Abstract: A method for finding a defective machine comprises the steps of selecting a searching period in which a plurality of wafer lots including good wafer lots and bad wafer lots passes through machines, acquiring a lot-passing information related to the passing sequence of the wafer lots through the machines, calculating a bad-lot continuity by taking the lot-passing information into account, and determining a defective machine by taking the bad-lot continuity into account. The bad-lot continuity is calculated by the steps of determining an impact period based on the aggregation degree of the bad wafer lots, calculating a bad-lot distribution probability in the impact period, and calculating the bad-lot continuity by taking the bad-lot distribution probability into account.

Abstract: A mask pattern verifying method include obtaining first information about a hot spot from design data of a mask pattern, obtaining second information about the mask pattern actually formed on a photo mask, and determining a measuring spot of the mask pattern actually formed on the photo mask, based on the first and second information.

Abstract: A device for evaluating defects in the edge area of a wafer (6) is disclosed. The evaluation may also be performed automatically. In particular, the device includes three cameras (25, 26, 27), each provided with an objective (30), wherein a first camera (25) is arranged such that the first camera (25) is opposite to an edge area on the upper surface (6a) of the wafer (6), wherein a second camera (26) is arranged such that the second camera (26) is opposite to a front surface (6b) of the wafer (6), and wherein a third camera (27) is arranged such that the third camera (27) is opposite to an edge area on the lower surface (6c) of the wafer (6).

Abstract: A method for manufacturing an electronic device is provided. The method includes: pressure-bonding a plurality of terminals of an electronic component to a plurality of electrodes formed on a surface of a transparent substrate, respectively, via an anisotropic conductive film to mount the electronic component on the transparent substrate; obtaining an image of the electrodes by imaging the transparent substrate with the electronic component mounted thereon from backside of the transparent substrate; measuring the number of indentations for each said electrode using the image of the electrode, the indentation being formed when the electrode is pressed by a conductive particle in the anisotropic conductive film; calculating an average and a standard deviation of the number of indentations per electrode throughout the transparent substrate; and calculating a probability that the number of indentations per electrode is less than a reference value on basis of the average and the standard deviation.

Abstract: An apparatus for inspecting pattern defects, the apparatus including: a defect candidate extraction unit configured to perform a defect candidate extraction process by comparing a detected image signal with a reference image signal; and a defect detection unit configured to perform a defect detection process and a defect classification process based on a partial image containing a defect candidate that is extracted by the defect candidate extraction unit, wherein the processes performed by the defect candidate extraction unit and/or the defect detection unit are performed asynchronously with an image acquisition process.

Abstract: Disclosed is a method of locating systematic defects in integrated circuits. The invention first performs a preliminary extracting and index processing of the circuit design and then performs feature searching. When performing the preliminary extracting and index processing the invention establishes a window grid for the circuit design and merges basis patterns with shapes in the circuit design within each window of the window grid. The invention transforms shapes in a each window into feature vectors by finding intersections between the basis patterns and the shapes in the windows. Then, the invention clusters the feature vectors to produce an index of feature vectors. After performing the extracting and index processing, the invention performs the process of feature searching by first identifying a defect region window of the circuit layout and similarly merging basis patterns with shapes in the defect region window. This merging process can include rotating and mirroring the shapes in the defect region.

Abstract: In the fabrication of a semiconductor integrated circuit device, a 2D-3D inspection technique for solder printed on a substrate is provided which permits easy preparation of data and easy visual confirmation of a defective portion. In a substrate inspecting step, first, a 3D inspection is performed, followed by execution of 2D inspection, whereby a 2D picked-up image of the portion of a pad determined to be defective can be displayed on a larger scale simultaneously with the end of inspection, thereby providing an environment for efficient visual confirmation of the defect. Further, by subjecting a raw substrate to measurement at the time of preparing inspection data, a relation between an original height measurement reference generated automatically by the inspection system and the height of a pad upper surface is checked, whereby it is possible to measure the height and volume of printed solder based on the pad upper surface.

Abstract: For assessing the position and quality of joins a combined image of a join including a light line image and a grey value image is taken in the same sensor, but in two different regions 20, 22 of the sensor. The grey value image is evaluated to detect the quality of the join. This allows both the position and the quality of the join to be detected in a simple way.

