Abstract: A method of training a system to identify inspection sites on a circuit board is described. The method uses a priori information, which includes a region of interest, approximate sizes and approximate spacings of a plurality of nominal pad locations, and a pad count or an aperture count. A region is created which is associated with each one of the nominal pad locations within an image of a printed circuit board. A search tool is run to find pad candidates within each one of the regions. The pad candidates are filtered. The best pad candidates are selected from among each of the found pad candidates. The best pad candidates are averaged to provide an average, and are modified based on the average.

Abstract: The present invention relates to a method for three-dimensional image reconstruction of basal ganglion. A novel geometrical algorithm has been developed to calculate the correction coordinates of the target based on the reference axial shift in the CT scan coordinate system. Furthermore, wavelet transform along with interpolation techniques are used to obtain continuous sectional images and three-dimensional image reconstruction is then performed to form the stereotactic atlas of basal ganglion. Therefore, the stereotactic atlas of basal ganglion established in this invention can be used as references for assisting operation and training for neurosurgeons.

Abstract: A method involves training a system to identify inspection sites on a printed circuit board. The method uses a priori information, which includes a sample pad description. A training region of interest is created within an image of the printed circuit board. A search tool is run to find pad candidates within the training region. The pad candidates are filtered and false pad candidates are eliminated. The filtered pad candidates are averaged to provide an average, and are modified based on the average.

Abstract: A hierarchical-segmenting pre-processor hierarchically segments the axis of each coordinate of a characteristic value used for classifying a pattern to decide a threshold value for each dimension, and generates hierarchized learning patterns which indicate a segment of the segmented coordinate axis to which each coordinate of the characteristic value of the learning pattern belongs. A developing variable determining unit selects a dimension (variable) having the highest classification efficiency in each node of a classification tree. A classification tree generator generates a classification tree based on the dimension (variable) obtained by the developing variable determining unit and a threshold value set in the dimension.

Abstract: The color correcting method and the image reading apparatus estimate a spectral sensitivity characteristic of an image reading apparatus using a measured value obtained by measuring a reference original with a preset measuring instrument or a characteristic value of the reference original and a statistic calculated by analyzing an image signal value obtained by reading the reference original with the image reading apparatus, create an input color correction parameter from the estimated spectral sensitivity characteristic and correct an image signal of an original image read with the image reading apparatus using the input color correction parameter. As a result, according to the method and the apparatus, when the original image is photoelectrically read, the dispersion of the spectral sensitivities of scanners (image reading apparatus) can be preferably corrected, whereby images of high quality in which appropriate colors are reproduced can be stably reproduced in a digital photoprinter and the like.

Abstract: An image processing apparatus includes a converter, a calculator and a reverse converter. The converter performs a frequency conversion operation on a color image signal which includes a brightness signal and color signals and divides values of each of the brightness signal and the color signals into high frequency coefficients and a low frequency coefficient. The calculator calculates the high frequency coefficients of the brightness signal and the color signals, generates a set of different high frequency coefficients, and produces a new brightness signal by adding the low frequency coefficient of the brightness signal to the set of different high frequency coefficients. The reverse converter performs a reverse frequency conversion operation on the new brightness signal.

Abstract: A means 9 for extracting the characteristic of the multi-value image causes an extracting filter to perform spiral retrieval so as to extract a nostril region from an image of the face input by a CCD camera 2 so as to cause the nostril region to be stored in the binarized image memory 10. The eye retrieving range is specified by using, as a reference, the position of the nostrils which is an intermediate point of the positions of the centers of gravity of the nostrils in the binarized nostril region stored in the binarized image memory 10. Then, an extracting filter is used to extract an eye region from the image of the face so as to store the eye region in the binarized image memory 10. The opening/closing determining means 11 determines opening/closing of the eyes in accordance with the binarized eye region.

