34results about How to "Reduce geometric distortion" patented technology

A system and method are provided for significantly reducing or substantially eliminating angular geometric distortions in devices designed for imaging and/or inspection of an interior portion or surface of a cavity. A series of processing steps or methods may be employed to eliminate Non-Uniform Rotational Distortion (NURD) in such devices, for example, unidirectional and bi-directional intravascular ultrasonic (IVUS) imaging systems. The system may include a processor and an electronic module which control operation of a transducer assembly provided at a distal end of a catheter assembly. The system invokes a first processing step or method to collect and store raw angle and line data, as well as one or more of second and third processing steps or methods which adjust for NURD experienced during backlash of a bi-directional imaging system and a fourth processing step or method which performs a line-to-line correlation function. The system and method provide more accurate and reliable angular orientations of anomalies identified during imaging and/or inspection of the interior portion or surface of the cavity, thus facilitating diagnosis and treatment options.

An image processing method determines a geometric transform of a suspect image by efficiently evaluating a large number of geometric transform candidates in environments with limited processing resources. Processing resources are conserved by using complementary methods for determining a geometric transform of an embedded signal. One method excels at higher geometric distortion, and specifically, distortion caused by greater tilt angle of a camera. Another method excels at lower geometric distortion, for weaker signals. Together, the methods provide a more reliable detector of an embedded data signal in image across a larger range of distortion while making efficient use of limited processing resources in mobile devices.

In a method and device for correcting distortion in MRI, k-space data are acquired in a number of data readout directions, the data are converted into a number of images, and a corresponding pixel shift map is generated for each image. The geometric distortion in the corresponding image is corrected according to the pixel shift map, and then all geometric distortion-corrected images are combined. Since movement distortion normally exists in the data readout direction, collecting the k-space data from a number of data readout directions can effectively correct movement distortion. Moreover, correcting the geometric distortion for the images converted from data acquired in a number of data readout directions according to the pixel shift map can reduce the geometric distortion of the final image generated from combination of images. The method and device correct not only movement distortion of MRI images, but also geometric distortion of MRI images.

A method for transforming and segmenting medical volumes based on generating an antagonistic network mainly comprises the acquisition of synthetic data, the interaction between a generator and a segmentation device, the complete target and the architecture of the antagonistic network and the process is that firstly, the generator is trained with the cyclic consistency loss function of the antagonistic network to compulsorily reconstruct the synthetic data so as to reduce the geometrical distortion of the synthetic image; then, two auxiliary maps, namely segmentation devices, are used to control the geometrical invariance of the synthesized data, so as to ensure the shape consistency of the synthesized image, and finally, the segmentation devices are amplified with the synthesized data generated in the generator to become the multi-mode segmentation devices to achieve efficient volume segmentation. Compared with the traditional method, the method can learn unpaired data, achieves the consistency of image set shapes and improves the segmentation efficiency by using synthetic data, thus achieving the goal of synthesizing clear 3D medical images efficiently.

The invention relates to an accumulation energy based three-dimensional image line clipping redirecting method. The method comprises the following steps: 1, inputting a three-dimensional image and a corresponding vision difference map; and initializing an energy matrix and an energy accumulation matrix of the input image; 2, finding out the optimal seam set of the left and right vision images based on the dynamic planning method, and recording the route; 3, accumulating the energy of each pixel on the optimal seam set route on the adjacent eight pixels; 4, detecting and accumulating the energyto adjacent two pixels in the maximum edge information direction; 5, deleting the optimal seam set; updating the energy matrix of the image, the energy accumulation matrix M and the corresponding vision difference image; and 6, iterating the abovementioned steps until the target size is met, and thus obtaining the re-directed left and right vision images and the corresponding vision difference images. With the adoption of the method, the vision distortion of three-dimensional images, caused by seam operation concentrated in some area of the images, can be effectively reduced; the geometric consistency of the left image and the right image can be maintained; and the three-dimensional image line cutting clipping performance is improved.

The invention provides a Hog and Gabor feature efficient fusion fast face recognition method based on near-infrared face image, belonging to the technical field of pattern recognition and image processing. The method includes Hog feature extraction and Gabor feature extraction for near-infrared face image samples respectively. The non-negative matrix decomposition method is used to reduce the dimension of two kinds of eigenmatrices respectively. The Hog feature and Gabor feature are fused to obtain the fused feature. The linear discriminant analysis (LDA) was used to reduce the dimension of the fusion feature matrix, and the feature vectors of the training samples after the transformation matrix of the second projection and the second reduction are obtained. The nearest neighbor algorithmKNN is used to classify and recognize the test samples based on the distribution of training samples. The invention ensures the comprehensiveness of acquiring characteristic information, effectively improves the characteristic representation efficiency, reduces the cost of algorithm operation storage and time consumption, and improves the efficiency of face recognition process.

