140results about How to "Rotation invariant" patented technology

The present invention provides a dynamic model directed angiography three-dimensional reconstruction method, pertaining to an intersectional field of digital image processing and medicine imaging, for satisfying special requests of auxiliary detection and surgery guidance for cardiovascular disease in clinical medicine. The invention includes steps of angiography image preprocessing, vascellum segmentation, vascellum skeleton and radii extraction, model directed vascellum base element recognition, vascellum matching and vascellum three-dimensional reconstruction. The invention also provides a cardiovascular dynamic model construction method including steps of cardiovascular slice data extraction, cordis static and dynamic model building, and static and dynamic model building. According to the invention, good angiography three-dimensional reconstruction result may be obtained, which effectively assists detection and surgery guidance for cardiovascular disease, thereby satisfying clinical requests.

The invention discloses a remote sensing image classification method based on an attention mechanism deep Contourlet network, and the method comprises the steps: building a remote sensing image library, and obtaining a training sample set and a test sample set; then, setting a Contourlet decomposition module, building a convolutional neural network model, grouping convolution layers in the model in pairs to form a convolution module, using an attention mechanism, and performing data enhancement on the merged feature map through a channel attention module; carrying out iterative training; performing global contrast normalization processing on the remote sensing images to be classified to obtain the average intensity of the whole remote sensing images, and then performing normalization to obtain the remote sensing images to be classified after normalization processing; and inputting the normalized unknown remote sensing image into the trained convolutional neural network model, and classifying the unknown remote sensing image to obtain a network output classification result. According to the method, a Contourlet decomposition method and a deep convolutional network method are combined, a channel attention mechanism is introduced, and the advantages of deep learning and Contourlet transformation can be brought into play at the same time.

The invention discloses a high-resolution remote sensing image plane extraction method based on skeleton characteristics, comprising the following steps: selecting a remote sensing image edge detection algorithm based on embedded confidence coefficient for edge detection, and realizing the remote sensing image edge detection algorithm based on embedded confidence coefficient; vectorizing a groundfeature target edge; extracting a ground feature skeleton base line from the vector edge of a ground feature based on a constraint Delaunay triangulation network algorithm; carrying out the target main skeleton extraction algorithm based on a binary tree structure; carrying out feature analysis on the target main skeleton of the plane; and realizing the automatic identification method of a plane target. By means of the invention, the plane target can be automatically identified and extracted and better identification extraction effect is obtained. The plane target skeleton has the excellent characteristics of rotation invariance and high discrimination index with other ground features, the vector edge of the ground feature target can be efficiently and precisely extracted from a remote sensing image with high spatial resolution, and the improved target skeleton can be extracted.

The invention provides an electrocardiosignal R peak detection method based on waveform characteristic matching. The method utilizes waveform characteristic matching to identify R peak of electrocardiosignal, the characteristic matching method takes difference vector between points as basic characteristic, the basic characteristic has translational invariance and rotational invariance and can overcome influence of baseline drift of electrocardiosignal signal; meanwhile, logarithm polar coordinate transformation is carried out on the difference vector and partition is carried out to measure similarity of wave form, the measurement is sensitive to the adjacent morphological characteristic, can capture global outline information of wave form and has robustness to wave form ripple; besides, influence of interference signal can be eliminated by setting proper threshold, and further accurate identification and detection on R peak of electrocardiosignal are realized. The invention is applied to related electrocardiogram analyser, accurate identification on R peak of electrocardiosignal can be realized, thus being beneficial to improving detection and analysis capability of electrocardiogram analysis equipment.

