507 results about "Image gradient" patented technology

An image processing device according to an example of the invention comprises a differentiating section which differentiates input image data to generate gradient image data, a gradient domain deconvolution processing section which applies a deconvolution to the gradient image data, the deconvolution performing deblurring corresponding to a prior distribution of an image gradient of an image to generate deconvolved data, and an integrating section which integrates the deconvolved data to generate deblurred image data.

A method of image processing using kernel regression is provided. An image gradient is estimated from original data that is analyzed for local structures by computing a scaling parameter, a rotation parameter and an elongation parameter using singular value decomposition on local gradients of the estimated gradients locally to provide steering matrices. A steering kernel regression having steering matrices is applied to the original data to provide a reconstructed image and new image gradients. The new gradients are analyzed using singular value decomposition to provide new steering matrices. The steering kernel regression with the new steering matrices is applied to the noisy data to provide a new reconstructed image and further new gradients. The last two steps are repeated up to ten iterations to denoise the original noisy data and improve the local image structure.

A method of coronary vessel segmentation and visualization includes providing a digitized coronary image, placing a plurality of seed points along an estimated centerline of a coronary vessel, selecting a seed point and constructing a cyclic graph around the seed point in a plane perpendicular to the centerline at the seed point, performing a multi-scale-mean shift filtering in the perpendicular plane to estimate image gradient values, detecting a vessel boundary using a minimum-mean-cycle optimization that minimizes a ratio of a cost of a cycle to a length of a cycle, constructing a sub-voxel accurate vessel boundary about a point on the centerline, and refining the location of the centerline point from the sub-voxel accurate boundary, where the steps of constructing a sub-voxel accurate vessel boundary and refining the centerline point location are repeated until convergence.

A method and apparatus for image data compression includes detecting a portion of an image signal that uses a disproportionate amount of bandwidth compared to other portions of the image signal. The detected portion of the image signal result in determined components of interest. Relative to certain variance, the method and apparatus normalize the determined components of interest to generate an intermediate form of the components of interest. The intermediate form represents the components of interest reduced in complexity by the certain variance and enables a compressed form of the image signal where the determined components of interest maintain saliency. In one embodiment, the video signal is a sequence of video frames. The step of detecting includes any of: (i) analyzing image gradients across one or more frames where image gradient is a first derivative model and gradient flow is a second derivative, (ii) integrating finite differences of pels temporally or spatially to form a derivative model, (iii) analyzing an illumination field across one or more frames, and (iv) predictive analysis, to determine bandwidth consumption. The determined bandwidth consumption is then used to determine the components of interest.

A method detects edges of an object in a scene by first acquiring a static image of the scene when the scene is static, and a live image of the scene including the object. A reference image is constructed from the static image. Then, image gradients of the reference image are compared with image gradients of the live image to identify edges of the object in the live image.

Systems and methods for initializing motion tracking of human hands are disclosed. One embodiment includes a processor; a reference camera; and memory containing: a hand tracking application; and a plurality of edge feature templates that are rotated and scaled versions of a base template. The hand tracking application configures the processor to: determine whether any pixels in a frame of video are part of a human hand, where a part of a human hand is identified by searching the frame of video data for a grouping of pixels that have image gradient orientations that match the edge features of one of the plurality of edge feature templates; track the motion of the part of the human hand visible in a sequence of frames of video; confirm that the tracked motion corresponds to an initialization gesture; and commence tracking the human hand as part of a gesture based interactive session.

A method and system detects candidate targets or objects from a viewed scene by simplifying the data, converting the data to gradient magnitude and direction data which is thresholded to simplify the data. Horizontal edges within the data are softened to reduce their masking of adjacent non-horizontal features. One or more target boxes are stepped across the image data and the number of directions of gradient direction data within the box is used to determine the presence of a target. Atmospheric attenuation is compensated. The thresholding used in one embodiment compares the gradient magnitude data to a localized threshold calculated from the local variance of the image gradient magnitude data. Imagery subsets are containing the candidate targets may then be used to detect and identify features and apply a classifier function to screen candidate detections and determine a likely target.

