486 results about "Image boundary" patented technology

A method, system, and computer-usable tangible storage device for robustly cropping and accurately recognizing license plates to account for noise sources and interfering artifacts are disclosed. License plate images and sub-images can be tightly cropped utilizing an image-based classifier and gradient-based cropping. An image-based classifier can identify the location of valid characters within the image. Because of a number of noise sources, such as, for example, residual plate rotation and shear in the characters within the image, the image-based classifier performs a “rough” identification of the image boundaries. An additional processing step utilizing gradient-based cropping is performed to fine-tune the license plate image boundaries. Gradient-based cropping eliminates unwanted border artifacts that could substantially impact the segmentation and license plate character recognition results.

Low-profile, large screen display using a rear projection array system using an array of micro projectors, each comprised of a micro-display device, several optical components, a red/green/blue (RGB) light emitting diode (LED) light source, a light sensor device for each color and power driving and interface electronics circuits. The plurality of Micro Projectors are arranged as an array along the vertices of a grid to conjointly project a uniform and seamless image that is comprised of the collective projected output pixels (sub-image) of the array of Micro Projectors. The Array Controller processes output signals generated by the light sensors embedded in each Micro Projector in the array and generates pixel grayscale input and light source control signals for each of the Micro Projectors in the array to maintain uniform luminance and chromaticity (color-point) across the array. Various features are disclosed, including tapering and diffusion of the sub-image boundaries to form a single large display.

Techniques are disclosed for reducing scan times in mass spectral tissue imaging studies. According to a first technique, a tissue imaging boundary is defined that closely approximates the edges of a tissue sample. According to a second technique, a low-resolution scan is performed to identify one or more areas of interest within the tissue sample, and the identified areas of interest are subsequently scanned at higher resolution.

An image display method for displaying a combined image by capturing images at areas surrounding a vehicle includes a) calculating a plurality of displacement vectors for a plurality of points taken on images captured by a plurality of cameras upon the application of a load that changes the attitude of a camera on the vehicle, and b) determining each image borderline between two adjacent images such that a difference in the directions of displacement vectors in the neighborhood of each image borderline between two adjacent images does not exceed a predetermined angle.

Some embodiments provide a method for editing an image. For a displayed image, the method draws a partial boundary based on movement of a cursor over the image. The partial boundary does not fully divide the image into a region of interest and a second region. Upon completion of the cursor movement, the method automatically extends at least one end of the boundary in order to divide the image into the region of interest and the second region. The method applies edits (e.g., color correction) to only the region of interest of the image. In some embodiments, automatically extending at least one end of the boundary involves (i) extending one or both of the ends to points at which the boundary ends intersect borders of the image and (ii) connecting the boundary from the intersection points along the borders of the image.

An image boundary line candidate pixel detection section detects image boundary line candidate pixels as candidates for pixels specifying an image boundary line from each frame of video and outputs, for each frame, image boundary line candidate pixel information as information indentifying the image boundary line candidate pixels. A line extraction section extracts for each frame as the image boundary line a line specified by the image boundary line candidate pixels indicated by the image boundary line candidate pixel information and output image boundary line description information as information describing the image boundary line for each frame. An image boundary line having frame-set period detection section judges whether or not a frame has the image boundary line for each frame by using the image boundary line description information of respective frames and detects a frame-set period including successive frames having the image boundary line as a frame-set period including special effect.

The invention discloses an edge blending method for splicing multiple projection images, comprising the following steps: setting the size value of a projection overlapping region between adjacent projection images; cutting each frame of image based on pixels according to the number and the resolution of projectors and the size value of the projection overlapping region; setting the sensitivity weights of color channels of red, green and blue of each projector; calculating the boundary distance from each pixel point in each image to the boundary of the image; according to the boundary distance and the size value of the projection overlapping region, calculating the color weight of each pixel point; according to the sensitivity weights of the color channels and the color weight of the pixel point, calculating to obtain the pixel attenuation weight vector of the projection overlapping region; and respectively multiplying the red color value, the green color value and the blue color value of each pixel point in the image overlapping region by the respective pixel attenuation weight vector. The edge blending method overcomes the image overlapping region display defects in the existing multi-projector projection technology, and realizes that images from multiple projectors form smooth transition in the overlapping region, thereby greatly improving the whole visual effect of a picture.