A relief print master is created by a printhead that moves in a slow scan direction. The nozzles of the printhead jet droplets of a polymerisable liquid on a rotating drum. The different nozzles jet droplets simultaneously on different layers that have different diameters. As a result, the droplets jetted by different nozzles travel over different distances before landing. The effect of this is that the droplets undergo different position lag as they land on the different layers. By rotating the printhead in a plane that includes the central axis of the rotating drum and a nozzle row this effect can be compensated for.

The invention discloses a digital method for rapidly evaluating the loss severity of alfalfa diseases and insects. According to the technical scheme of the method, firstly, the focal regions and the non-focal regions of alfalfa leaves are analyzed and then the common disease degree and the RGB color component law thereof are generalized. After that, a color decision-making tree component system for the focal regions and the non-focal regions of alfalfa leaves is established accordingly. The visual processing flow of digital pictures is integrated as one, so that the method is suitable for non-computer professionals to use. At the same time, the functions of batch processing, data exporting and the like are realized, so that the method can be used for processing volume data. Based on the geometric projection imaging rule, the inscribed circle calculation manner is adopted, so that the geometric deformation avoided. The calculation accuracy is improved. Moreover, binary pictures for the healthy regions and the non-healthy regions of alfalfa leaves are constructed, and then the pictures are displayed and compared. In this way, the method can be applied to alfalfa leaves of smaller than 0.5 m in both length and width, with the diameters of the focal regions thereof to be larger than 1mm, and the area statistical precision of the focal regions thereof to be larger than 95%.

The high-temperature and high-pressure synthesis device comprises an outer salt pipe, an inner salt pipe and pyrophyllite, the pyrophyllite is provided with through holes used for assembling the outer salt pipe and a conductive steel ring, the outer salt pipe is arranged in the pyrophyllite, a carbon pipe is assembled in the outer salt pipe, the inner salt pipe is assembled in the carbon pipe, a metal cup is placed in the inner salt pipe, and the metal cup is placed in the conductive steel ring. The upper end and the lower end of the through hole of the pyrophyllite are provided with the carbon plates and the conductive steel rings, and the carbon plates are attached to the outer salt pipe, the carbon pipe, the inner salt pipe and the salt plates. During application, the carbon tube simultaneously heats the inner salt tube and the outer salt tube to simultaneously generate two isostatic pressing areas formed by molten salt, namely an inner isostatic pressing pool and an outer isostatic pressing pool, and the inner isostatic pressing pool provides a hot isostatic pressing environment which is suitable for sintering the diamond hard alloy compact and has equal pressures in all directions; the outer isostatic pressing tank provides a pressure environment with uniform stress for the carbon tubes in the outer isostatic pressing tank, and the stress of the carbon tubes is balanced; and the sintering quality of the diamond hard alloy compact is obviously improved.

The invention discloses a multi-dimensional synthetic aperture radar registration method and device, which are used for carrying out consistency processing on signals in an imaging process to realize multiband consistency imaging. The method comprises the following steps: selecting a reference wave band, and obtaining distance offset and azimuth offset of each wave band relative to the reference wave band based on the antenna phase center position of each wave band, a reference track and a reference drift angle of each wave band; performing range direction signal resampling, range direction frequency spectrum band-pass filtering and range direction signal interception to obtain processed range pulse pressure data; carrying out azimuth resampling, frequency spectrum band-pass filtering and azimuth signal interception to obtain a processed SAR image; checking the registration precision between each wave band image and the reference wave band image by using the scaling points; and if the registration precision is greater than one pixel, correcting the distance offset and azimuth offset of each non-reference wave band image relative to the reference wave band by using the scaling points.

A relief print master is created by a printhead that moves in a slow scan direction. The nozzles of the printhead jet droplets of a polymerisable liquid on a rotating drum. The different nozzles jet droplets simultaneously on different layers that have different diameters. As a result, the droplets jetted by different nozzles travel over different distances before landing. The effect of this is that the droplets undergo different position lag as they land on the different layers. By rotating the printhead in a plane that is orthogonal to the jetting direction this effect can be compensated for.

The embodiment of the invention discloses an image compensation method and device and a computer storage medium. The method can comprise the following steps: dividing a linear charge coupled device CCD array into a plurality of CCD line segments; determining the current to-be-rotated angle of each CCD line segment according to the current relative angle between the corresponding target area of each CCD line segment in the to-be-imaged area and each CCD line segment; for each CCD line segment, rotating according to the current to-be-rotated angle of each CCD line segment; and shooting the to-be-imaged area through the rotated CCD line segment.