An apparatus, system, and method of optically inspecting printed circuit boards (PCBs) for defects, that reliably determines the dimensions of components including those having the same color as the background, and which can detect components which are missing, misoriented, misaligned, or not properly seated. The apparatus uses a camera and a coherent primary light source mounted at an angle away from the vertical so as to produce sharply defined PCB component shadows on the top surface of the PCB. An image of the PCB is captured, the shadow edges are symbolically decomposed into primitives from which gradients are produced, and then compared to a previously captured gradient of a defect-free PCB. Differences in the two image gradients, if any, are used to identify missing, misaligned, misoriented, and improperly seated components, and to detect foreign objects and other PCB defects.

A gradient-based image enhancement and restoration method and system which applies an orientation-isotropy adaptive filter to the gradients of high structured regions, and directly suppresses the gradients in the noise or texture regions. A new gradient field is obtained from which image reconstruction can progress using least mean squares. The method generally comprises: inputting image data; calculating image gradients; defining the gradients as having large or small coherence; filtering the large coherence gradients for edge enhancement; suppressing the small coherence gradients for noise reduction; assembling an enhanced gradient field from the filtered large coherence and suppressed small coherence gradients; and optimizing the assembled gradient field into a restored image.

The invention discloses a sea surface wind measurement method based on an X-band marine radar and belongs to the technical field of marine dynamic environment remote sensing. The measurement method comprises three parts of radar image preprocessing, wind direction measurement and wind speed measurement. In the wind direction measurement indexes, image gradient, gray level and smoothing item are organically combined, the proportion of the image gradient, the gray level and the smoothing item is adjusted through proportionality factor and a model suitable for the sea surface wind characteristic is established, compared with the prior art, the wind direction measurement precision is improved by 68.4 percent. In the wind speed measurement indexes, when the radar is used for measuring individually, normalized radar cross section (NRCS), the actually measured wind direction and signal to noise ratio (SNR) serve as back propagation (BP) network input, compared with the traditional algorithm, the wind speed measurement precision is improved by over 84 percent. In the wind speed measurement indexes, sea boundary layer parameters serve as addition input of the BP network, so that the wind speed measurement precision of the marine radar can be further improved, and the measurement precision is improved by over 48 percent by taking air-sea temperature difference, salinity, sea level and atmospheric pressure into consideration.

A method for segmenting tubular structures in digital medical images includes extracting a subregion from a 3-dimensional (3D) digital image volume containing a vessel of interest, identifying potential vessel centerpoints for each voxel in the subregion by attaching to each voxel a tip of a 3D cone that is oriented in the direction of the voxel's image gradient and having each voxel within the cone vote for those voxels most likely to belong to a vessel centerline, selecting candidates for a second vote image that are both popular according to a first vote image, as well as being consistently voted upon by a radius image, reconfiguring the subregion as a graph where each voxel is represented by a node that is connected to 26 nearest neighbors by n-link edges, and applying a min-cut algorithm to segment the vessel within the subregion.

Systems and methods for tracking human hands by performing parts based template matching using images captured from multiple viewpoints are described. One embodiment includes a processor, a reference camera, an alternate view camera, and memory containing: a hand tracking application; and a plurality of edge feature templates that are rotated and scaled versions of a finger template that includes an edge features template. In addition, the hand tracking application configures the processor to: detect at least one candidate finger in a reference frame, where each candidate finger is a grouping of pixels identified by searching the reference frame for a grouping of pixels that have image gradient orientations that match one of the plurality of edge feature templates; and verify the correct detection of a candidate finger in the reference frame by locating a grouping of pixels in an alternate view frame that correspond to the candidate finger.