Abstract: A localization method of a moving robot is disclosed in which the moving robot includes: capturing a first omni-directional image by the moving robot; confirming at least one node at which a second omni-directional image having a high correlation with the first omni-directional image is captured; and determining that the moving robot is located at the first node when the moving robot reaches a first node, at which a second omni-directional image having a highest correlation with the first omni-directional image is captured, from among the at least one node.

Abstract: A 3-dimensional scanner capable of acquiring the shape, color, and reflectance of an object as a complete 3-dimensional object. The scanner utilizes a fixed camera, telecentric lens, and a light source rotatable around an object to acquire images of the object under varying controlled illumination conditions. Image data are processed using photometric stereo and structured light analysis methods to determine the object shape and the data combined using a minimization algorithm. Scans of adjacent object sides are registered together to construct a 3-dimensional surface model.

Abstract: A two dimensional/three dimensional (2D/3D) digital acquisition and display device for enabling users to capture 3D information using a single device. In an embodiment, the device has a single movable lens with a sensor. In another embodiment, the device has a single lens with a beam splitter and multiple sensors. In another embodiment, the device has multiple lenses and multiple sensors. In yet another embodiment, the device is a standard digital camera with additional 3D software. In some embodiments, 3D information is generated from 2D information using a depth map generated from the 2D information. In some embodiments, 3D information is acquired directly using the hardware configuration of the camera. The 3D information is then able to be displayed on the device, sent to another device to be displayed or printed.

Abstract: A method, system and computer program product for detecting presence of an object in an image are disclosed. According to an embodiment, a method for detecting a presence of an object in an image comprises: receiving multiple training image samples; determining a set of adaptive features for each training image sample, the set of adaptive features matching the local structure of each training image sample; integrating the sets of adaptive features of the multiple training image samples to generate an adaptive feature pool; determining a general feature based on the adaptive feature pool; and examining the image using a classifier determined based on the general feature to detect the presence of the object.

Abstract: The present invention provides a system and method for identifying a pattern as belonging to one of a set of predetermined classes of patterns. The system comprises a plurality of classifier blocks wherein each classifier block corresponds to a distinct predetermined class of patterns and produces a mirror image of an input pattern if the input pattern belongs to the predetermined class. The system also comprises a plurality of sub-classifier blocks wherein each sub-classifier block corresponds to a distinct predetermined sub-class of a predetermined class of patterns and is coupled to a classifier block corresponding thereto for producing a mirror image of an input pattern if the pattern belongs to the predetermined sub-class. The system further comprises an input unit for capturing the pattern for identification and an output unit for displaying at least one of a mirror image of an input pattern and an identified class and sub-class of the input pattern.

Abstract: An image processing apparatus includes a first separator, a second separator, a dividing unit, and a generating unit. The first separator separates image data into character image data and other image data. The second separator separates the character image data into shape image data and color image data. The dividing unit divides the shape image data and the color image data based on a dividing size decided from the size of the image data and the capacity of processing memory used in output processing of the image data. The generating unit generates additional information for combining a corresponding pair of divided shape image data and divided color image data with the other image data.

Abstract: An image processer has an extractor to extract a character area from color image data. A color-difference-value acquirer acquires information about color-difference values in the character area. A color-saturation-value acquirer acquires information about color saturation in the character area. A color-difference-subrange storage stores pre-defined color-difference subranges. A chromatic-region determination section determines the character area as gray when color salutation values fail to satisfy a condition for a chromatic color, and determines the character area as a chromatic region when color saturation values in the character area satisfy the condition. A first color-difference-subrange assignment section assigns a stored color-difference subrange to the character area determined as the chromatic region based on information about color-difference values.

Abstract: An improved solution for categorizing moving objects into familiar colors in video is provided. In an embodiment of the invention, a method for categorizing moving objects into familiar colors in video comprises: receiving a video input; determining at least one object track of the video input; creating a normalized cumulative histogram of the at least one object track; and one of: performing a parameterization quantization of the histogram including separating the histogram into regions based on at least one surface curve derived from one of saturation and intensity; or identifying a significant color of the quantized histogram.