The invention relates to palm print identifying technology, and provides a palm print identifying method and a palm print identifying device aiming at the defects that the preprocessing requirement for the acquired palm print images is high in the prior palm print identifying technology, and the like. The palm print identifying method comprises the step of extracting the palm print characteristics of an image to be extracted, and the extraction specifically comprises the following steps: rotating and correcting the image to be extracted to generate a corrected image; carrying out convolution operation for the corrected image according to the preset Gabor wavelet, carrying out the operation of taking an amplitude value or a phase from the corrected image after the convolution operation, and generating a response image; and carrying out local binary mode characteristic extraction for the response image to acquire a local binary mode code of the image to be extracted so as to generate the palm print characteristics. The invention also provides the palm print identifying device. The technical proposal of the invention can provide rotational invariance and has high processing speed, so the technical proposal can achieve real-time palm print identification.

The invention relates to a tooth X-ray image matching method based on SURF point matching and RANSAC model estimation. The tooth X-ray image matching method includes the steps that (1), images are collected; (2), the images are enhanced; (3), features are extracted; (4), the features are matched; (5), related matching coefficients are calculated; (6), a matching result is displayed; (7), if reference images which do not participate in matching exist in an image library, the step (1) is carried out, a new reference image is selected from the image library, and if all images participate in matching, operation is finished; (8), matching succeeds, personal information corresponding to the reference images is recorded, and then operation is finished. The feature points of an input tooth image and a reference tooth image are extracted according to an SUFR algorithm, then the feature points are matched according to an RANSAC algorithm, and finally, the matching degree of the two images is measured according to the correlation coefficient of the two matched images. Experiment shows that by the tooth X-ray image matching method, the high precision ratio and high real-time performance are achieved.

The invention discloses a key point and local characteristic-based three-dimensional human face identification method. The method comprises the steps of preprocessing a three-dimensional human face model by human face region cutting, smoothing processing and pose normalization, and arranging all human faces in a pose coordinate system; detecting key points according to valuable contour lines and an average curvature; constructing a spatial structure of local characteristics in the form of a DAISY descriptor; adopting a shape index histogram, a slant angle histogram and a directional angle histogram as the local characteristics; and performing key point matching, and measuring the similarity of curved surfaces of two human faces by using the number of successfully matched key points. The method is relatively good in identification performance and has the robustness for expression change to a certain extent.

The invention discloses a pose measurement method combining initial pose measurement with target tracking, and belongs to the field of computer vision. The invention aims to realize real-time output of pose parameters of a moving target in a video sequence for an irregular moving target. The method is technically characterized by comprising the steps that initial pose measurement of a target is conducted, the initial pose measurement of the target is used for starting follow-up target tracking, and real-time output of pose parameters is achieved. The method comprises the steps of reference pose measurement, feature point extraction and matching and pose measurement based on multi-point matching. Target tracking comprises searching and matching of edge features, tracking and matching of point features and nonlinear optimization solution of pose parameters. According to the method, the initial pose of the target is combined with a target tracking method, so that real-time output of the pose parameters of the moving target in a video sequence is realized; the method has a certain adaptive capacity to the change of the environment, and the pose of the object can be measured when the object is partially shielded.

The invention relates to a matching method for three-dimensional coronary angiography reconstruction, which belongs to the crossing field of digital image processing and medical imaging, and aims to meet the special requirements on the auxiliary detection and the surgical navigation of angiocardiopathy in clinical medicine. The method comprises two steps, i.e. model guidance contrastographic picture vessel segment matching and contrastographic picture puncta vasculosa matching. The matching method uses a multi-scale vascular tree model so as to better guide vascular matching, simultaneously can well solve the problem of individual difference, and improves the matching precision of vessel segments and puncta vasculosa through the method of iterative matching and largest declination of searching potential energy. The matching method for three-dimensional coronary angiography reconstruction can obtain very good angiography matching results, thereby solving the difficult problems in the automatic three-dimensional reconstruction by the multi-view angiography map.

The invention provides a detection method for a fatigue state of a driver. Confidence coefficients are acquired through calculation by sending eye SIFT features into a classifying model; the opening-closing states of the eyes are determined according to the confidence coefficients without being affected by a human face angle; and the detection method has a rotation invariable property, high accuracy on eye detection, simple calculation process, and can detect the fatigue state of the driver in time and can satisfy real-time detection requirement. In addition, the invention also provides a detection system for the fatigue state of the driver.