A technique is disclosed for estimating the measurement error in motion vectors used for example in a motion compensated video signal process. For each motion vector corresponding to a region of an image a plurality of temporal and spatial image gradients are calculated corresponding to that region. From the constraint equations of the image gradients a plurality of error values can be calculated for each motion vector and a parameter generated describing the size of the distribution of motion vector measurement errors. Subsequent processing of the video signals using the motion vectors can then be adapted, for example by graceful fallback in motion compensated interpolation, depending on the accuracy of each motion vector. The "confidence' in the accuracy of each motion vector can be described by a parameter calculated in relation to the size of the error distribution and the motion vector speed.

The invention discloses an intelligent multifunctional belt surface patch edge detection method which is characterized by including steps: (1) two direction templates are adopted to have neighborhood convolution with images in an image space to complete image gradient magnitude calculation; (2) the gradient value and the gradient direction of edge pixel points are calculated, and edge searching is performed according to the gradient direction information to obtain accurate conveying belt spot image edge point information; and (3) target edge sub pixel positioning is achieved through quadratic polynomial interpolation in the edge point gradient direction. The intelligent multifunctional belt surface patch edge detection method completely eradicates potential safety hazards of conveying belts, reduces irregular maintenance and shutdown overhaul time of the conveying belts, improves production efficiency, has a protection effect for safety production, has important practical significances for promoting the economic development, has a wide application prospect, and can be used for belt surface abrasion detection and surface greasy dirt detection.

The invention discloses an SAR image segmentation method based on wavelet pooling convolutional neural networks. The SAR image segmentation method comprises 1. constructing a wavelet pooling layer and forming wavelet pooling convolutional neural networks; 2. selecting image blocks and inputting the image blocks into the wavelet pooling convolutional neural networks, and training the image blocks; 3. inputting all the image blocks into the trained networks, and testing the image blocks to obtain a first class mark of an SAR image; 4. performing superpixel segmentation of the SAR image, and blending the superpixel segmentation result with the first class mark of the SAR image to obtain a second class mark of the SAR image; 5. obtaining a third class mark of the SAR image according to a Markov random field model, and blending the third class mark of the SAR image with the superpixel segmentation result to obtain a fourth class mark of the SAR image; and 6. blending the second class mark of the SAR image with the fourth class mark of the SAR image according to an SAR image gradient map to obtain the eventual segmentation result. The SAR image segmentation method based on wavelet pooling convolutional neural networks improves the segmentation effect of the SAR image and can be used for target detection and identification.

The invention belongs to the technical field of digital image processing and pattern recognition and discloses a general Hough transformation-based method for detecting the position of a traffic signal lamp, which comprises the following steps: by taking an image sequence as input, calculating image gradient information by adopting a first-order differential operator on an image by using image gradation; establishing a traffic lamp shape describing function; defining mapping from an image point to the space of an accumulator; and searching the extreme value of the space of the accumulator to acquire the coordinates of the traffic lamp to provide positional information for traffic lamp state identification. The general Hough transformation-based method for detecting the position of the traffic signal lamp can cope with the significant change of illumination, is insensitive to the influence caused by image sampling color cast and can cope with the traffic lamp with various common shapes.

The present invention discloses a binocular visual image stereo matching method, relating to image data processing. The method comprises the steps of the acquisition and pre-processing of a binocular image, the image gradient matrix solution of the binocular image, the obtainment of an initial disparity map, and the obtainment and output of a final disparity map and the completion of the binocular visual image stereo matching. According to the method, the defect of low matching precision and insufficient real-time performance of the existing binocular stereo matching technology is overcome.

The invention provides a non-reference image quality evaluation method based on gradient relevance, and belongs to computer image analysis. The method comprises the following steps: firstly, determining three sub-characters, namely, an image gradient amplitude character, an image gradient direction change character and an image gradient amplitude change character, which are easily influenced by distortion in an image gradient; performing M*M image blocking on the three characters, and determining a statistic variance of the three characters in each image block, wherein the average number of the statistic variances of all the image blocks in the whole image is taken as an image characteristic; and finally, determining the image quality by combining a support vector with a two-step frame in image quality evaluation. The method provided by the invention has the advantages of being small in time complexity, high in subjective consistency, low in image feature dimension and good in universality; the method can be applied to applications related to small computer devices or image quality, and is high in practical value.