Abstract: A histogram generating section generates a histogram for each channel of a color space which shows colors of pixels constituting an image, in which tone levels of said channel are divided into plural intervals as classes, and frequency of appearance of tone levels of the pixels in each interval is shown as degree. An interval extraction section extracts the intervals in each of which the frequency of appearance becomes local maximal value. A score calculation section calculates scores of the extracted intervals. The score indicates visibility of color to human based on human color sense. An interval selection section selects one or more extracted interval to be representative color, based on the calculated scores. A representative color extraction section generates the representative colors based on tone levels of the selected intervals.

Abstract: Exemplary embodiments are described in which is performed not only a shot detection (continuous recording with a camera) and an association of several key-frames to the shots, it then being possible for a subsequent scene recognition to be based on the grouping of shots into scenes. Rather, it is observed that a scene only relates to one event in a setting. Since both can change within a shot, not every scene boundary is at the same time also a shot boundary. In addition, not every shot is short enough, so that a reliable retrieval of different picture contents is not guaranteed. Therefore, exemplary embodiments are shown which are capable of defining sub-shots so that in principle, scene and shot boundaries are also sub-shot boundaries at the same time. Sub-shots furthermore include only video pictures with a small change in picture content.

Abstract: An improved solution for detecting events in video is provided, in which a region of interest within a series of video images of the video is monitored. An object at least partially visible within the series of video images is tracked and a fiducial region of the object is identified. The fiducial region is one or more points and/or area(s) of the object, which are relevant in determining whether an alert should be generated. The fiducial region is monitored with respect to the region of interest and a restricted behavior. When the restricted behavior is detected with respect to the region of interest, an alert is generated.

Abstract: User friendly coding systems are provided for Chinese characters, either complicated or simplified. Each Chinese character is assigned a code based on the shape of the character. In particular, the characters sharing the same beginning strokes are grouped together. The coding systems are useful for searching or sorting Chinese characters, as well as for typing Chinese characters on a computer or word processor.

Abstract: A method and system provides intelligent node-link diagram creation and editing, including an electronic display device having a surface on which a writing and/or drawing canvas is provided. An input device permits writing and/or drawing of electronic ink strokes, and a computing device is in operative association with the electronic display and the input device, and has stored therein for operation in connection with actions of the input device, a user interface (UI). The UI includes a graphical user interface (GUI) module, which controls input and display of the ink strokes applied to the canvas by the input device, and a recognition module which interprets the ink strokes by performance of structure recognition operations.

Abstract: The invention relates to a method for using portable electronic equipment, which comprises a digital camera or can be used with a digital camera, to scan a surface containing text and/or drawings or sketches. According to the method, a digital photograph, which comprises the surface to be scanned, is taken with the digital camera of the electronic device. The text and/or drawings or sketches of the surface to be scanned are transferred to a digital image file, maintaining both their own and their mutual spatial arrangement. The effects that appear during the creation of the photograph comprising the surface to be scanned and that have a detrimental effect on the image, for example geometric distortion, lack of focus, blurring, shadows and/or light reflection effects, digital noise, lack of contrast and/or colorimetric shift, are removed or compensated.

Abstract: The image processing apparatus comprises: an image correction unit which applies a correction processing to the digital image data; a subject detection unit which detects a human subject from an input image data; a skin color setting unit which sets skin color information based on the detected human subject; a skin color extraction unit which extracts pixels having a skin color similar to a skin color represented by the set skin color information from the digital image data; an area setting unit which sets mask information used to apply correction only to an area to be corrected; and an image output unit which produces output image data based on the inputted digital image data, the corrected image data and the mask information. In a case where the human subject is not detected, skin color information is set using the pre-defined skin color information.

Abstract: An image processing apparatus that detects a face area from image information includes a pattern database, a face-direction determining unit, and a face-area detector. The face-direction determining unit determines, as a face direction, a direction in which a face image in image information is upright based on determination pattern information stored in the pattern database. The face-area detector matches the direction of the image information with the direction of the determination pattern information based on the face direction, and detects a face area from the image information.

