2586 results about "Image edge" patented technology

Video signal post-processor de-blocks signal by processing block edges, particularly vertical and / or horizontal neighboring pixels. Depending on boundary condition, received signal is filtered using smoothing LPF function. Low-memory post-processor system neither requires DCT block characteristics nor blurs image edges close to block boundary.

A wide-angle lens system comprises, sequentially from the object side to the image side: a first lens element, a second lens element, a third lens element, an aperture and a fourth lens element. If the field of view of the wide-angle lens system is as high as 140 degrees, the extreme distortion of the image edge can be prevented with only four lens elements, and the image has a high sharpness. Therefore, it is very suitable for use in the monitor and vehicle-related lens system.

A method of forming a composite digital image comprising: providing 1-N digital images formed from 1-N contiguous segments of a larger radiographic image recorded in 1-N overlapping storage phosphor screens wherein N is equal to or greater than 2 and wherein the image content in the overlapped region of contiguous images is the same, and the end edge of a screen nearest an x-ray source is present in both contiguous images; selecting a pair of contiguous digital images, wherein one image is closer to said x-ray source than said other image; correcting for any geometric distortion if applicable in said pair of digital images based on the distance between x-ray source and said storage phosphor screen; determining any rotational displacement and any vertical displacement between said pair of digital images by matching said end edge of said one image present in said pair of images correcting for image orientation if applicable based on any said rotational displacement; determining any horizontal displacement between said pair of digital images by correlating the image content in said overlapping regions of said pair of digital images; stitching said pair of digital images together to form a larger composite digital image along said one image edge based on any said horizontal and vertical displacement; and repeating said correcting for any geometric distortion to said stitching with the larger composite image and the next consecutive overlapping digital image until all N digital images are stitched together to form a full composite image.

A rapid vehicle license plate locating method is provided, which uses top hat transformation and character texture characteristic, and is divided into background subtraction, vehicle license plate region crude location and precision location three steps, specifically comprises: (1) background subtraction, converting obtained color vehicle license plate image into gray image, using top hat transformation to inhibit large-size background object, highlighting vehicle license plate region; (2) crude location phase, calculating image edge map and proceeding binaryzation, morphological dilation and connected components analysis and other operation, obtaining reasonable size vehicle license plate candidate region set; (3) precision location phase, extracting candidate region texture characteristic, using support vector machine classifier to classify candidate vehicle license plate region, thus accurately locating vehicle license plate region. The invention uses the top hat transformation to filter vehicle license plate image, reduces large-size background interference, so that greatly enhances environment adaptation; meanwhile, from crude to fine location method is more efficient, and reduces greatly computing complexity.

The invention discloses a binocular stereoscopic vision matching method combining depth characteristics. The binocular stereoscopic vision matching method comprises: obtaining a depth characteristic pattern from left and right images through a convolutional neural network; calculating a truncation similarity measurement degree of pixel depth characteristics by taking the depth characteristics as the standard, and constructing a truncation matching cost function combining color, gradients and depth characteristics to obtain a matched cost volume; processing the matched cost volume by adopting a fixed window, a variable window and a self-adaptive weight polymerization or guide filtering method to obtain a cost volume polymerized by a matching cost; selecting an optimal parallax error of the cost volume by adopting WTA (Wireless Telephony Application) to obtain an initial parallax error pattern; then finding a shielding region by adopting a double-peak test, left-right consistency detection, sequence consistency detection or shielding constraint algorithm, and giving a shielding point to a parallax error value of a same-row point closest to the shielding point to obtain a parallax error pattern; and filtering the parallax error pattern by adopting a mean value or bilateral filter to obtain a final parallax error pattern. By adopting the binocular stereoscopic vision matching method combining the depth characteristics, the incorrect matching rate of three-dimensional matching can be effectively reduced, the images are smooth and image edges including edges of small objects are effectively kept.

A method of post-processing decompressed images includes identification of the direction of an image edge in a pixel block of the image and filtering applied along the boundary of the block in a direction substantially parallel to the detected image edge. Pixels are selected for filtering on the basis of the quantization parameter of the block of which they are members, the relative difference between pixels adjacent to the block boundary, and significant changes value of pixels in a filtering segment. Filtering is applied parallel to the detected edge to protect the sharpness of the edge while reducing or eliminating blocking and ringing artifacts. A method of separately post-processing fields of interlaced video eliminating complications arising from separate compression of the fields is also disclosed.

