Abstract: In an image processing apparatus, a face recognizer is trained using images of one or more faces to generate representation data for the face recognizer characterising the face(s). Face recognition processing is then performed using the representation data. The training and face recognition processing is performed taking into account a person's age.

Abstract: A method for characterizing the risk associated with atherosclerosis is disclosed. The method uses one or more images of cross-sections of the artery or other vessel of interest to identify and locate components of the atherosclerotic deposit, including any hemorrhage, necrotic core, and calcification, and to determine the status and composition of the fibrous cap. In one embodiment, high resolution MRI images are utilized, although other imaging modalities may alternatively be used. A simple scoring system is applied that accounts for the presence of these components and more heavily weights the presence of these components in the juxtaluminal portion of the deposit. The status of the fibrous cap (intact or ruptured) and the composition of the fibrous cap (collagen or mixed tissue) are also incorporated into a final atherosclerosis risk score.

Abstract: In a telemanipulation system for manipulating objects located in a workspace at a remote worksite by an operator from an operator's station, such as in a remote surgical system, the remote worksite having a manipulator with an end effector for manipulating an object at the workspace, such as a body cavity, a controller including a hand control at the control operator's station for remote control of the manipulator, an image capture device, such as a camera, and image output device for reproducing a viewable real-time image, the improvement wherein a position sensor associated with the image capture device senses position relative to the end effector and a processor transforms the viewable real-time image into a perspective image with correlated manipulation of the end effector by the hand controller such that the operator can manipulate the end effector and the manipulator as if viewing the workspace in true presence.

Abstract: A robot having an imaging capability includes: an imaging device, and at least one actuator separate from the imaging device for moving at least a portion of the robot. The at least one actuator is controllable in response to a control command, the imaging device being responsive to the control command to modify characteristics of image data produced.

Abstract: A video segmentation method for segmenting video clips according to content of the video clips is disclosed. The method comprises scanning pixels of video frames with a first horizontal scan line to determine if colors of the pixels fall within a predetermined color range; creating a color map utilizing pixels located on the first horizontal scan line from a plurality of successive video frames; labeling the current video segment as a candidate video segment if the color map indicates the presence of a stable region of pixels falling within the predetermined color range for a predetermined number of successive video frames; and performing histogram color comparisons on the stable regions for detecting shot transitions. Audio signals of the video clips may also be analyzed to further verify the candidate video segments.

Abstract: An apparatus for detecting the presence of one or more images of a known kind in a scene is disclosed which comprises a digital input means and an optical output means. The digital input means comprises a capture means which passes a capture image to a first electronic processing means to produce a scene pattern corresponding to a Fourier Transform of the scene image. This pattern is then digitally combined with one or more reference patterns corresponding to Fourier Transforms of a reference image. The resulting combined patterns are then used to modulate a beam of light which may be focused to perform an inverse Fourier Transform providing correlation information. In a preferred embodiment, the combined pattern is displayed on a spatial light modulator.

Abstract: A three-dimensional image photographing apparatus acquires an image that includes shape information and texture information of an object, and acquires a three-dimensional image of the object by utilizing the image that includes the shape information and the texture information. A three-dimensional measuring device measures the three-dimensional shape of the object. An illumination device is disposed fixed at a predetermined position relative to the object and comprises an illumination light source and an optical system to illuminate the object. A texture image photographing device photographs a texture image of the object illuminated by the illumination device from a plurality of viewpoints.

Abstract: The invention provides a device to inspect an illumination optical device and a method to inspect an illumination optical device that make it possible to efficiently inspect illumination optical devices and to control manufacturing cost. A lens array inspecting device is provided with a light source device to emit a parallel luminous flux, lens array holders to retain lens arrays, which are test objects that split the parallel luminous flux into a plurality of partial luminous fluxes, and a ground glass on which the optical images of the luminous fluxes emitted through the lens arrays are projected. On the ground glass, a parting frame appropriate to a design illumination region is formed. Therefore, whether the lens arrays are defective or non-defective can be determined by checking whether the optical images projected onto the ground glass include the area of the parting frame.

Abstract: A method for suppressing ghost image artifacts in x-ray images is provided. In chronological order, a plurality of x-ray images of one or more objects is generated with the interposition of at least one solid-state detector for generating a visible image by incident x-radiation. From each currently generated x-ray image, a previously ascertained correction image is electronically subtracted. The last correction image ascertained is generated by a blank image, and before its use, it is examined for the presence of residual-image effects. If a predetermined limit value of a proportion of residual-image effects (proportion of residual images) is exceeded, the last correction image is discarded at least partially, and an earlier correction image ascertained by a blank image with a lesser proportion of residual images is used at least partially for correcting the current x-ray image.

Abstract: Table-like structures in documents are located by analysis of sub-regions (crops) on the document. The analysis involves determining the location of lines having lengths above a certain threshold and assigning these lines to groups. A set of adjacent lines is assigned to a common group if the separation between adjacent pairs of lines within the set is less than a threshold value. The crop selected as the location of the table-like structure is that having a group with the greatest number of lines. When the technique is applied to locating title blocks in technical drawings, it is preferred to analyze crops corresponding to the corners or ends of the document. The analysis is also applicable to an image of the document produced at a reduced resolution.

