion disclosed by the invention for distinguishing a fault differential current and an excitation inrush current if the value exceeds the setting value differential protection starting component; judging and acquiring an extreme value of the differential current signal sequence I by adopting a 1/4 cyclic wave data window, regarding a differential sequence A after per-unit treatment as an edge feature point of a Hausdorff distance algorithm object graph, regarding a standard sine sequence B with amplitude being 1 as an edge feature point of a Hausdorff distance algorithm template graph, comparing an Hi value with a set Hausdorff distance threshold value Hset, and conducting protection action if the Hi value is less than the threshold value; and blocking protection if the Hi value is greater than the threshold value. The transformer excitation inrush current and fault differential current recognition method is used for directly judging difference of waveform pattern overall features of inrush currents including symmetric inrush currents, and ensures correct action of transformer differential protection.

The present invention discloses a thymic cell image segmentation method based on an improved U-Net network, which comprises the following steps: carrying out image preprocessing on a UCSB breast imagedata set; in a U-Net network, adding a void residual module and an attention module; training the U-NET network according to the set training strategy; setting up the evaluation indexes including F1score, object-level Dice coefficient and Hausdorff distance. The optimal model is obtained by optimizing the network through the evaluation indexes. The cell image to be segmented is inputted into theoptimal model, and the segmentation mask is obtained by feature extraction and feature upsampling. By improving a basic segmentation network and creating a new cell image segmentation method, the invention solves the problem of low precision in the automatic segmentation process of the thymus image, and improves the accuracy and efficiency of the segmentation.

The invention discloses an image registering method for a panoramic assisted parking system. The method comprises the following steps of: (1) acquiring image data of a reference image and an image to be registered; (2) performing histogram equalization and Gauss smooth filtering pre-processing; (3) selecting characteristic points with a Hrris comer extraction method respectively; (4) performing sub-pixel correction with a Taylor polynomial; (5) coarsely matching the reference image with the image to be registered; (6) accurately matching the reference image with an image to be matched with a Canny operator and a Hausdorff distance algorithm; (7) performing spatial transformation processing on image points to be matched with an affine transformation model; and (8) fusing an affine transformation coordinate with the reference image which is accurately matched in the step (6) so as to output a registering image, wherein each affine transformation coordinate corresponds to each image point in the to-be-matched image acquired in the step (7). The image registering method has the advantages of small calculation amount, high accuracy and high robustness in the splicing process.

The invention belongs to the technical field of precision machining and measurement, and discloses a complex curved surface part point cloud reduction method capable of effectively keeping boundary and local features. The method comprises the following steps: generating a scanned point cloud of a complex curved surface part; obtaining a plurality of neighborhood points for each point in the point cloud and calculating each normal line vector; finding out m points within the shortest radius range with each point being as the centre of sphere, and then, calculating the average value of included angles between the normal line vectors of the points in the point cloud and the normal line vectors of the m points; setting a threshold value based on the average value of included angles, and then, carrying out feature coarse classification; carrying out secondary subdivision to finish selection of a first reduction subset, and then, calculating directional Hausdorff distance to finish selection of a second reduction subset; and finally, merging the two reduction subsets to obtain a reduced scanned point cloud. Compared with the prior art, the method can achieve higher precision and efficiency, and can effectively keep the boundary and local features of the point cloud model.

The invention relates to a method for picking up and identifying human ear characteristic by means of improved Hausdorff distance. The invention obtains standard human ear image through pretreatment of human ear image such as collection of human ear images, denoising of non-complexion noise, normalization of space dimension and illumination compensation; then, gray scale morphologic gradient and local threshold subdivision are adopted to pick up human ear edge feature so as to obtain standard human ear edge image. With the method and the Hausdorff distance improved through the length difference between standard variance and edge line segment, the influence of point set non-outline edge line segment point (outfield point) is reduced so as to obtain better anti-noise performance; moreover, the invention increases the accuracy of human ear edge image recognition by means of the characteristic value obtained on the basis of Hausdorff distance, thereby greatly increasing human ear recognition rate.