A pattern inspection apparatus is used for inspecting a fine pattern, such as a semiconductor integrated circuit (LSI), a liquid crystal panel, and a photomask (reticle) for the semiconductor or the liquid crystal panel, which are fabricated based on data for fabricating the fine pattern such as design data. The pattern inspection apparatus includes a reference pattern generation device configured to generate a reference pattern represented by one or more lines, comprising one of a line segment and a curve, from the data, an image generation device configured to generate the image of the pattern to-be-inspected, a detecting device configured to detect an edge of the image of the pattern to-be-inspected, and an inspection device configured to inspect the pattern to-be-inspected by comparing the edge of the image of the pattern to-be-inspected with the one or more lines of the reference pattern.

Methods and apparatuses for nonlinear scaling of video images. To match the aspect ratios of a video image and the target display area, at least one embodiment of the present invention scales the video image according to one or more nonlinear functions along the horizontal direction and / or the vertical direction. In one embodiment, the nonlinear functions are such that the original aspect ratio of the video image is preserved near the center region (or strip) of the image and the image is gradually stretched (or compressed) as it is mapped to the edges. In one example, the scaling is implemented by the texture mapping functionality of OpenGL using graphics hardware. In one embodiment of the present invention, the nonlinear mapping is constructed according to a polynomial mapping; and, the coefficients of the polynomial are adjustable by a user to trade off distortion between the image center and the image edges, giving the user control over the location and the amount of distortion.

The invention relates to an intelligent vehicle-bone type running state monitoring and early warning device used for rail transporting vehicles. The device comprises at least a group of sensing component units used for obtaining the vehicle operation state, including the operation state of wheels on rails, the state of the deformation of a vehicle chassis component and a railway and abnormal road conditions or the state of vehicle-bone devices; an intelligent sensing information processing unit based on a micro processor and used for processing the sensing signals of the vehicle state, including signal processing, data-collecting processing, image edge detection and extraction, image tracking, the processing and the intelligent analyzing of mechanical vibration / noise information, data identification and extraction, the learning of vehicle states and relevant background information, the forming of monitoring and early warning results and information recording and storing; input / output units used for the output, the operation, the control and the data communication of the monitoring and early warning results; and a power supply unit. The intelligent vehicle-bone type running state monitoring and early warning device has the advantages of multiple functions, high intelligentization and informatization level, high cost performance, high creditability and convenient installation, etc., is easy to be expanded, and can be applied under all weather conditions.

The present invention provides a fast high-precision geometric template matching method enabling rotation and scaling functions. According to the method, based on image edge information, with the sub-pixel edge points of a template image adopted as feature points, the tangent directions of the gradient directions of a target image adopted as feature lines, and based on the local extremum points of a similarity value, the similarity and the candidate positions of the template image and the target image are calculated from fine to rough through adopting a Pyramid algorithm and according to a similarity function; and pixel-level positioning accuracy is obtained at the bottommost layer of a Pyramid, the least squares method is adopted to carry out fin adjustment, so that sub-pixel positioning accuracy, higher-precision angle and size scaling accuracy can be achieved. The method can realize fast, stable and high-precision positioning and identification of target images which are moved, rotated, scaled and is partially shielded, and where the brightness of illumination changes, illumination is uneven, and cluttered background exists. The method can be applied to situations which require machine vision to carry out target positioning and identification.

The invention provides a character picture verification code identifying method based on identification feedback. The character picture verification code identifying method is characterized by comprising the following steps of: firstly, converting an original colorful image into a gray level image and carrying out binaryzation treatment to obtain binaryzation image data; then, repairing a binaryzation image, removing image edge burrs and filling a central blank; finishing the connection of broken strokes to obtain a repaired image; removing a background and an interference point or line of the repaired image to obtain a noise-free image; thinning the noise-free image to obtain a thinned image with a single pixel; then, cutting the thinned image to obtain a single-character image which only contains a single character; and finally, carrying out normalization on the single-character image and identifying the character. According to the character picture verification code identifying method based on the identification feedback, a corresponding algorithm is designed to process a character picture identification code including various types of noises and having the phenomena that the character is stuck, inclined, rotated, deformed and the like, so as to finish high-efficiency and high-precision identification. The character picture verification code identifying method based on the identification feedback can be applied to verification code identification in an automatic program.

