Abstract: The present invention is embodied in a system and method for detecting a face within an image using a relational template over a geometric distribution of a non-intensity image property. In general, the system of the present invention includes a hypothesis module for defining a sub-region in which to search for a face, a feature extraction module for extracting image feature values image based on a non-intensity image property, an averaging module for grouping the extracted image feature values into geometrically distributed facial regions, and a relational template module that uses a relational template and facial regions to determine whether a face has been detected. In a preferred embodiment the image property used is edge density, although other suitable properties (such as pixel color) may also be used.

Abstract: A method and an apparatus for inspecting microbes, etc. including, as an apparatus for detecting microbes, etc., a cultivating device, an image taking-in device, and an arithmetic processing unit, in which an image of a medium to be inspected obtained from a sample collected from a substance or a physical solid having proper color microbes or the medium subjected to illumination treatment, dyeing treatment, etc. prior to or after cultivation in accordance with necessity is separated into the three primary colors, or the like, then, chromatic information of histogram, color and hue for each primary color are calculated, and the information thus obtained is compared with integrated data obtained by combining second data of generic information of microbes, etc. with first data of microbes, etc.

Abstract: A data processing apparatus includes a connection unit for connecting a plurality of terminals, a storage unit for storing respective processing abilities of the plurality of terminals, a reception unit for receiving data via a line, a converting unit for converting the data received by the reception unit in accordance with the processing abilities stored in the storage unit, and a transfer unit for transferring the data converted by the converting unit to one of the plurality of terminals via the connection unit. A method of controlling a data processing apparatus capable of connecting a plurality of terminals, includes the steps of storing respective processing abilities of the plurality of terminals, receiving data via a line, converting the received data in accordance with the stored processing abilities, and transferring the converted data to one of the plurality of terminals.

Abstract: A method for examining the surface of an unwinding strip to detect a surface fault. The method includes forming at least a digital image of the strip having a set of image elements each with an assigned digital value. The digital image is filtered to detect surface defects. The filter digital image is processed to identify the type of surface fault in the strip. Before the digital image processing step, the digital image is segmented into doubtful zones each containing a surface defect with the image processing step being carried out on the doubtful zones.

Abstract: An image registration system and method employs a registration processor (130) to find an optimal registration of two volumetric images (110, 112) by finding a spatial orientation that optimizes the statistical measure cross-entropy. The cross-entropy can be minimized where one or more likely or reasonably good a priori estimations of the true joint probability density function (pdf) of voxel value pairs are available. Where such an estimate is not available, the joint pdf for one or more known incorrect spatial arrangements (e.g., based on prior misregistrations), can be used as the prior pdf estimate(s). Since the prior pdf estimate(s) are unlikely to be the true pdf, a spatial orientation maximizing the cross-entropy is found. Likely and unlikely prior pdf estimations can also be used together to register images.

Abstract: In accordance with a specific embodiment of the present invention, an image is projected upon a surface. The image can include a pattern having a plurality of individual shapes used to measure and map the surface. The plurality of individual shapes include features that are detectable in a direction parallel to the plane formed by a projection axis of the projected shapes and a point associated with a view axis. The image further comprises a feature containing an encoding information for identifying the plurality of shapes individually. The feature containing encoding information can be a separate feature from each of the plurality of individual shapes, or may be a feature integral to the plurality of individual shapes. The feature containing encoding information is oriented such that the encoding information is retrieved along a line perpendicular to a plane formed by the projection axis and the point along the view axis. The use of the feature is used to perform multiframe reference independent scanning.

Abstract: A photograph album system dynamically rearranges a template for a photograph album based on images supplied by a user. The photograph album system also allows the user to edit an existing album template and can create a new template from a completed photograph album. When the photograph album system is an online web site, the system may require compensation for the user's activity on the web site.

Abstract: A photogrammetric image processing apparatus and method defining a plurality of pairs of images including a common target as belonging to the same groups (pairs), providing an image display area and drawing area on the screen of the display device, displaying images of a pair 1 on the image display area, calculating a valid mapping range for the pair 1, displaying an area marker showing the valid mapping range on the survey map superimposed in the drawing area, designating corresponding image points on the image of the pair 1 to calculate the three-dimensional coordinates of physical points, and generating a survey map based on the three-dimensional coordinates.

Abstract: A method and apparatus for determining defects in a circuit pattern. An image including a circuit pattern is acquired. An outline of the circuit pattern is extracted and a contour image is generated. A shape of a contour in the contour image is evaluated to determine whether a defect exists.

Abstract: A system for activating a microphone based on visual speech cues, in accordance with the invention, includes a feature tracker coupled to an image acquisition device. The feature tracker tracks features in an image of a user. A region of interest extractor is coupled to the feature tracker. The region of interest extractor extracts a region of interest from the image of the user. A visual speech activity detector is coupled to the region of interest extractor and measures changes in the region of interest to determine if a visual speech cue has been generated by the user. A microphone is turned on by the visual speech activity detector when a visual speech cue has been determined by the visual speech activity detector. Methods for activating a microphone based on visual speech cues are also included.

Abstract: In accordance with a specific embodiment of the present invention, an image is projected upon a surface. The image can include a pattern having a plurality of individual shapes used to measure and map the surface. The plurality of individual shapes include features that are detectable in a direction parallel to the plane formed by a projection axis of the projected shapes and a point associated with a view axis. The image further comprises a feature containing an encoding information for identifying the plurality of shapes individually. The feature containing encoding information can be a separate feature from each of the plurality of individual shapes, or may be a feature integral to the plurality of individual shapes. The feature containing encoding information is oriented such that the encoding information is retrieved along a line perpendicular to a plane formed by the projection axis and the point along the view axis. The use of the feature is used to perform multiframe reference independent scanning.