The invention provides a circular center detection method based on Gaussian fitting sub-pixel edge detection and an improved RANSAC algorithm, belonging to the field of aircraft ground simulation. Themethod comprises the follow concrete steps: an original image is matched by a model and RIO processing is conducted on the image; edge pixel extraction and thinning is carried out; sub-pixel edge location based on Gaussian fitting is carried out; an improved RANSAC circle fitting algorithm is provided; the coordinates of the center of a circle are calculated. The invention roughly locates the position of the circular marker through a model matching mode, and performs RIO processing to reduce the size of image processing. Gaussian fitting improves the accuracy and stability of the algorithm. The improved RACNAC algorithm reduces the sampling times, optimizes and screens the candidate circles, reduces the running time and improves the accuracy and stability.

The invention discloses a different-source image fusion method based on salient target region extraction and NSST (Non-subsampled Shearlet Transform). The method comprises the following steps that: firstly, extracting the salient target region of an infrared image; carrying out registration on infrared and visible images to obtain an affine transform matrix; through the affine transform matrix, obtaining the position of the salient target region of the infrared image in the visible light image; carrying out NSST on the infrared and visible light image; utilizing different methods to carry outfusion on the NSST results of a target area and a non-target area of two images; and finally, through NSST inverse transform, obtaining a final fusion result. By use of the method, two different-source images of the infrared light and the visible light can be effectively fused, a fusion result can better highlight and keep the target, and the background detail information of the non-target area inthe visible light image can be more favorably kept.

This invention relates to a method and device to catch object from multiple point, which divides special capture space into multiple sub special capture spaces and divides the sub special capture space into multiple spaces from multiple visional point and comprises the following steps: establishing tree shape tester with one large branch; the branch covers all sub space with multiple branches with each one responding to one branch; adopting vector induction formula to train each branch into determine vector to determine each point to those down layer point; testing the sent point object as special object with relative visional angle.

The invention discloses a picture correction method and system based on an ORB algorithm. The ORB algorithm and perspective transformation are combined in use. The method comprises the specific operation steps of S1, feature point detection; S2, feature point description; S3, feature point matching; S4, preliminary screening of matching point pairs; S5, acquisition of first N optimal point pairs;S6, calculation of a homographic matrix H; and S7, image registration and correction. Compared with existing methods, the method has the remarkable advantages that operation speed is 100 times that ofa SIFT algorithm and 10 times that of a SURF algorithm, correction precision is higher than that of the SIFT algorithm and slightly lower than that of the SURF algorithm, the method has rotation invariance, and the noise sensitivity problem is solved, so that the final correction effect is certainly ideal; and during calculation of the homographic matrix H, a random sampling consensus (RANSAC) algorithm is adopted, so that the homographic matrix H is solved more robustly, and mistaken matching points are eliminated.

The invention discloses a detection identification method for a three-X combined mark, comprising the following three steps: 1. manufacturing the three-X combined mark, and combining three standard X angular points into the B type and W type of combined marks according to certain constraint rules; 2. detecting the X angular points, carrying out symmetry calibration by taking a corresponding Hessian matrix feature vector direction as the direction of the symmetry axis of the X angular points on the basis of a Hessian matrix probing X angular point algorithm; and 3. in the detected sequence of the X angular points with direction, detecting and indentifying the three-X combined mark. Two types of three-X combined marks defined by the detection identification method have the advantages of rotation invariance and distortion resistance; and by utilizing the detection identification algorithm, different three-X combined marks can be detected in a distinguishing mode, and the difficulty of subsequent vision matching and identification is lowered.