The invention is suitable for a robot field, and provides a planning platform based on a mowing robot. The planning platform comprises an image boundary identification device, which is used for acquiring an image of a to-be-planned area, is used for processing the image, is used to identify the boundary of the to-be-planned area, and is used to output boundary image information after being processed to a control device; a positioning device, which is used to acquire the main positioning data of the platform to form first positioning information, and is used to output the first positioning information to the control device; an inertia device, which is used to acquire the inertia data of the platform during a moving process, is used to process the inertia data to be the second positioning information of the platform, and is used to output the second positioning information to the control device ; the control device, which is used to process the boundary image information, the second positioning information, and the first positioning information to form the map of the to-be-planned area, is used for route planning according to the map, and is used to control the moving of the platform according to the planned route. The planning platform has advantages of low requirements on operation places, low construction quantity, high mowing efficiency, high mowing coverage, and ability of reducing complexity of devices and costs.

A vehicle vision system that uses a depth map, image intensity data, and system calibration parameter to determine a target's dimensions and relative position. Initial target boundary information is projected onto the depth map and onto the image intensity. A visibility analysis determines whether the rear of a target is within the system's field of view. If so, the mapped image boundary is analyzed to determine an upper boundary of the target. Then, vertical image edges of the mapped image boundary are found by searching for a strongest pair of vertical image edges that are located at about the same depth. Then, the bottom of the mapped image boundary is found (or assumed from calibration parameters). Then, the target's position is found by an averaging technique. The height and width of the target are then computed.

A system and method for motion compensation of color sequential displays, receiving a motion image data input, extracting an estimate of a motion of an image portion represented in said image data input with a motion estimator, and calculating, for a time instance of display of each image subframe of an image frame, a compensated representation for reducing display artifacts with a processor, wherein each subframe represents a different aspect of the image frame. The subframes are preferably different color planes of the image frame. The processor preferably performs a bilinear interpolation where the compensated image boundary does not fall on a display pixel boundary. The motion compensation algorithm is preferably robust in the face of erroneous motion vectors. The system and method is advantageously used in single panel liquid crystal display projection systems, although the techniques are applicable to various image display technologies.

The invention particularly relates to a method for detecting the camber of plates based on machine vision, belonging to the automatic control field of steel rolling processes. The method comprises thefollowing steps: obtaining plate images through plane array CCD cameras installed right above a roller way outside of roller beds in front of and behind a rolling mill, and correcting the distortionof the images through camera calibration; performing Gaussian low-pass frequency domain filtering on the corrected images, and performing image sharpening differential operation on the filtered imagesto enhance the image boundary. Mathematical morphology transformation and threshold binarization are carried out on the images with enhanced boundaries to segment and completely extract the plate image. The pixel coordinates of the edge contour points are extracted by using the Canny edge detection operator after threshold segmentation and the sub-pixel coordinates of the plate edges are obtained by using the improved Zernike orthogonal moment sub-pixel edge detection algorithm, and the camber value is obtained by fitting.

A method is disclosed of analyzing an image to identify “must exclude” regions and of determining the best fit of an image outline so as to generate an image boundary that excludes the majority of “must exclude” regions. The method is applicable to the automatic generation of greeting cards and photo-montages.

An estimated motion vector within image signals to obtain robust motion vectors is provided by creating at least one candidate motion vector for at least one current block within an image of the signal, determining for each of said candidate motion vectors at least one match block within at least one image which is temporally neighboring the image of the current block, detecting if the at least one match block lies at least partially outside the active area of the image, then candidate motion vector is calculated based on at least the shifted current block and the shifted match block and shifting at least the current block and the match block such that the match block lies within the active area of the image.