Abstract: Image data is acquired, and a comparator circuit or similar structure determines the status of a value of at least one value type of the image data with respect to at least one predetermined range of valid values for the value type. Then, the image data is defined as a function of the status of the image data with respect to the at least one predetermined range of valid values. The image data that falls within the predetermined range(s) of valid values may then be passed for further processing to contribute to a displayed image. Image data that is defined as invalid is typically then removed from the image rendering process to conserve processing and memory resources.

Abstract: An information processing apparatus includes a content storage unit storing a plurality of pieces of content; a background-image storage unit storing a background image corresponding to the plurality of pieces of content stored in the content storage unit; an attribute-information storage unit storing attribute information for each of the plurality of pieces of content in association with the plurality of pieces of content, the attribute information including a corresponding position in the background image; a classification unit classifying the plurality of pieces of content into one or more clusters on the basis of the attribute information; and a rendering unit rendering images indicating the classified pieces of content in a predetermined order on a cluster-by-cluster basis and rendering an area of the background image, the area including the corresponding position included in the attribute information of content corresponding to at least one of the images rendered.

Abstract: A scene classification apparatus includes: a characteristic amount obtaining section that obtains a partial characteristic amount indicating a characteristic of a partial image that is a portion of a classification-target image; a partial classification section that classifies, based on the partial characteristic amount, whether or not the partial image belongs to a predetermined scene; a detection section that detects the number of the partial images classified as belonging to the predetermined scene; and a decision section that decides, according to the number of the partial images detected by the detection section, whether or not the classification-target image belongs to the predetermined scene.

Abstract: A system to display automatically organized images coordinating with pace of background music is disclosed. Users only need to give images and a music clip, and the system will automatically generate a presentation that combines visual and aural effects to display the organized images synchronously accompanying the music. Multiple images that have similar characteristics are well arranged and displayed at the same frame to emphasize the atmosphere of viewing experience. In addition, collaborative presentation of images that is synchronous to music even improves the enjoyment of image browsing.

Abstract: An object image detection device is disclosed that is able to rapidly detect an object image from an input image. The object image detection device includes an image block generation unit to generate plural image blocks from the input image for detecting the object images, an image classification unit to determine whether each of the image blocks includes one or more of the object images by using one or more features of the object images, and acquire the image blocks including the object images to be object image candidates; and a detection unit to sequentially detect the object images from the object image candidates. The image classification unit acquires the object image candidates based on a relative positional relationship between the image blocks and already-acquired object image candidates.

Abstract: A technique for prioritizing portions of compressed multi-resolution medical image data to be processed. More relevant portions of medical image data are compressed at a higher resolution than less relevant portions of medical image data. A mask is created from the image data and used to assign data compression quality factors to corresponding image blocks in the image data. The image data in each region is compressed based on their assigned quality factor. During processing of the compressed image data, the compressed image data and the mask are accessed. The mask is used to direct the processing of the compressed image data. Depending upon the application, the mask can be used to direct that the image data for the regions of most relevance be processed before the image data for the regions of lesser relevance. However, the mask can be used to direct that the image data for the regions of lesser relevance be processed before the image data for the regions of most relevance.

Abstract: A technique for selecting portions of a medical image data set to be stored and portions of the medical image data set to be discarded in order to reduce the overall amount of image data that is stored for each image data set. The selection is based on the clinical purpose for obtaining the medical image data. The clinical purpose for obtaining the medical image is used to select an atlas. The atlas is labeled with information that establishes the relative relevance of various regions of the atlas. The atlas is aligned to the image and the labeling information is transferred from the atlas to the medical image. Each region of the medical image is then processed based on the labeling information received from the atlas. The regions of greatest relevance are stored at their full resolution. Regions of lesser relevance are stored at less than the full resolution. Finally, regions of no relevance are discarded and not stored at all.

Abstract: A technique for selecting portions of a multi-resolution medical image data set to be stored and the portions of the multi-resolution medical image data set to be discarded in order to reduce the overall amount of image data that is stored for each image data set. The selection is based on the clinical purpose for obtaining the medical image data. The clinical purpose for obtaining the medical image is used to select a segmentation algorithm to segment the image data into several regions based on their relevance to the purpose for obtaining the image data. A mask is created from the segmented data. The mask is used to assign data compression quality factors to corresponding regions in the image data. The image data in each region is compressed based on their assigned quality factor. The image data that is highly relevant is compressed with lossless data compression. The image data in regions of lesser relevance are compressed with lossy data compression.