The invention relates to a three-dimensional attitude estimation method in disordered grabbing based on SHOT and ICP algorithms. The method is used for object pose estimation in the disordered grabbing process. A good initial position is provided for ICP fine registration through an SHOT coarse matching method, an M matrix in an SHOT algorithm is constructed, eigenvalue decomposition is carried out, and then a local reference system is constructed; topological characteristics under a corresponding reference system are calculated, a result is stored in a histogram, Hough transform is performedon a characteristic extraction result corresponding to the model and the scene point cloud, wrong point pairs are eliminated, and resolving is performed to obtain a final coarse registration attitudeestimation result; and nearest point searching is carried out by using an ICP algorithm, a covariance matrix construction is constructed, and a rotation matrix and a translation vector for minimizingan objective function are calculated. The problem that the registration precision is reduced when the traditional ICP is applied to the collection of point clouds with holes due to the reflection of workpieces is solved.

The invention discloses a gesture identification method. The method comprises: a shape of a to-be-identified gesture is obtained, a closed profile is extracted from a gesture-shaped edge, and all profile points on the profile and a coordinate of each profile point are obtained; the layer number of the profile is determined, and an area parameter, an arc length parameter, and a gravity center parameter that correspond to each profile point at each layer are calculated based on the coordinate of each profile point, wherein the parameters are used as feature parameters of the profile point; with the feature parameters of each profile point, a to-be-identified gesture and a template in a preset template base are matched to obtain an optimal matching template, and the optimal matching template is determined as the to-be-identified gesture. According to the invention, a global feature, a local feature, and a relation between the global feature and the local feature are described; multi-scale and omnibearing analysis expression is carried out; effective extraction and expression of the global feature and the local feature of the to-be-identified gesture shape can be realized; and a phenomenon of low identification accuracy caused by a single feature can be avoided.

The invention provides a uterine neck cell image characteristic identification method and a uterine neck cell characteristic identification apparatus. The uterine neck cell image characteristic identification method comprises the following steps: S100, converting a uterine neck cell color picture into a gray-scale image; S200, segmenting the uterine neck cell grey-scale image by use of a mean value segmentation method to extract nuclei of uterine neck cells; S300, accurately positioning the centers of the nuclei by use of a gray scale weight center positioning method; S400, converting a uterine neck cell image in a cartesian coordinate system into a uterine neck cell image in a polar coordinate system; S500, taking a vector composed of a gray-scale median value of the uterine neck cell image on each polar radius in the polar coordinate system as a characteristic vector of the uterine neck cell image; and S600, training a support vector machine vector machine classifier by use of a uterine neck cell training sample and performing class determination on the image of the uterine neck cell training sample by use of the classifier. Compared to geometrical characteristics extracted by use of a conventional method, the uterine neck cell image characteristic identification method has the advantages of dimension invariability, rotation invariability, high identification rate and fast identification speed.

The invention relates to a method for tracking a point feature based on fractional-order differentiation, comprising detecting a point feature by adopting a method based on the fractional-order differentiation; forecasting the location of the next frame point by using a Kalman method or an extension method; searching in a given area, carrying out a similarity measurement, and acquiring a corresponding tracking point if requirements are satisfied; otherwise, considering the corresponding tracking point to be absent, and for such a point, considering the tracking is lost if a corresponding matched tracking point is still absent in a range of following k frames, wherein the value of k is larger than 2; and updating the point feature if the tracking is normal. The fractional-order differentiation has advantages over integral-order differentiation in presenting areas which have abundant texture details and inconspicuous texture information. Different differential gradient images are formed for fractional-order differentiation with different directions and different orders, and convolution directional diagrams with different scales are formed by combining the different differential gradient images with Gaussian kernel convolution in different sizes respectively, so that significant changes presented by the point feature are ensured when the direction is changed, having properties of rotation invariance, translation and scale invariance.