The invention relates to the technical field of user behavior trace mining, in particular to a user behavior similarity mining method based on the space-time mode. The space-time mode matching method of a sign-in point set is designed to carry out user behavior mining on data in consideration of the condition that sign-in records of LBSN users are discontinuous and seriously fragmented; sign-in points are classified into a sequence subset and isolated points, and time sequence information in the sequence subset is reserved and effectively integrated with position information in the similarity comparison process. By means of the new space-time Hausdorff distance matching method, space-time mode similarity discrimination can be effectively carried out, behavior trace recovery of the sign-in points is not needed, the sign-in time sequence information is effectively utilized, and therefore the similarity of user sign-in behaviors can be well judged.

The invention discloses a method for controlling a hierarchical type route suitable for a wireless sensor network. The method comprises the following steps of: 1) sensing and storing a distance of a network topology formed from wireless sensor nodes in a random arrangement; 2) based on an order N neighbor theory, when the position of the sensor nodes and the network topology are changed dynamically, determining the number of current optimal clusters kopt by analyzing the distribution dispersion and the curved transition of the nodes; 3) computing an occupation ratio of optimal cluster heads popt according to the number of the optimal clusters kopt, and selecting cluster aggregation by combining node residual energy; 4) introducing Hausdorff distance to adjust a cluster structure formed initially and quickly; and 5) transmitting data: transmitting data information acquired by each of the sensor nodes to a base station by using the cluster heads. The method has the advantages of providing correct computation for the optimal clusters, saving energy consumption of each of the nodes, realizing load balancing of the wireless sensor network, along with uniformly distributed cluster headsand reasonable cluster structure.

The invention discloses a pole tower deformation detection method with constraint registration. The method includes steps: acquiring original three-dimensional point cloud data of an original pole tower; acquiring state three-dimensional point cloud data of a to-be-detected stage pole tower; denoising, and extracting axis of the pole tower; performing initial registration and fine registration; measuring an included angle between axis of the original pole tower and deviation state axis of the pole tower to acquire an inclination angle of the pole tower; calculating Eucidean distance from each spatial point on the deviated pole tower to the original pole tower, calculating Hausdorff distance between two denoised point cloud data after going through fine registration, and taking a ratio of the Eucidean distance to the Hausdorff distance as deviation amount of the pole tower; converting the deviation amount into a visual gray value to acquire a pole tower deformation deviation cloud chart. By the method, effective analysis of overall deformation of the pole tower is realized to directly acquire deformation degree of the pole tower in three-dimensional space; the method is high in detection accuracy and efficiency, low in cost, free of influence by outside environment and convenient to operate.

A medical image segmentation method includes: step 1, initialize of the number of clusters and determine the initial values of the cluster centroids; step 2, calculate a Hausdorff distance between each cluster centroid and each pixel in the image; step 3, calculate a membership function of each pixel based on the Hausdorff distance and a Euclid distance between the cluster centroids and each pixel; step 4, calculate an objective function, cluster the pixels of the image based on the updated membership function, and update the centroid value; and repeating step 2-4, until a difference between two objective function values is less than a threshold value. Then the membership function from the last iteration is a final segmentation.

The invention relates to a classifying and processing method based on an active shape model and a K nearest neighbor algorithm for facial forms of human faces; the method comprises the following steps of: (1) a sample database in the K nearest neighbor algorithm is established; (2) a user uploads images to be measured to a server through a network multi-media terminal, and the server extracts characteristic points of the human faces from the image to be measured by adopting an ASM (Automated Storage Management) algorithm and determines facial contours by selecting the characteristic points of the faces and lower jaws; (3) the server carries out normalization processing on point sets of the images to be measured according to a sample normalization method and integrates the point sets of the images to be measured and point sets of samples in a coordinate system; (4) the server classifies the images to be measured based on the Hausdorff distance and the K nearest neighbor algorithm to obtain a classifying result; and (5) the server automatically sends the classifying result to a network multi-medium terminal; and the network multi-medium terminal displays the classifying result. Compared with the prior art, the classifying and processing method has the advantages of high recognition rate, fast speed, easy implementation and the like.

