Abstract: A non-destructive evaluation system and method is provided for detecting flaws in an object. The system includes a lamp for impinging the object with optical pulses and a focal plane array camera configured to capture the images corresponding to evolution of heat due to an impact of the optical pulses in the object. The system also includes an image acquisition system for capturing data corresponding to the images from the focal plane array camera. Both transmission mode imaging and reflection mode imaging techniques are used in an exemplary embodiment. A time of flight analysis system is also provided for analyzing the data from both transmission mode imaging technique and reflection mode imaging technique. The data from transmission mode imaging is used to determine thickness values at different points in the data and for determining location of flaws using the thickness values. The data from reflection mode imaging is used for determining depth of these flaws.

Abstract: There is provided a medical image processing apparatus including an image-extracting section extracting a frame image from in vivo motion picture data picked up by an in vivo image pickup device or a plurality of consecutively picked-up still image data, and an image analysis section analyzing the frame image extracted by the image-extracting section to output an image analysis result. The image analysis section includes a first biological-feature detection section detecting a first biological feature, a second biological-feature detection section detecting, based on a detection result obtained by the first biological feature detection section, a second biological feature in a frame image picked up temporally before or after the image used for detection by the first biological feature detection section; and a condition determination section making a determination for a biological condition based on a detection result obtained by the second biological feature detection section to output the determination.

Abstract: The present invention relates to a method of automated process control operation wherein a physical object is directed into a read zone, information stored on an ID Container attached to the physical object is retrieved, physimetric property of the physical object is captured, the retrieved information is processed to provide recorded physimetric property specific to the physical object, the recorded physimetric property and captured physimetric property are passed to an analysis algorithm for comparison, and the results of the comparison are delivered to a controlling device. The results of the comparison will determine whether the physical property will continue to pass through the read zone or require to be rotated by the operator.

Abstract: An apparatus including a memory for storing information associating a fingerprint input with a function of the apparatus; a user input device including a device for detecting a multi-fingerprint input, the multi-fingerprint input including a plurality of fingerprints where each fingerprint is associated with a different function of the apparatus; and a processor configured to identify the plurality of fingerprints within the multi-fingerprint input and, in response to the identification of the plurality of fingerprints, determine a function associated with the multi-fingerprint input and enable access to that function, wherein the function associated with the multi-fingerprint input is a combination of the functions associated with the plurality of fingerprints within the multi-fingerprint input.

Abstract: A method and system analyzes data acquired by image systems to more rapidly identify objects of interest in the data. In one embodiment, z-depth data are segmented such that neighboring image pixels having similar z-depths are given a common label. Blobs, or groups of pixels with a same label, may be defined to correspond to different objects. Blobs preferably are modeled as primitives to more rapidly identify objects in the acquired image. In some embodiments, a modified connected component analysis is carried out where image pixels are pre-grouped into regions of different depth values preferably using a depth value histogram. The histogram is divided into regions and image cluster centers are determined. A depth group value image containing blobs is obtained, with each pixel being assigned to one of the depth groups.

Abstract: A method and apparatus is described for recording and digitizing intensity profiles (IP) of the papillary structure of the skin with high intensity resolution using sensors S with low intensity resolution. For this purpose, a plurality of digital image signals (DS, DS1, DS2) of an identical subarea e.g. of a fingerprint are recorded, whereby the continuous intensity domain (KI) of the fingerprint is scanned in different intensity resolutions, and/or different portions (A1, A2) of said continuous intensity domain (KI) are mapped to discrete intensity domains of the single digital image signals (DS, D1, DS2). By the pixelwise combination of all digital image signals (DS, DS1, DS2), a digital fingerprint image signal (PS) is finally produced whose discrete intensity domain (DI) represents a larger portion of the continuous intensity domain (KI) of the fingerprint and/or has a higher resolution intensity than each single one of the digital image signals (DS, DS1, DS2).

Abstract: A method for determining values of motion vectors includes receiving an irregular pattern of motion vectors for a target image, estimating an initial value for each of the motion vectors, using the motion vectors to generate a tap structure for an adaptive temporal prediction filter, and using the tap structure to re-estimate the value of each motion vector.

Abstract: A method of extracting information parts, and a recorded medium recording the method, for retrieving image sequence data are disclosed. According to an embodiment of the present invention, image frames included in an image sequence are converted to frames, in a quantity of n, including only the object that is separated from a background, and the corresponding shape descriptors, in a quantity of n, are extracted. The shape descriptors, in a quantity of n, are aligned according to a temporal order, to generate a shape sequence, which is frequency-converted along the time axis to obtain conversion coefficients having frequency information. Using coefficients in a low frequency area among the obtained conversion coefficients, a shape sequence descriptor is extracted. With this invention, video data expressing the motion of an object can be captured as an image sequence, and the similarity between video data can be distinguished by extracting information parts from each image sequence.

Abstract: A method is disclosed for an imaging device, for anatomically assigning an image generated by the imaging device to object components of an object. Further, a computer program product and computer readable medium are disclosed, which are set up to carry out such a method. In the method, the object components are identified in a substantially autonomous fashion in an overview image that covers a larger area than an examination area. The image of the examination area is automatically assigned to at least one object component identified in the overview image given a known positional relationship between the image and the overview image, such that there is no need for an operator to carry out an individual assignment of the imaged object components.