The invention discloses an H.264 / AVC intra-prediction method based on edge characteristics, which includes: performing data block prejudging before intra-prediction based on principal edge intensity (DES) and the like edge direction characteristics calculated by the edge histogram description describing the image marginal distribution, selecting the mode subclass corresponding to the characteristics to perform RDO calculation, thereby reducing the mode selection number of the intra-prediction; at the same time directly determining the Intra_8*8 chrominance prediction mode from the Intra_16*16 brightness prediction mode according to the correlativity of the chrominance prediction mode and the brightness prediction mode, to further reduce the complexity of the algorithm. The method has six steps, and is convenient and facilitating. Practice shows that the method can obviously improve the encoding speed, and can ensure that the bit-rate encoding (an increase of 3%) and peak signal-noise ratio (reduced about 0.02dB) have little change compared with the full search method. The method has very good practical value and application prospects.

The invention provides an image edge detection method based on threshold segmentation. The method is a novel threshold segmentation algorithm capable of thresholding all points of the image one by one and then sorting. The statistical information of average gray-scale value of the pixel neighborhood region in the image is used as the reference of threshold setting of the point, and the variance of gray-scale value of pixel in the neighborhood region of the point is used as additional judgment condition, so that the overall binarization of the region information is considered comprehensively to ensure the image edge to be extracted as target point. Additionally, the size of structural element for calculating the average value and variance can be adjusted to select the structural elements with different sizes according to different demands. The method can define each pixel with a threshold value, and the overall binarization of region information is comprehensively considered. The invention has good effect of image segmentation and high accuracy of edge positioning.

The invention relates to a video dynamic super-resolution processing method and system. The processing method comprises the steps of obtaining a motion vector of any pixel in a current to-be-processed frame according to motion estimation and calculating reliability degree of the motion vector; extracting the corresponding pixel of the pixel in a former high-resolution frame according to the motion vector of the pixel and carrying out Kalman filtering processing according to the corresponding pixel, thereby obtaining a first processing result; carrying out interpolation processing on the to-be-processed frame to obtain a second processing result; and carrying out weight fusion on the first processing result and the second processing result through utilization of the reliability degree, thereby obtaining a super-resolution frame after fusion. According to the method and the system, the problems of protecting edge information well and improving image edge sawteeth are realized; more image details are restored effectively on the condition of not increasing excessive extra time cost; moreover, relatively high robustness is achieved; and disorder of a super-resolution result or motion blurring resulting from inaccurate motion estimation is avoided.

The invention discloses a laser lap welding gap detecting system and a laser lap welding gap detecting method based on molten pool image visual sensing. The detecting system is a visual sensing system and comprises a CMOS camera, a light filtering system, a secondary light source, an image capture card, a computer, a display and the like, wherein the CMOS camera has a LinLog photosensory technology. According to the detecting method, the secondary light source and emitted light of molten pools are used as light sources; plasma is filtered out by utilizing the light filtering system, and light intensity is adjusted; the computer is used for collecting and displaying molten pool images in real time, wherein the molten pool images are obtained by the CMOS camera; molten pool image edges and areas and orifice image edges and areas are extracted and calculated by utilizing a Labview image processing platform, and the quantitative relations between molten pool sizes and orifice areas and between the molten pool sizes and orifice gaps are obtained. The detecting system is simple in structure, clear in monitoring image, high in light signal detecting accuracy, strong in anti-jamming capacity, good in engineering practicability and capable of monitoring laser welding of T-type overlap joint gaps in real time.

The invention relates to an automatic license plate positioning and recognition method based on a complex background. Images are acquired in a way that traffic polices or management personnel use digital cameras to take automobile pictures at any time and under various operating conditions instead of acquiring at certain fixed positions or intersections, and automatic license plate positioning and recognition are realized aiming at the random conditions. The method includes the steps: acquiring license plate images; converting color images; acquiring marginal information of the license plate images; acquiring alternate license plate zone images; precisely positioning license plate character zones; subjecting characters to single-character segmentation; and finally, using a BP (back propagation) neural network to realize recognition of license plate characters. The automatic license plate positioning and recognition method based on the complex background has the advantages of high accuracy and the like.