The invention belongs to the crossing field of physical oceanography and computer graphics and image processing, and particularly relates to a mesoscale eddy tracing method based on a hybrid algorithm. The hybrid algorithm mainly comprises nearest neighbor search, deformation control based similarity match and delay logic. The method comprises the following steps: step one, for the nearest neighbor search, eddies in a search range are delineated according to global mesoscale eddy data recognized with an SSH (sea surface height) method; step two, for a deformation control based similarity match method, the eddies in the range and attributes of the eddies are subjected to similarity calculation of area, amplitude, kinetic energy, relative vorticity and Hausdorff distance, the eddy with the maximum similarity is selected as the position of the next eddy, and jump of an eddy path is avoided through combination of physical attributes and geometric attributes of the eddies; step three, the delay logic is adopted, search at multiple time points is considered, the eddies temporarily disappearing at certain time points are processed, and discontinuity of the eddy path is avoided, so that the purpose of multi-year long-term efficient tracing on the eddies is achieved.

The invention discloses a judging method of a suspension curve model for power line sag calculation, belonging to the technical field of installation and maintenance of power equipment. The judgment method comprises the following steps of: obtaining a power line image; extracting power line image characteristics; selecting a characteristic point set of single power line for sag calculation from power line image characteristic point sets; determining two end points of the single power line in the characteristic point set of the single power line and calculating a gradient k of a straight line for connecting the two end points; calculating tangency point coordinates of the straight line which takes the k as the gradient and the single power line; calculating parameters of the suspension curve model according to the tangency point coordinates; respectively determining a catenary curve, an inclined parabola curve and a horizontal parabola curve; respectively calculating Hausdorff distances between the single power line and the catenary curve, and between the inclined parabola curve and the horizontal parabola curve; and taking a model corresponding to the curve with the minimum Hausdorff distance as the suspension curve model for meeting the requirement of the power line. The judging method disclosed by the invention improves the precision of the power line sag calculation.

The invention discloses a distribution network fault line selection method based on a random matrix and a Hausdorff distance. Three-phase current sampling values of a feeder line before and after fault are selected, through blocking and translation processing, white Gaussian noise is added, a state data matrix is generated, a product matrix is obtained by using equivalent transformation of singular values of the random matrix, a standard matrix product is obtained by normalization, eigenvalue vectors are acquired, probability statistics is carried out, eigenvalue vectors with the probabilitiesP to be smaller than 10% are used as outliers to be filtered, a Hausdorff distance algorithm is adopted, the Hausdorff distances between the eigenvalue vector of a certain feeder line and the eigenvalue vectors of other feeder lines are calculated, the maximum value is removed, averaging is carried out to obtain an average Hausdorff distance of the feeder line, if the average distance is larger than a threshold, fault of the feeder line is judged, and if the average Hausdorff distance of each feeder line is smaller than the threshold, fault of a connected bus is judged. A fault feeder line and a fault bus can be judged accurately, the judgment does not rely on a distribution network model and is not influenced by a fault location, transition resistance, an initial phase angle and a line type, and the practicability is good.

The invention discloses a human body movement recognition method based on surveillance isometric mapping, and belongs to the field of pattern recognition and computer vision. The human body movement recognition method comprises the following steps; S1, performing foreground extraction through codebook method for the video to acquire a binarized human body foreground image; S2, performing morphology processing and normalization for the human body foreground image to acquire a human body silhouette image; S3, performing periodization analysis for the human body silhouette image sequence, wherein each video is represented by a series of key frames comprising a complete movement period; S4, performing vectorization for the key frames of the human body silhouette image, and performing characteristic dimension reduction through surveillance isometric mapping; S5, recognizing the characteristic after dimension reduction through the nearest categorizer according to Hausdorff distance. The human body movement recognition method breaks through the limitation of the conventional algorithm, and reduces complexity of the algorithm while increasing the categorizing accuracy, thereby being more feasible in practical engineering application.

