Abstract: An analysis system for detection of defects within an inspection image of an inspected object, the inspection image comprising a plurality of pixels, the system including: a computerized segmentation module configured to segmentize the inspection image based on multiple anchor locations and on a mask which defines multiple mask-segments, by assigning each part out of multiple parts of the inspection image to a respective image-segment selected out of a multiple image segments, wherein the multiple image segments correspond to at least one mask-segment of said multiple mask-segments; and a defect detection processor configured to determine a presence of a defect in the inspection image based on the segmentation at least by assessing each pixel out of a plurality of pixels of the inspection image.

Abstract: A method for tracing edges of an image using hysteresis thresholding includes: (i) receiving an edge map of the image, (ii) scanning one row of the input edge map, (iii) assigning a label to each edge pixel in the row based at least in part on the presence or absence of a neighboring edge pixel, (iv) grouping contiguous labels, and (v) identifying groups of edge pixels.

Abstract: A system and method of processing an image is disclosed. A particular method of determining whether a particular pixel of an image is a feature candidate includes receiving data corresponding to a subset of a plurality of pixels surrounding the particular pixel. Each of the plurality of pixels may be from the image. The method further includes excluding the particular pixel from consideration as a feature candidate based on a comparison of values of the data to a comparison value. The comparison value may be based on an attribute value of the particular pixel and a threshold attribute value.

Abstract: A method for objectively evaluating quality of a stereo image is provided. The method obtains a cyclopean image of a stereo image formed in the human visual system by simulating a process that the human visual system deals with the stereo image. The cyclopean image includes three areas: an occlusion area, a binocular fusion area and a binocular suppression area. Representing characteristics of the image according to the singular value of the image has a strong stability. According characteristics of different areas of the human visual system while dealing with the cyclopean image, the distortion degree of the cyclopean image corresponding to the testing stereo image is presented by the singular value distance between cyclopean images respectively corresponding to the testing stereo image and the reference stereo image, in such a manner that an overall visual quality of the testing stereo image is finally evaluated.

Abstract: Embodiments described herein include an image-content dependent system for cutting a print in response to content of an image disposed on the print. The system includes a print cutter, a computer storage device, and a processing device. The print cutter cuts a print according to an image-content dependent cut pattern. The computer storage device stores image component metadata created from image content of an image disposed on the print to be cut. The processing device uses the image component metadata to generate the image-content dependent cut pattern to be used by the print cutter to cut the print.

Abstract: Techniques are disclosed relating to generating generic labels, translating generic labels to image pipeline-specific labels, and automatically adjusting images. In one embodiment, generic labels may be generated. Generic algorithm parameters may be generated based on training a regression algorithm with the generic labels. The generic labels may be translated to pipeline-specific labels, which may be usable to automatically adjust an image.

Abstract: A method for generating a feature descriptor is provided. A set of pre-generated sparse projection vectors is obtained. A scale space for an image is also obtained, where the scale space having a plurality scale levels. A descriptor for a keypoint in the scale space is then generated based on a combination of the sparse projection vectors and sparsely sampled pixel information for a plurality of pixels across the plurality of scale levels.

Abstract: Apparatus and methods disclosed herein provide for a set of reference images obtained from a camera and a reference image obtained from a viewpoint to capture an entire concave region of an object; a silhouette processing module for obtaining a silhouette image of the concave region of the object; and a virtual-image synthesis module connected to the silhouette processing module for synthesizing a virtual inside-out image of the concave region from the computed silhouette images and for generating a visual hull of the object having the concave region.

Abstract: Method for marking graphical elements comprising the steps of selecting at least three coherent edge portions (6) of a graphical element (1), wherein the relative orientation of the coherent edge portions (6) is constant and/or smoothly varies along their entire length, the coherent edge portions (6) comprising at least two reference edge portions (66) and one edge portion to mark (67); defining a family of smooth and non-intersecting curves (65), said curves (65) intersecting all of the coherent edge portions (66, 67); shifting the edge portion to mark (67) along the curves (65) relative to the reference edge portions (66); and method for detecting a marking in a graphical element, comprising the steps of locating an encoding area (7) in a digital image of a graphical element (1); retrieving at least two reference edge portions (66) and at least one modified edge portion (68) of the encoding area (7) in the digital image; and determining the relative position of the modified edge portion (68) relative to the

Abstract: Described herein are a system and a method for abnormal behavior detection using automatic classification of multiple features. Features from various sources, including those extracted from camera input through digital image analysis, are used as input to machine learning algorithms. These algorithms group the features and produce models of normal and abnormal behaviors. Outlying behaviors, such as those identified by their lower frequency, are deemed abnormal. Human supervision may optionally be employed to ensure the accuracy of the models. Once created, these models can be used to automatically classify features as normal or abnormal. This invention is suitable for use in the automatic detection of abnormal traffic behavior such as running of red lights, driving in the wrong lane, or driving against traffic regulations.