The invention discloses a method for extracting a suspected flame region based on infrared light and visible light images, and relates to the field of computer vision. In this method, brightness threshold segmentation is performed on a collected infrared image to obtain a suspected high-temperature flame region; at the same time, the infrared image and a visible light image are image-registered toobtain an affine transformation matrix, and the position of the suspected high-temperature flame region on the visible light image is obtained by combining the suspected high-temperature flame regiontherewith; and finally, a suspected flame region is obtained by flame segmentation based on the YCrCb color space, morphological processing, and connected component labeling. The method can effectively extract the more accurate suspected flame region, can guarantee the detection of the suspected flame region in the night environment at the same time, and is conducive to the all-weather flame detection.

The invention relates to the technical field of processing of images, in particular to a real-time circular printing image defect detecting method. The method comprises the following steps: a standard template graph and an on-line real-time graph of a target to be detected, obtaining a circle point coordinate through an exponential changing and searching step-length method, calculating a circle center and semi-diameter of a circular area of each of the standard template graph and the on-line real-time graph according to a method for positioning a circle through three points, dividing each circular area into a large quantity of annular areas, counting characteristics of grey level histograms of the annular areas, and comparing the characteristics of the grey level histograms of the annular areas of the standard template graph and the on-line real-time graph to complete image defect detection. Through the adoption of the real-time circular printing image defect detecting method, the circular printing image defection speed is improved from two aspects; a practicable method is provided for on-line defect detection based on machine vision.

The present invention discloses a method and device for gesture identification based on substantial feature point extraction. The device comprises: an extraction module configured to obtain shape of a gesture to be identified, extract an unclosed contour from the edges of the shape of the gesture to be identified and obtain coordinates of all the contour points on the contour; a calculation module configured to calculate the area parameters of each contour point, perform screening of the contour points according to the area parameters, extract the substantial feature points and take the area parameters of a substantial feature point sequence and the point sequence parameters after normalization as the feature parameters of the contour; and a matching module configured to facilitate the feature parameters of the substantial feature points, perform matching of the gestures to be identified and templates in a preset template library, obtain the optimal matching template of the gesture to be identified and determine the type of the optimal matching template as the type of the gesture to be identified. The method and device for gesture identification based on the substantial feature point extraction have good performances such as translation invariance, rotation invariance, scale invariance and hinging invariance while effectively extracting and expressing gesture shape features so as to effectively inhibit noise interference.

The invention relates to a coin image recognition method based on sparse representation. The traditional image recognition method has poor recognition effect. The coin image recognition method comprises the steps of: firstly, obtaining gray level images of the front face and the back face of a coin for preprocessing and determining a coin region, standardizing the size of a coin image; expanding a training sample image into a plurality of angle samples and selecting a main training sample, expressing a testing coin sample into sparse representation of a training sample set, solving an optimal sparse coefficient vector; reconstructing the testing coin image, determining the coin image category by using a reconstructing error; and identifying the coin by utilizing the statistical property of the sparse coefficient vector. The invention can recognize the coin image without extracting the surface characteristics of a coin with rotational invariance, and has simple implementation method.

The invention provides a GPU-based automatic generation and collision detection method for a soft tissue organ metaball model. The method comprises four steps: a metaball model generation step: performing point sampling of an original mesh, calculating a Voronoi diagram of a mesh model, acquiring a medial surface of a triangular mesh model, and placing an initial ball on the medial surface; a step for local optimization of the metaball model: according to the initial position and radius of the metaball model, utilizing the method for adjusting the radius, the method of filling and other methods to perform local optimization of the metaball model; a step for global optimization of the metaball model: utilizing a charge gravity model, and calculating the gravity between the metaball and the gap to move and adjust the position of the metaball; and a collision detection step: utilized the generated metaball model to perform collision among soft tissue organs and collision between soft tissues and surgical instruments. The invention provides a soft tissue modeling method and a collision detection method for a virtual surgery. The soft tissue modeling method and the collision detection method for a virtual surgery can use a GPU parallel computation to realize acceleration and are high in real-time.