The invention relates to a moving target detecting method based on differential fusion and image edge information. The method comprises the following steps of: extracting a video image for preprocessing, and extracting the edge of the image to acquire continuous edge images; performing inter-frame differential operation on the continuous edge images respectively in a unit 8 data format, and performing background differential operation on the image in an intermediate frame; and fusing the detecting results of two differences to primarily extract a moving pedestrian target. In a background difference, a background automatic extracting method is improved, and a continuous-edge-image-based background image extracting and updating method is provided. A moving target area in the image is extracted by using an adaptive-background-model-based dynamic threshold value, and morphologic filtering and connectivity detection are performed, so that the foreground target of a moving pedestrian is acquired. Under the complex condition of sudden light variation, a moving target can be accurately and reliably detected, and the method is superior to the three traditional methods in the two aspects ofan identification rate and an error detection rate.

The invention relates to a MRI brain tumor image segmentation method based on an optimized U-net network model. The method comprises the following steps: 101, preprocessing the acquired multimodal MRIbrain tumor image data; 102, inputting the preprocessed multimodal MRI brain tumor image data into the trained U-Net network model; 103, acquiring multi-modality MRI brain tumor image segmentation data output by a U-NET network model, wherein the multimodal MRI brain tumor image segmentation data output from the U-NET network model can preserve the image edge information to generate a complete segmented image feature map. The image segmentation method provided by the invention can not only preserve the image edge information and generate a complete characteristic map, but also improve the accuracy of image segmentation.

The invention discloses a white blood cell image accurate segmentation method and system based on a support vector machine. The method comprises performing nucleus initial positioning and segmenting, performing rough expansion so as to obtain a substantial area labeled graph of cells, and accurately segmenting the cells by using color characteristics and the classifier of the support vector machine. According to the method provided by the invention, on one hand, according to a mankind visual saliency attention mechanism, the sensitivity of human eyes to the change of image edges are simulated, and a nucleus area can be accurately and rapidly segmented by using the clustering of edge-color pairs; and on the other hand, the adopted classifier of the support vector machine has excellent stability and anti-interference performance, and at the same time the space relationship of color information and pixel points are fully utilized so that the training sample sampling mode of the classifier of the support vector machine is improved, thus the accurate segmentation of white blood cells in a cell small image can be realized.

The invention relates to a human body measurement method, in particular to the non-contact human body measurement method for clothing design which belongs to the technical field of clothing design. The digital images of the front surface and the side surface of the human body are firstly obtained; the extraction of the image edges are carried out by adopting the color segmentation, the best threshold segmentation, the hole filling, the opening operation and the pixel communication image processing method, thereby obtaining the image edges of the front surface and the side surface of the human body; the human body measurement feature points and the lines are determined, the corresponding height and width measurement data of the human body for the clothing design are obtained by calculation; a mathematical model is established by applying the width and the thickness data of the human body to obtain the related circumference data, and the human body circumference measurement data for the clothing design is obtained by BP neural network simulation and regression prediction treatment. The method has simple device, convenient operation and low measurement cost, thereby being capable of meeting the requirements on the design and the production of the clothing industry and having broad popularization and application prospects.

A method of eliminating unwanted steps at edges in image or graphic representations in the line raster, in particular in on-line operation having the steps:a) Application of an edge operator to an image portion for coarsely ascertaining at least one rastered edge configuration,b) Determining the position of at least a first pixel from the amount of those pixels which form the rastered edge configuration or adjoin said rastered edge configuration,c) Approximation of a straight line for ascertaining a probable configuration of the unrastered image edge in the proximity of the first pixel,d) Ascertaining a criterion from the approximation straight line and the position of the first pixel for mixing a color X to the color C in the first pixel considered, ande) Mixing the ascertained color X to the color C in the first pixel considered.

A system and method for creating an enhanced virtual top-down view of an area in front of a vehicle, using images from left-front and right-front cameras. The enhanced virtual top-down view not only provides the driver with a top-down view perspective which is not directly available from raw camera images, but also removes the distortion and exaggerated perspective effects which are inherent in wide-angle lens images. The enhanced virtual top-down view also includes corrections for three types of problems which are typically present in de-warped images—including artificial protrusion of vehicle body parts into the image, low resolution and noise around the edges of the image, and a “double vision” effect for objects above ground level.