The invention relates to a method for tracing text and strengthening multi-frame in a video. The texts in the video are mostly laminated in a complicated background, and if the texts are directly delivered into OCR (Optical Character Recognition) software for recognition, the recognition rate is low, therefore, the text strengthening operations are required to separate the texts from the background. The texts in the video mostly last for tens of frames, and even hundreds of frames, and in the adjacent frames, the colour of the texts are basically invariable but the background changes dynamically, accordingly, abundant complementary information between the multi-frames can be used for strengthening the texts. The method of the invention eliminates the influence of background edge pixel through the text stroke's characteristic of possession of edge pair, then uses Hausdorff distance measurement method for tracing the location of the texts at the adjacent frame, after obtaining a plurality of copies of the text images at the adjacent frame, makes use of minimum pixel searching method to remove the background in order to acquire binary text image including the clean background, greatly improving the rate of OCR software in identifying the video texts.

The invention discloses a static gesture identification method. The invention provides a gesture identification method based on HCDF (Hand Coordinate Distribution Feature) and similar-Hausdorff distance template matching. The static gesture identification method comprises the following steps: firstly, extracting a gesture feature vector by HCDF; then, carrying out similarity measurement to the extracted feature and a sample library to select M types of similar candidate samples; and finally, identifying a final gesture from the M types of similar candidate samples by the thought of the similar-Hausdorff distance template matching. The invention has beneficial effects that the static gesture identification method exhibits a higher identification rate if the static gesture identification method is compared with a HDF (Hand Distribution Feature), can accurately identify gestures of rotation, zoom and translation and still keeps the high identification rate for similar gestures with a small distinction degree. In addition, compared with a method that only the similar-Hausdorff distance is used for identification, the static gesture identification method is characterized in that identification speed is greatly quickened.

The invention discloses a steganography detection method for audio subjected to MP3Stego steganography. The method includes the steps of forming a sample library through MP3 compressed audio not subjected to steganography and MP3 compressed audio subjected to steganography, conducting double-compression coding on each sample to obtain carrier estimation of each sample, extracting a quantized MDCT coefficient of each frame in each sample to obtain a first coefficient matrix corresponding to the sample, extracting a quantized MDCT coefficient of each frame in the carrier estimation of each sample to obtain a second coefficient matrix corresponding to the carrier estimation, calculating a Hausdorff distance value between corresponding lines in each first coefficient matrix and the corresponding coefficient matrix to obtain the final steganography analysis characteristic line vector of each sample, obtaining a training template through SVM classifier training, and detecting the MP3 compressed audio to be detected through the training template. The method has the advantages that whether the MP3 compressed audio is subjected to MP3Stego steganography or not can be quite accurately determined, and particularly, the quite high detection efficiency can still be obtained under the condition that the steganography information embedment rate is low.

The invention discloses a three-dimensional face identification method with topology robustness. The three-dimensional face identification method with the topology robustness comprises the following steps of S1, carrying out preprocessing on three-dimensional face data in a test sample and three-dimensional face data of a training set and a test set in a three-dimensional face database, S2, building a model (X, dx) of a preprocessed three-dimensional face in a metric space, S3, calculating the similarity of the three-dimensional face by using the discretization Hausdorff distance as the similarity criterion of appearance matching of the three-dimensional face, and S4, determining a three-dimensional face identification result. According to the three-dimensional face identification method with the topology robustness, due to the facts that complementation between the advantages of the Euclidean distance method and the advantages of the geodesic distance method is achieved, a new ranging method with geometry meaning, namely, the dispersion distance method is formed in a combined mode, the dispersion distance can show the average distance between two points on a curved surface instead of only showing the shortest path, and the topology robustness is achieved, the geometric structural characteristics of the face can be kept, and the problem that the identification rate is reduced due to changes of expressions and changes of topology geometric structures is completely solved.