Abstract: An object of the present invention is to be able to output moving image data that enables a desired image group partially included in all intra-subject images to be played as a moving image. An image display apparatus according to the present invention includes an image display function of displaying a series of images obtained by picking up an interior of a digestive canal of a subject at time series, and includes an input unit 11, an image extracting unit 16e, an image file generator 16b, and output processor 16f. The image extracting unit 16e extracts one or more partial image groups, in each of which an image designated by the image designation information input by the input unit 11 is arranged at the center, from the series of images. The image file generator 16b generates a normal moving image including the one or more partial image groups extracted by the image extracting unit 16e, based on the one or more partial image groups.

Abstract: An object is to provide a user with various options on a processing method of an original document including a code image. To accomplish the object, the image processing apparatus includes a decoding section for extracting information by decoding the code image contained in the original document image, and a decision section for making a decision according to selection of the user as to whether to output the original document image or the information extracted by the decoding section.

Abstract: In one aspect, there is provided a video decoder including a first write port to write uncompressed video data to a first buffer in a first format adapted based on an input required by the video decoder and to suppress writing to the first buffer. The video decoder also includes a second write port to write uncompressed video data to a second buffer in a second format adapted to provide the uncompressed video data for subsequent processing external to the video decoder.

Abstract: Provided are a method and apparatus for image encoding which improves encoding efficiency in accordance with image characteristics by performing prediction in lines and performing a one-dimensional transformation in lines on an input image, and a method and apparatus for image decoding. Encoding efficiency of an image may be improved by generating a prediction sub residual block using neighboring residues and performing a one-dimensional discrete cosine transformation (DCT) on a difference residual block which is a difference between an original sub residual block and the prediction sub residual block.

Abstract: A method and apparatus for encoding and decoding an image are provided. The method includes selecting a context model by referring to previously encoded pixels that are adjacent to the current pixel for entropy-encoding a binary value of a pixel value of the current pixel, and entropy-encoding the binary value using the selected context model, thereby performing entropy-coding with high compression efficiency.

Abstract: A motion blurred image restoring method includes following steps. A blur parameter is estimated through a global motion relation between a target image and an image next to the target image, and a restored image is generated through the blur parameter. In order to avoid errors from occurring to the estimated blur parameter, the blue parameter is further adjusted according to the image quality value of the restored image, such that the restored image has a more desirable image quality.

Abstract: The present invention relates to a method and an apparatus for reducing motion blur in a video signal. The apparatus comprises motion estimation means (1) for providing motion information of a video signal, high pass filter means (3a, 3b) for high pass filtering said video signal, and first modulating means (4a, 4b) for modulating the high pass filtered video signal from said high pass filter means (3a, 3b) with motion information from said motion estimation means (1) and for outputting a motion dependent high pass filtered video signal.

Abstract: A computer system for registering synthetic aperture radar (SAR) images includes a database for storing SAR images to be registered, and a processor for registering SAR images from the database. The registering includes selecting first and second SAR images to be registered, individually processing the selected first and second SAR images with an anisotropic diffusion algorithm, and registering the first and second SAR images after the processing. A shock filter is applied to the respective first and second processed SAR images before the registering. Elevation data is extracted based on the registered SAR images.

Abstract: Methods and apparatus for creating a digital image in which exposure varies by region of the image are described. The image may be created from first and second images. In one embodiment, a method comprises writing pixels of the first image that are within a first region of a space to pixel locations in a memory that correspond with coordinates of the respective first image pixels. A replacement pixel is generated by combining a pixel of the first image that is within the first region with a spatially corresponding pixel of a second image. The replacement pixel is written to a pixel location in the memory that corresponds with the coordinates of the replacement pixel. Pixels of the first image that are within a second region of the space may be written to pixel locations in the memory that correspond with the coordinates of the respective first image pixels.

Abstract: The detection of red-eye defects is enhanced in digital images for embedded image acquisition and processing systems. A two-stage redeye filtering system includes a speed optimized filter that performs initial segmentation of candidate redeye regions and optionally applies a speed-optimized set of falsing/verification filters to determine a first set of confirmed redeye regions for correction. Some of the candidate regions which are rejected during the first stage are recorded and re-analyzed during a second stage by an alternative set of analysis-optimized filters to determine a second set of confirmed redeye regions.