The invention discloses a footprint pressure distribution characteristic representation method which comprises the steps of (S1) using a footprint sampling instrument to collect footprint pressure image information, and preprocessing a footprint pressure image, (S2) extracting footprint front foot and back foot pressure distribution characteristics and constructing a footprint pressure distribution characteristic map, (S3) projecting front foot and back foot pressure distribution characteristic maps along direction, finding a direction with a maximum projection value (pressure value) as a main direction, and carrying out pressure distribution characteristic map main direction standardization, and (S4) carrying out characteristic selection on the obtained footprint pressure distribution characteristics. According to the method, the extracted footprint pressure distribution characteristics can represent the distribution characteristics of foot pressure when a human body is walking, the distribution between a footprint of barefoot and a footprint with socks is not needed, and the applicability is wide.

The invention relates to an industrial part defect detection algorithm based on a pixel vector invariant relation characteristic. The algorithm comprises the following steps that 1) contour extractionis carried out on a counter to be detected and local texture, and edge pixels to be detected are obtained; 2) the width of a detection window is defined, and is optimized according to a defined pixellinearity relation decision function, an inter-pixel direction vector is extracted from the window, the detection window is slid along the detection edge in a preset step length, and pixel vectors are extracted from all edges to be detected; and 3) an invariant relation characteristic of the pixel vectors of the edges to be detected is calculated, the invariant relation characteristic is comparedwith an inter-pixel invariant relation characteristic of a standard part, and whether the part has a defect is determined. The edge pixel vector is constructed by utilizing the difference in the local position relation of the contour pixels, difference matching is carried out by using invariance information between vector directions or vector module values, and defect detection is realized.

The invention discloses an improved Online Boosting and Kalman filter improvement-based TLD tracking method, and belongs to the technical field of machine vision, artificial intelligence, man-machineinteraction and target tracking. The method comprises the following steps of: (1) initialization: initializing an improved Online Boosting classifier and a P-N learning device by utilizing an initialsample set formed through selecting a target and carrying out affine transformation; (2) image tracking: selecting a feature point, tracking the feature point for twice by using an L-K optical flow method, and comparing an error between the twice tracking with a threshold value so as to obtain a tracking result; (3) image detection: obtaining a detector result through a Kalman filter, a variance classifier, the Online Boosting classifier and a KNN classifier; (4) tracking result and detection result integration: assessing confidence coefficients of the tracker result and the detector result soas to determine which module result is finally adopted; and (5) online learning: correcting the tracker result and the detector result by using the P-N learning device, and enriching the sample set.The method is capable of effectively overcoming the shielding problems, improving the speed of original methods and effectively the precision and robustness of detectors.

The invention relates to a non-contact video displacement measuring method. The method comprises the following steps that 1, motion videos of a digital equipment photographing structure are adopted and guided into a processor; 2, the processor obtains a first frame image in the motion videos, a target point is adopted as a center selection target area; 3, the next frame image is obtained, a target point in the previous image is adopted as a center selection matching area, pixel points in the matching area obtain matching blocks equal to the size of the target area by adopting the pixel point position as the center; 4, the target area and the matching blocks are matched to determine a matching block matched with the target area, the center point of the matching blocks is the position of the target point in the frame image, the position is adopted as a novel target point, and the matching blocks are adopted as the novel target area; 5, the steps 3 and 4 are repeatedly executed to obtain the position where the target point in each frame image is located, and a displacement curve of the target point is obtained. Compared with the prior art, measuring equipment is cheap, and the measuring result is reliable.

The invention discloses a control method for safety box with palmprint recognition system, comprising the following steps: A1, acquiring a palmprint image, A2, pre-treating the palmprint image, A3, extracting the feature vector of the pre-treated palmprint image, and A4, matching the extracted feature vector with the palmprint feature vector of a pre-stored authorised user, sending an unlocking instruction if matched; or else, not sending the unlocking instruction if not matched; no matter matched or not, the unlocking time and user information are stored in a storage module.