Abstract: A system for image object tracking and segmentation, includes (i) a modified adaptive resonance theory-2 (M-ART2) model for detecting changes of scenes, (ii) a two-dimensional correlative autopredicitve search (2D CAPS) method for object tracking, (iii) a derivation of contour energy for use in modelling an object edge, and (iv) an active contour model with global relaxation for defining optimal image object boundaries. The modelled object boundary is derived from an edge potential energy calculation and a set of current edge points. For each edge point, several candidate data points are also selected. Rather than calculate an energy value for each potential contours, a solution is achieved by comparing energy differences along a travel path. The selected contour is built in steps. An optimal path is selected from the potential paths.

Abstract: A system for monitoring and reporting incidences of traffic violations at a traffic location is disclosed. The system comprises a digital camera system deployed at a traffic location. The camera system is remotely coupled to a data processing system. The data processing system comprises an image processor for compiling vehicle and scene images produced by the digital camera system, a verification process for verifying the validity of the vehicle images, an image processing system for identifying driver information from the vehicle images, and a notification process for transmitting potential violation information to one or more law enforcement agencies.

Abstract: A method and apparatus for inspecting the placement of a device-under-inspection (DUI), for example a surface-mount component, on a circuit board includes scanning the circuit board to acquire stored images of the circuit board. From the stored images, a pad-bounding rectangle is constructed that circumscribes the outer edges of the pads for the DUI. An error-bounding rectangle is then constructed from the pad-bounding rectangle. The error-bounding rectangle has a length equal to the length of the pad-bounding rectangle plus a lengthwise error deemed allowable for placing the pins of the DUI over its pads. Similarly, the error-bounding rectangle has a width equal to the width of the pad-bounding rectangle plus an allowable widthwise error. A pin-bounding rectangle is constructed that circumscribes the outer edges of the pins of the DUI. The invention then determines whether the DUI is properly placed by examining whether any portion of the pin-bounding rectangle lies outside of the error-bounding rectangle.

Abstract: A system is disclosed for identifying matching arcs in sets of geometric objects, such as a pair of electronic maps, without relying on attributes being assigned to the arcs. An arc in a first set of geometric objects is identified as matching an arc in a second set of geometric objects, when the arc in the first set is co-bounded on both sides by polygons which match the corresponding co-bounding polygons of the arc in the second set. A determination is made of which polygons in the first set of geometric objects match polygons in the second set of geometric objects, by computing and comparing a set of similarity metrics. Examples of characteristics for which similarity metrics are determined include, proximity, area, shape and rotation. Each similarity metric is determined in an isolated fashion, so that no other metric is reflected in the metric being measured.

Abstract: A vector block information indicating a plurality of line segment rows is read out from a block map. Each line segment row divides an area of a block from an area of a road in an image drawing region. Each point at which one end of a line segment row contacts with a boundary line of the image drawing region is set as a boundary point. In this case, a road crossing the boundary line of the image drawing region is indicated by a pair of line segment rows having a pair of boundary points close to each other. To determine an area of the road, the pair of boundary points are connected with each other through a connecting line segment. Therefore, a road area in the image drawing region can be automatically extracted from the block map.

Abstract: This invention is directed toward an object recognition system and process that identifies the location of a modeled object in a search image. This involves first capturing model images of the object whose location is to be identified in the search image. A co-occurrence histogram (CH) is then computed for each model images. A model image CH is computed by generating counts of every pair of pixels whose pixels exhibit colors that fall within the same combination of a series of pixel color ranges and which are separated by a distance falling within the same one of a series of distance ranges. Next, a series of search windows, of a prescribed size, are generated from overlapping portions of the search image. A CH is also computed for each of these search windows using the pixel color and distance ranges established for the model image CHs. A comparison between each model image CH and each search window CH is conducted to assess their similarity.