The invention discloses an improved image edge detection method. The improved image edge detection method comprise steps of S1, performing smoothing processing on an image and using an improved media filter to suppress noise, S2, obtaining a difference between a horizontal direction and a perpendicular direction through first-order-partial derivatives of directions of x,y,45 degrees and 135 degrees and thus obtaining a gradient amplitude and a gradient direction, S3, performing non-maximum value inhibition on the gradient amplitude, S4, using a gradient histogram to solve a high threshold and a low threshold and then using a double-threshold algorithm to perform edge detection on the image, and S5, performing sharpening processing and connecting the edges to obtain a final edge image. The improved image edge detection method use weighted media filtering to replace gauss filtering, uses the partial derivatives of four directions, uses the gradient histogram to determine the high threshold and the low threshold, reduces detection errors, improves detection accuracy, and makes the counter of the edge image more clear and continuity better.

The invention is suitable for the field of detection, and provides a defect detection method and a system. The method comprises the following steps of: acquiring the image of equipment to be detected, and preprocessing the acquired image; performing difference operation on a pre-stored grey scale template and the preprocessed acquired image to obtain a grey scale template difference image; performing binary processing on the grey scale template difference image to obtain a difference binary image; performing difference operation on a pre-stored binary template and the difference binary image to obtain a binary template difference image; and performing profile search on the binary template difference image, and judging whether the equipment to be detected has any defect according to a result of the profile search. Due to the adoption of the detect detection method based on dual template matching, image edge interference caused by light ray variation is reduced; and in particular for detection equipment with a complex surface, a false drop rate can be lowered effectively, detection accuracy is increased, and high practicability is achieved.

A method and system for detecting slant edge areas in an image comprising a plurality of pixels, and for preventing zigzagged slant edge artifacts in an image detail enhancement process. Image pixels that belong to a slant image edge are detected and gain suppression factors are determined for the detected pixels. The image is detail enhanced while selectively reducing enhancement of the detected image pixels relative to enhancement of other image pixels based on the gain suppression factors.

An edge-preserving diffusion filter maintains the sharp edges in images while smoothing out image noise. An edge-preserving diffusion filter applies an edge-preserving smoothing filter to an image to form a filtered image. The modified image is then blurred by a blurring filter to form a blurred image. The modified image and the blurred image are blended together to form an output image based on an error metric associated with each pixel. The edge-preserving diffusion filter may be utilized to perform a multilevel decomposition of the image. The edge-preserving diffusion filter may be applied to an unfiltered image to produce a base image. The difference between the unfiltered image and the base image defines a detail image. The detail image may be used as the input for recursively generating additional levels of detail. The multilevel decomposition may utilize filter kernels associated with different contrast levels for each iteration.

A Tracking Dip Estimator software including a novel Multi-Sine Tracking Software is adapted to be stored in a computer system memory for instructing a processor to produce a "first output" including a plurality of tracks in response to input borehole image data, and a "second output" including a plurality of "dip data" d in response to the plurality of tracks, the Tracking Dip Estimator software generating the "first output" and "second output" by:(1) pre-processing the input borehole image data with a Detector to output a plurality of image edge elements called "reports",(2) using the reports as input to a Multi-Sine Tracking software that recursively develops a "first output" including a plurality of tracks, or a plurality of connected sets of track points, lying along sinusoidal dip events in the input borehole image data; the Multi-Sine Tracking software has embedded mathematical models for sinusoidal dip events,(3) using the "first output" plurality of tracks as input to a Best Fit software that determines a set of pure sine curves that best fit the respective plurality of connected sets of track points, and develops a "second output" including a plurality of "dip data d corresponding to the plurality of "first output" tracks.

The invention relates to a method for purifying error matching of visual image characteristic points based on ORB (Oriented FAST and Rotated BRIEF). The method comprises the following steps of readingtwo to-be-detected left and right images shot under different viewing angles, constructing scale image pyramids for the images and performing grid processing; detecting characteristic points in eachsmall grid of each layer of pyramid images, extracting the characteristic points and determining a characteristic point coordinate; removing the characteristic points close to edges of the images, andcalculating the direction of a barycenter of the remaining characteristic points; calculating descriptors of ORB characteristic points; performing rough matching on the characteristic points of the two images; screening rough matching pairs of the characteristic points; removing error matching pairs again; and performing an RANSAC (Random Sample Consensus) algorithm iteration on the remaining characteristic points, and outputting the purified matching images. According to the method for purifying error matching of the visual image characteristic points based on the ORB, the detected characteristic points are uniformly distributed, the characteristic point clustering effect caused by easy huddle of multiple characteristic points is avoided, and the matching speed is accelerated while improving the matching accuracy.