Abstract: A hand-held fingerprint scanner having local storage of image normalization data is disclosed, as well as a method of manufacturing such a scanner. The image normalization data is representative of fixed pattern noise associated with the image sensor used in the fingerprint scanner. This data may be combined with the raw image data resulting in normalized image data. The image normalization data is stored in non-volatile memory where it can be transmitted to a host processor. Alternatively, the fingerprint scanner may include a normalization processor, allowing transmission of normalized fingerprint images to a host processor. Also disclosed is a fingerprint scanning system having remote fingerprint scanners with local storage of image normalization data.

Abstract: A method and apparatus for tissue dependent filtering for digital image magnification includes using bilinear interpolation and digital convolution filters to approximate bicubic interpolation for digital image magnification. A library of set s of representative images may be created for particular anatomies and particular imaging modalities. Two-dimensional convolution filter coefficients may be estimated using a set of representative images chosen for a particular anatomy. The two-dimensional convolution filter coefficients may be employed to form a two-dimensional convolution filter to be used with bilinear interpolation to magnify a digital image.

Abstract: A multi-resolution label locator system divides an input image into a plurality of multi-pixel cells. The multi-resolution label locator system then creates a decimated image or low resolution image corresponding to the input image. The decimated image includes a common-characteristic value that corresponds to a multi-pixel cell of the input image. The multi-resolution label locator system identifies one or more areas within the decimated image that have characteristics corresponding to the characteristics of interest. While generating the decimated image, the multi-resolution label locator system simultaneously creates an edge-occurrence image that corresponds to the input image. The edge-occurrence image includes an edge value that corresponds to each cell of the input image. Each edge value represents the number of occurrences of an edge within the pixels of a corresponding cell of the input image.

Abstract: A method for analyzing structure of a treatise type of document image in order to detect a title, an author and an abstract region and recognize the content in each of the regions is provided. In order to analyze the structure of a treatise type of document, first, the document image divided into a number of regions and the divided regions are classified into text regions and non-text regions according to attributes of the regions. And then, the candidate regions representing an abstract and an introduction is selected, thereafter word regions are extracted from the candidate regions, and an abstract content portion is determined. Thereafter, the title and the author are separated by using the basic form and the type definition representing an arrangement of each of journals. Finally, the content of the separated regions is recognized to generate said table of contents.

Abstract: The disclosure describes a method of progressively decoding a digital watermark on a distributed computing platform. A client device equipped with a digital camera, such as a PDA or cell phone, captures a digital image of a watermarked object, and pre-filters the image to isolate a portion of the image data suspected of containing a digital watermark. The pre-filter de-correlates a portion of the image data suspected of containing a digital watermark from the remaining host image signal using a predictive filter. The client then quantizes the filtered data and progressively transmits the quantized data to a watermark decoder. The progressive transmitter sends image data as necessary to achieve a valid decoding operation. To reduce bandwidth requirements, the transmitter starts with the most highly quantized version of the filtered image, and sends lesser quantized versions until the watermark decoder completes a successful decoding operation.

Abstract: A surface shape recognition apparatus includes a plurality of sensor electrodes, passivation film, capacitance detection circuit, and ground electrode. The sensor electrodes are formed on an interlevel insulator on a substrate and insulated from each other. The passivation film is formed on the interlevel insulator to cover the upper and side surfaces of each sensor electrode. The passivation film is formed from a dielectric material. When a target recognition object comes into contact with the surface of the passivation film, the capacitance detection circuit detects an electrostatic capacitance formed between the sensor electrode and the surface of the target recognition object opposing the sensor electrode. The ground electrode passes static electricity on the surface of the passivation film.

Abstract: A computer-implemented method and system for adjustment and matching of stereoscopic images (206, 208) of the eye fundus (106). Illumination errors between the images are eliminated, such as by adjusting groups of pixels so that the mean and variance of a group (306) from the left image (206) will have the same mean intensity and variance as the corresponding group (308) from the right image (208). An epipolar line adjustment is performed, such as by shifting points in the images based on matched points in the images. Image occlusion errors are detected and removed, such as by matching point analysis. Once these adjustment steps have been completed, a matching analysis can be preformed using the corrected images.

Abstract: A watermark information embedding method, and apparatus, capable of suppressing the quality degradation of contents and increasing the survivability of embedded information. When embedding watermark information in moving picture data formed of a plurality of still picture frames arranged in time series, a motion vector representing a property specific to moving picture is detected for each of image blocks generated by dividing a target frame. According to a motion quantity, a pixel change factor specifying rule is selected for each block. Out of pixels permitted to be changed in luminance depending upon the state of an image in each block representing a property specific to still picture, as many pixels as a number specified by the selected rule are selected. Luminance change processing for forming watermark information is conducted on the selected pixels.

Abstract: The present invention provides a vehicle driving information storage apparatus capable of preserving condition changes of inside and outside of a vehicle and a driver as synchronized images. Inside a vehicle 1, a fisheye lens 5 is arrange at a position capable of simultaneously filming a driver's state and a state inside and outside the vehicle and filming is performed at a predetermined cycle and a predetermined number jmax of the latest images are always stored in the image storage unit M1. Upon detection of a driving condition sudden change such as a sudden brake and a collision, image update is performed the operations times of jmax−x1 (0<x1<jmax) and the image update is stopped so that x1 images before sudden change and jmax−x1 images after the sudden change are preserved in the image storage unit M1.