Abstract: When an image capturing apparatus connected to a LAN, which is connectable a plurality of terminals, transmits image data obtained by reading an image on an original to a desired terminal on the LAN, the read image is confirmed by, e.g., previewing the image using a display device placed in the vicinity of the image capturing apparatus, and is then transmitted to an actual destination. With this control, an image of a desired format can be easily transmitted even from an image capturing apparatus having no satisfactory image display function to a desired destination.

Abstract: The present invention is an image processing apparatus comprising: dividing means for dividing an image signal obtained by scanning an original document into predetermined local blocks and output a predetermined including a target pixel; a binary coding processing section which converts the image signal in the predetermined block into binary code information; means for calculating each area (dimension) of the binary values; means for calculating number of times that the binary values are changed; a threshold processing section for performing threshold processing by properly and selectively using a threshold of the maximum density difference in the predetermined area, each area (dimension) value after binary coding and number of counts as a parameter; and a judgement processing section for judging the image signal in the predetermined area.

Abstract: An information recording medium (30) has a recorded system control file (SCF) (96) representing processing parameters necessary for reproduction processing for reading out a print-recorded code pattern and reproducing original multimedia information. With an SCF readout switch (88) operated, an initially determined SCF read-out parameter is input from a parameter memory (92) to a controller (66). The controller (66) controls each part in accordance with the input parameter and outputs read-out image data as a 1-SDU1 to an overlying layer and a state signal, that is, a signal showing that the SCF is being read out, as a 1-SDU2 to the overlying layer. The overlying layer decodes the contents of the SCF (96) and a parameter setting signal is input as the 1-SDU3 from the overlying layer and it is stored in the layer 1 parameter memory (92). At a time of reading out an actual dot code (10) corresponding to the operation of a scanning start switch (86) the parameter memory (92) utilizes its stored contents.

Abstract: A generic spatially scalable shape encoding apparatus and method for deriving shape information for chrominance components from luminance component. The present generic spatially-scalable shape encoding applies a series of subband (e.g., wavelet) filters to obtain N-levels of wavelet decomposition for the texture information of both luminance and chrominance components. The application of the corresponding subsampling filters of said subband filters is applied in a manner such that the shape of the chrominance can be derived from the shape of the luminance at the same spatial layer.

Abstract: A method and apparatus is provided for inspecting a semiconductor wafer for field-to-field critical dimension (CD) variations using statistical techniques, such that an optimal number of fields on the wafer under inspection are measured, thereby increasing the accuracy of the results of the inspection procedure and avoiding unnecessary sampling. Embodiments include randomly selecting a predetermined number of fields on a semiconductor wafer to be inspected, and measuring the CD of a comparable feature in each of the sample fields, as by a critical dimension scanning electron microscope (CD-SEM). A statistical function, such as an average or standard deviation, of the measured CDs is calculated. Further fields are the randomly selected, CDs measured, and the running average or standard deviation calculated after each CD is measured. If the last acquired CD does not change the average or standard deviation by a predetermined amount, the inspection procedure for the wafer under inspection is terminated.

Abstract: A data hiding system and method for providing a method of embedding multiple layers of hidden data into multimedia data. First, a media unit of the multimedia data is evaluated to determine an appropriate embedding procedure. Next during a first embedding pass, a ruling layer of primary hidden data is embedded into the media unit. In another embedding pass, a governing layer of secondary hidden data is embedded on top of the ruling layer. The secondary hidden data provides control information for controlling the primary hidden data and the host data. Control information such as error correction data, synchronization data, decoding data, and authentication data is embedded in the governing layer. Embedding schemes such as base domain and spectrum domain embedding are employed.

Abstract: A method and apparatus for single channel color image segmentation using local context based adaptive weighting is provided. The varying weightings of the projection vector are determined as a function of local input image activity context. A Sobel operator is used to calculate the input image activity. A binary map is created for each color channel and is adapted to store binary markers indicative of local activity levels on a per pixel basis. The binary maps are low pass filtered and then normalized to generate a context based adaptive weighting vector for use in single color segmentation of a multi-channel color image signal.