Abstract: According to one embodiment, a method includes acquiring information about a two-dimensional distribution of secondary electron intensity for a measurement target pattern, extracting, by a first method, an edge position of an edge for correction value acquisition, extracting, by a second method, an edge position of the edge for correction value acquisition, acquiring a difference between the edge positions extracted by the first and second methods, as a correction value, extracting, by the second method, an edge position of a desired edge based on the information about the two-dimensional distribution, and correcting the edge position of the desired edge based on the correction value.

Abstract: A training set for a post-filter classifier is created from the output of a face detector. The face detector can be a Viola Jones face detector. Face detectors produce false positives and true positives. The regions in the training set are labeled so that false positives are labeled negative and true positives are labeled positive. The labeled training set is used to train a post-filter classifier. The post-filter classifier can be an SVM (Support Vector Machine). The trained face detection classifier is placed at the end of a face detection pipeline comprising a face detector, one or more feature extractors and the trained post-filter classifier. The post-filter reduces the number of false positives in the face detector output while keeping the number of true positives almost unchanged using features different from the Haar features used by the face detector.

Abstract: According to one embodiment, an image processing system includes a decoder, a corresponding area detector and an image corrector. The decoder is configured to decode an input image signal obtained by encoding a plurality of images viewed from a plurality of viewing points different from each other, to generate a first image signal, a second image signal, and a motion vector for referring to the first image from the second image. The corresponding area detector is configured to detect a corresponding area in the second image, the corresponding area corresponding to a target block in the first image. The image corrector is configured to mix each pixel in the target block with each pixel in the corresponding area according to a degree of similarity between the target block and the corresponding area, to generate a third image signal.

Abstract: An image processing apparatus includes: an image feature outputting unit that outputs each of image features in correspondence with a time of the frame; a foreground estimating unit that estimates a foreground image at a time s by executing a view transform as a geometric transform on a foreground view model and outputs an estimated foreground view; a background estimating unit that estimates a background image at the time s by executing a view transform as a geometric transform on a background view model and outputs an estimated background view; a synthesized view generating unit that generates a synthesized view by synthesizing the estimated foreground and background views; a foreground learning unit that learns the foreground view model based on an evaluation value; and a background learning unit that learns the background view model based on the evaluation value by updating the parameter of the foreground view model.

Abstract: An image processing apparatus includes a detector to detect a face. The image processing apparatus sets a size of the face to be detected, changes a detection condition for face detection in accordance with the size of the face set, applies the detection condition changed to the detector, and detects the face from the image by use of the detector to which the detection condition is applied.

Abstract: An image processing apparatus includes a noise removal unit that corrects a geometric mismatch of optical noise of a left eye image and a right eye image by performing a noise removal process for removing the separately generated optical noise on the left eye image and the right eye image which are captured and obtained by a two-lens type stereoscopic image capturing camera.

Abstract: An electronic device may include a housing and at least one infrared (IR) proximity sensor carried by the housing. The at least one IR proximity sensor may include an IR emitter configured to emit IR illumination toward a user, and an IR sensor configured to sense reflected IR illumination from the user. The electronic device may also include a camera carried by the housing and configured to capture an image of the user's face based upon the reflected IR illumination. The electronic device may further include a controller configured to apply facial recognition to the captured image of the user's face based upon the reflected IR illumination.

Abstract: A pattern analysis method includes the steps of: grouping a plurality of polygons in a circuit layout into a plurality of polygon groups; locating a potential defect area of each polygon group according to an aerial image of the circuit layout; determining a representing point of the potential defect area of each polygon group; determining representing points of the plurality of polygons in each polygon group; and comparing a distribution pattern of the representing points of the plurality of polygons relative to the representing point of the potential defect area in one of the polygon groups with a distribution pattern of the representing points of the plurality of polygons relative to the representing point of the potential defect area in another of the polygon groups. The steps aforesaid are executed by a processor in a computer system.

Abstract: A method is provided for visualizing a surgical trajectory (32, 101, 42, 46, 47). The method comprises steps of receiving (71) 3D imaging information (31) of a region to undergo surgery and combining (72) the received 3D imaging information (31) with data from a digitized anatomical atlas. As a result, a combined map of the region to undergo surgery is obtained. The combined map comprises expected positions of anatomical structures (102, 103, 104) in the region to undergo surgery. The method further comprises steps of receiving (73) the surgical trajectory (32, 101, 42, 46, 47) for the surgery, determining (74) positions of intersections (43, 44) of the surgical trajectory (32, 101, 42, 46, 47) with the anatomical structures (102, 103, 104) and providing (75) the positions of the intersections (43, 44) in a coordinate system aligned with the surgical trajectory (32, 101, 42, 46, 47).

Abstract: A blur classification module may compute the probability that a given pixel in a digital image was blurred using a given two-dimensional blur kernel, and may store the computed probability in a blur classification probability matrix that stores probability values for all combinations of image pixels and the blur kernels in a set of likely blur kernels. Computing these probabilities may include computing a frequency power spectrum for windows into the digital image and/or for the likely blur kernels. The blur classification module may generate a coherent mapping between pixels of the digital image and respective blur states, and/or may perform a segmentation of the image into blurry and sharp regions, dependent on values stored in the matrix. Input image data may be pre-processed. Blur classification results may be employed in image editing operations to automatically target image subjects or background regions, or to estimate the depth of image elements.