The invention discloses a super resolution image reconstruction method based on gradient consistency and anisotropic regularization. The super resolution image reconstruction method based on the gradient consistency and the anisotropic regularization is used for solving super resolution image reconstruction self-adaption to maintain high-frequency image information, and recovering image detail information. The steps includes inputting a low resolution image, obtaining an interpolation image by using dual-three interpolation methods to sample the input image, adopting gradient consistency and anisotropic regularization (GCAR) conditions to restrain an objective function, performing a deconvolution operation for the interpolation image, judging a deconvoluted image whether to meet output requirements, outputting a super resolution result if the deconvoluted image meets the output requirements, otherwise, performing reconvuluting and pixel replacement for the deconvoluted image, going to a next deconvolution operation, and iterating like those until the output requirements are met. The super resolution image reconstruction method based on the gradient consistency and the anisotropic regularization has the advantages of maintaining the gradient consistency of low contrast image area low resolution images and corresponding high resolution images, and capable of recovering image detail information in a self-adaption mode and being used for the field of video applications.

Systems and methods for tracking human hands by performing parts based template matching using images captured from multiple viewpoints are described. One embodiment of the invention includes a processor, a reference camera, an alternate view camera, and memory containing: a hand tracking application; and a plurality of edge feature templates that are rotated and scaled versions of a finger template that includes an edge features template. In addition, the hand tracking application configures the processor to: detect at least one candidate finger in a reference frame, where each candidate finger is a grouping of pixels identified by searching the reference frame for a grouping of pixels that have image gradient orientations that match one of the plurality of edge feature templates; and verify the correct detection of a candidate finger in the reference frame by locating a grouping of pixels in an alternate view frame that correspond to the candidate finger.

The invention discloses an image blind deblurring method based on edge self-adaption. To solve the problems that as for an existing total variation deblurring algorithm, edges and details of images are easily blurred, a de-mean gradient total variation canonical model is built, weighting coefficients are calculated in an iterated mode by means of local variance self-adaption of gradients of the images, and the ability of the deblurring algorithm to restore the edges and the details of the images. The image blind deblurring method comprises the following steps that (1) a blurred image is input, solutions to a gradient-region clear image and a blurring kernel are obtained alternately, and the initial blurring kernel of the blurred image is obtained; (2) the initial blurring kernel is used for conducting primary non-blind deblurring on the blurred image, and an initial clear image is obtained; (3) clustering is conducted on the initial clear image, the mean value and the weighting coefficient in the de-mean canonical model are updated, and a solution to the blurring kernel is obtained again; (4) the new blurring kernel is used for conducting secondary non-blind deblurring so as to obtain a clear image. Experimental results show that the image blind deblurring method based on edge self-adaption has better deburring effect than the prior art and can be used for image restoration.

The invention provides a wireless multimedia sensor network-oriented video compression method, which solves the problem of large data volume in video application. Due to the adoption of the method, code rate is reduced and the quality of a decoded image is improved at the same time, and at last, the energy consumption of a node of the sensor is reduced, so that the life cycle of a network is prolonged. In the method, encoding in a strenuous motion area and in a motion edge area is enhanced by adopting an ROI distinguishing algorithm, and the decoded image is postprocessed by adopting a deblocking filter, so that the subjective quality of the decoded image is further improved. On the basis of a Wyner-Ziv distributed video encoding scheme, the strenuous motion area is extracted through an ROI judging criterion based on an image gradient field and based on Huffman encoding and decoding compression is preformed, and the other areas are encoded and decoded based on the LDPC distribution type, so that the method has the advantages of reducing code rate, improving the quality of the decoded image, reducing the processing and transmission energy consumption of the nodes, implementing the optimized transmission of video and prolonging the life cycle of the whole network.