Abstract: Digital signals, such as image/video signals are converted between a first format and a second format by using Multiple Description Coding, whereby the second format conveys multiple descriptions (D1 to D4; D1? to D4?) of the digital signals. In combination with MD coding, the signals are jointly subject to an error concealment process. Preferably, the error concealment process takes place in converting said digital signals from the second format conveying multiple descriptions to the first format.

Abstract: In an intelligent video surveillance system, video processing software performs a number of operations on video data received from a camera, including foreground extraction, shadow removal and object tracking. The foreground extraction stage classifies each pixel of a received frame as representing either foreground or background. Since shadow regions can be wrongly classified as foreground, a two-branch shadow removal operation is employed, comprising weak shadow removal (32) and strong shadow removal (33). The purpose of weak shadow removal (32) is to remove only the most severe shadows in each frame. Conversely, the purpose of strong shadow removal (33) is to remove substantially every shadow present in each frame. By comparing the overlap of foreground regions in the two resulting images, it is possible to identify foreground regions that have fragmented due to strong shadow removal, and thereafter classify them as representing a common foreground object.

Abstract: System and method for digitally watermarking data. A preferred embodiment comprises a quantizer to limit a data value provided by a signal input to a set of values, a rounder unit coupled to the quantizer, a control unit coupled to the rounder unit and to a watermark input, and a multiplexer having a first input coupled to the rounder unit and a control input coupled to the control unit. The rounder unit rounds a quantized data value to a nearest integer, the control unit provides a control signal based on the rounded, quantized data value and a parity of a watermark provided by the watermark input, and the multiplexer selects between an output of the rounder unit, an incremented output of the counter unit, and a decremented output of the counter unit, based on the control signal provided by the control unit.

Abstract: Some embodiments of the present invention may relate to a device and a method of enabling the stabilization of a series of retinal angiography images to provide a coherent serial display, the method comprising: locally matching a pair of overlapping images, said locally matching includes at least providing a best offset vector for the images, wherein the best offset vector is provided based upon a matching of features from overlapping portions of the images; globally matching at least a triplet of matching pairs of images, wherein pairs of globally matching images include locally matching pairs whose best offset vector sum is substantially zero; choosing a key image; and aligning all the remaining images to the key image.

Abstract: A lane mark recognition apparatus includes an image capturing means (30) which captures a color image (IM—0) of a road via a color video camera (10), a specific-color-extracted image generating means (31) which generates a luminance-extracted image (IM—1) obtained by extracting white-color data from the color image (IM—0) and a yellow-color-extracted image (IM—2) obtained by extracting yellow-color data from the color image (IM—0), and a lane mark detection means (50a) which detects a white line and a yellow line from a composite image (IM_C) formed from the luminance-extracted image (IM—1) and the yellow-color-extracted image (IM—2) and outputs position data (Pd1) of the white line and position data (Pd2) of the yellow line.

Abstract: A method of performing adaptive temporal prediction includes receiving a target image, wherein a position of an object in the target image is different from a position of the object in a reference image, using a boundary of the object to generate an irregular pattern of target image motion vectors, using the target image motion vectors to partition the target image into area of influence cells, wherein each area of influence cell contains a unique one of the target image motion vectors, and generating a prediction of the target image by applying an adaptive area of influence filter to the area of influence cells.

Abstract: A method and an apparatus localize an object part location in a digital image. The method according to one embodiment accesses digital image data containing an object part; obtains an initial position estimate for object part location of the object part; extracts a sub-image window around the initial position estimate of the object part location; calculates feature values based on pixel values within the sub-image window; and determines an updated position estimate for the object part location based on the calculated feature values.

Abstract: There is described a method for a periodic and three-dimensional representation of a periodically variable structure. A number of rotation images is generated for this purpose. The required rotations relating to the same event of the periodic process are started at intervals offset by a defined angle. From the rotation images, new image series are assembled with which three-dimensional representations relating to different phase ranges of the period are reconstructed.

Abstract: A method of registering 3-dimensional digitized images to 2-dimensional digitized images during a medical procedure includes providing a pair of correctly-registered training images L={lr, lf} and their joint intensity distribution pl(ir, if), wherein ir and if are reference and floating images, respectively, providing a pair of observed images O={or, of} and their joint intensity distribution po(ir, if), mapping a marginal intensity distribution of the observed pair O={or, of} to a marginal intensity distribution of the training pair L={lr, lf}, and estimating a set of parameters T that registers image of to image or by maximizing a weighted sum of a Jensen-Shannon divergence (JSD) of a joint intensity distribution of the observed pair and a joint intensity distribution of the training pair and a similarity measure between the observed images.

Abstract: Various technologies and techniques are disclosed that improve cursive handwriting recognition. Cursive handwriting input is received from a user. The system performs a hierarchical prototype search as part of a recognition operation. A same space search is performed against a mixed database that has both print and cursive samples. A same space search is also performed against a cursive database that has only cursive samples. The results of these two same space searches are merged into a combined alternate list. The combined alternate list is then used as a constraint for the dynamic time warp searches that are performed against the mixed and cursive databases, respectively. The results of the dynamic time warp searches are also merged into a final combined alternate list, and the combined alternate list is used to make a recognition decision regarding the user's handwritten input.

Abstract: A system and method for identifying an unknown individual from a plurality of enrolled individuals is provided. In an embodiment, the method comprises comparing at least two parameters of the unknown individual to at least two enrolled parameters of the enrolled individuals. The method then determines a score correlating to the closeness of the comparison and then stores the score.