Abstract: In an image composer includes a storage for storing a first and a second image, a region classifier compares the first image with the second image to extract as a non-common sub-region a partial region of one of the two images that does not have a similar pixel property to that of the other image. An image composing unit superimposes the extracted non-common sub-region of one of the images onto the other image to produce a resultant composite image.

Abstract: To provide an image matching method, an image matching apparatus, and a program able to perform a matching images at a high accuracy. A Hough transform unit 15 performs a Hough transform processing to a registered image AIM and an image to be matched RIM, in detail, an image processing by which points in each image are transformed to a curved pattern and linear components in each image are transformed to a plurality of the overlapped curved-patterns, based on a distance ? from a reference position to a shortest point in a straight line L passing through a point in the image and an angle ? between a straight line n0 passing though the reference position and the shortest point and a x-axis as a reference axis including the reference position, and generating a transformed image S1621 and a transformed image S1622.

Abstract: Disclosed are systems for and methods of registering (i.e., aligning) a deformable image with a reference image subject to a plurality of regions within the deformable and reference images. Different members of the plurality of regions may be used in different phases of a deformation algorithm and the identity of these regions may change between different iterations of the deformation algorithm. In some embodiments, most of an image is used for calculation of the internal force of the demons algorithm while a smaller subset of the image is used for calculating the opposing external force.

Abstract: When different images are combined, the corresponding parts are to be aligned accurately. To thus combine images, the feature point of each pixel is calculated from each original image using an operator (filter). The pixels are divided into blocks that the resolution matches that of the reduced image of each original image, and an expectation value map for registering the expectation value of the feature point of each block is drawn. Feature points are expected from the expectation values which the expectation value map holds, and reduced images are superposed one on the other. The feature points of the original images corresponding to the feature points between which the correspondence is derived from the reduced images are extracted, and the original images are superposed one on the other using the extracted feature points.

Abstract: The present invention provides an improved method and device for generating a depth map (112) by extracting three-dimensional depth information from the movement vectors of an encoded video bit stream (102) to display two-dimensional video sequences onto three-dimensional displays. In particular, the invention performs depth extraction (110) by means of a post-processing of the movement vectors of the inter-coded macroblocks, which have been already encoded in the video bit stream, thereby significantly reducing the heavy processing requirements associated with conventional motion estimation techniques.

Abstract: An image recognition device for generating an output rotation image from input original image data, including a memory section being capable of storing data of a line including pixels of the original image data to be processed, an angle-to-sine/cosine converting section obtaining an X component and a Y component where a pixel interval of the original image data is an oblique side based on a rotating angle, and a coordinate searching section calculating a reference coordinate of the output rotation image for the original image using the X component and the Y component in order of input of the original image data and outputting data of the output rotation image based upon the reference coordinate.

Abstract: A technique for selecting portions of a multi-resolution medical image data set to be stored and the portions of the multi-resolution medical image data set to be discarded in order to reduce the overall amount of image data that is stored for each image data set. The selection is based on the clinical purpose for obtaining the medical image data. The clinical purpose for obtaining the medical image is used to define regions of interest in the medical image. At each resolution level of the multi-resolution medical image data set, the regions of interest are stored at the full resolution, while the remaining portions of the medical image are stored at a lesser resolution. A three-dimensional bit mask of the regions of interest is produced from a segmentation of the regions of interest. The segmentation list and the multi-resolution medical image data set are decomposed into multiple resolution levels. Each resolution level has a low frequency component and several high frequency components.

Abstract: An image storage apparatus comprises an image capture unit configured to sequentially capture images of a subject, a storage unit including storage areas to store the images of the subject captured by the image capture unit, a storage controller configured to overwrite a storage area which is permitted to be overwritten with an image of the subject captured by the image capture unit, a life setting unit configured to set a life of the storage area which is overwritten by the storage controller, a life controller configured to change gradually the life of the storage area set by the life setting unit, a determination unit configured to determine whether the life of the storage area changed by the life controller expires or not, and a permission unit configured to permit to overwrite a storage area when the determination unit determines that the life of the storage area expires.