The invention relates to a multi-scale velocity field measurement method for adjacent two frames in a sun high-resolution image sequence and belongs to the astronomical and image technical field. The method comprises the following steps: to begin with, carrying out image pretreatment: expanding image boundary of the adjacent two frames; then, decomposing the two frames into two frame pyramid images; next, carrying out segmentation on the two frame pyramid images layer by layer; measuring block displacement between the two frames; obtaining point-by-point displacement amount between the two frames through weighted smoothing and interpolating calculation; then, superposing the displacement amount between the two frames of all layers of the images; and finally, obtaining comprehensive displacement amount and velocity field between the two frames. The method can calculate the velocity field between the two frames more accurately, and effectively improves measurement precision of the velocity field.

In a system for segmenting a pixel based image, pixels containing image boundaries are identified. The image boundaries are then fattened by repeatedly adding fattening rows of pixels to the pixels containing boundaries to separate the remaining pixels into separate segments. The separate segments are then grown back to their original size before the boundaries were fattened. This operation has the effect of linking the boundaries together to separate the image into segments and to extend incomplete boundaries into complete boundaries around segments in the image.

Disclosed is an image encoding method comprising the steps of: configuring block division information and size information of a boundary block which is located at a boundary of an image and is smaller than a size of a basic encoding block, on the basis of size information of a picture and size information of the basic encoding block; dividing the boundary block into at least one encoding block, on the basis of the size information of the basic encoding block and the size information and the block division information of the boundary block; and encoding the at least one divided encoding block.

The invention discloses a method for automatically segmenting liver tumors in abdominal CT sequence images. The method comprises the following steps of: preprocessing: preprocessing an abdominal CT sequence image so as to obtain a liver area in the image; liver enhancement: improving a contrast ratio of normal liver parenchyma to tumor tissue by adoption of a segmented nonlinear enhancement operation and an iterative convolution operation according to a grey level distribution characteristic of the liver area; automatic segmentation: constructing an image segmentation energy function for multi-target segmentation by utilizing the enhancement result and combining image boundary information, minimizing the energy function by adoption of an optimal algorithm and obtaining a liver tumor preliminary automatic segmentation result; and post-processing: optimizing the preliminary segmentation result by adoption of a three-dimensional mathematic morphological open operation, and removing mis-segmented areas to improve the segmentation precision. The method is beneficial for helping radiological experts and surgeons to timely and effectively obtaining overall information and three-dimensional display of liver tumors and providing technical support for computer-aided diagnosis and treatment of liver diseases.

The invention discloses an image processing method and device. The image processing method is applied to a display unit comprising an optical amplification part. The method includes the steps that a marginal area in an image area is determined, and the image area except the marginal area serves as a middle area; image reduction processing is conducted on images in the marginal area in the image boundary direction; image magnification processing is conducted on images in the middle area in the image boundary direction; the images which are reduced and magnified are displayed through the display unit, and therefore the display unit can present images in the same proportion. According to the image processing method and device, under the effect of the optical amplification part, the images with the marginal areas reduced are magnified in vision, the magnification proportion of the images is equal to that of the images in the middle area, so that the display unit presents the images which are consistent in proportion, and therefore the images are displayed in a non-deformation mode in overall vision.

Systems and methods relating to SAR image processing and object detection within a SAR image. A sea clutter model in which the texture random variable is drawn from a finite and discrete set of values is used in the processing of SAR derived images. SAR images are divided into sub-images, each sub-image being processed in turn. A statistical test is applied to each sub-image to determine whether it contains pixels representing only non-clutter information. The statistical test is based on the sea-clutter model, parameters of which are derived and adapted from each sub-image. The model is designed such that it will not permit more than a pre-determined number of false alarms. Pixels in each sub-image with information other than clutter are clustered, according to proximity, into object detections. Detections from all sub-images are combined to provide global object detection and to group clusters that may have split across sub-image boundaries.