Abstract: A reference minutiae template comprising reference minutiae and a first partial minutiae template, which overlaps the reference minutiae template, the first partial minutiae template comprising first minutiae, are selected. The reference minutiae of the reference minutiae template are matched with the first minutiae of the first partial minutiae template. Using the matched minutiae, a transformation function is determined, which describes the relation between the reference minutiae and the first minutiae. The first minutiae, which are located outside the overlapping region, are transformed using the transformation function, thereby generating a new reference template. Furthermore, a second partial minutiae template is selected, which overlaps the new reference minutiae template, the second partial minutiae template comprising second minutiae.

Abstract: An object of the present invention is to provide an image retrieval system for computing similarity in the case when components are different between an image feature vector of a query image and the image feature vectors of images to be retrieved when retrieval is carried out by using features of images. A first image feature vector conversion device converts a query image feature vector into a first image feature vector for use in a similarity computation according to similarity computation image feature vector configuration information describing a given configuration of an image feature vector for use in a similarity computation. A second image feature vector conversion device converts an images-to-be-retrieved feature vector into a second image feature vector for use in a similarity computation according to the similarity computation image feature vector configuration information.

Abstract: The invention relates to the reading of addresses on mailings whereby the images with the addresses are videocoded in several video-coding sites by means of a job distribution device. At fixed intervals a current individual error rate, for first-pass video coding for each video-coded addresses which are not successful on the first pass in the video coding units with the highest current individual error rates, is determined with respect to the total coding error rate to be maintained, by means of the video coding units coming free which have the lowest current individual error rates.

Abstract: The invention relates to a method in which object functions are generated from projections of an object by means of an iterative reconstruction algorithm with determination of approximation images. This method is used in, for instance, image-generating systems for producing images of object functions. Image-generating systems of this kind are generally used when images of an object are to be generated without cutting or destroying the object itself in the process. In the process, projections of the object are acquired from different projection directions from a maximum angular range. In an iteration cycle, an approximation image of the object function and a projection are used to calculate, using the reconstruction algorithm, a new approximation image which produces a further new approximation image in the subsequent iteration cycle in conjunction with a projection from a different projection direction.

Abstract: Pattern recognition apparatus and method for recognizing a recognition object by comparing with pre-registered models. From an inputted image, multiple feature points are extracted; therefrom, combination of multiple feature points is selected; and from the multiple selected feature points, bases which represent the positions and positional relations of these feature points are calculated. A partial pattern of the recognition object corresponding to each of the calculated bases is extracted from the image; and a search place on the table is decided based on an invariant parameter to geometric transformation of the partial pattern. The similarity between the partial pattern of the model registered in the search place on the table and the partial pattern of the recognition object is judged; and a plurality of hypothesis information showing that the recognition object exists in the image is generated based on the similarity between both partial patterns.

Abstract: An eye image pickup apparatus includes an image pickup unit, a guide mirror, a range sensor, and an infrared illuminating section. The image pickup unit includes an objective lens, an image pickup element such as a CCD, a shooting section and a light guide section as a basic configuration, and the image pickup unit shoots an image of an eye of a person. The guide mirror guides a subject to a shooting position. The range sensor measures the distance between the image pickup apparatus and the subject. The infrared illuminating section illuminates the subject. Rough guidance of the user is made using the guide mirror and fine alignment is made by using a guiding visible light obtained from the light guide section.

Abstract: The invention provides a method for image resolution enhancement, which utilizes a fuzzy analysis system simulating the human vision system and uses the neural network as a basis for digital image interpolation. After an original image is inputted in, the image analysis module will divide and classify the original image, and then each of the image being classified will be processed by either the bilinear interpolation or the neural network interpolation. Because the fuzzy analysis system is configured according to the human vision system, and because the neural network is a model obtained from learning real natural images, the vision effect of the image enlarged through the processing method of the invention is very close to the real natural image.

Abstract: A method and computer program product are disclosed for use in classifying an input pattern into one of a plurality of output classes. A plurality of modular classifiers each represent a set of at least one associated output class. The modular classifiers are capable of being trained separately from the system. The classifiers select one of the associated output classes as a classification result and compute an associated confidence value. This confidence value possesses common significance across the plurality of modular classifiers. A processing stage processes the confidence values from the plurality of modular classifiers. As a result of this processing, the processing stage selects an associated classification result.

Abstract: A highly accurate identification system is built by using an identification module, which has predetermined values of FAR and FRR. A plurality of (m) biometrics are registered and managed. At the time of identification, a collation process is executed by using the m biometrics, and also a collation process is executed a plurality of (n) times with each biometrics. An identification result of the system is judged and outputted by combining the results of the m-biometrics collation and n-time collation trials. As conditions of judgment, when the collation is judged to be successful even once in the n-time collation trial, the collation is judged to be successful with respect to that biometrics. In the in-biometrics collation trial, when the collation is judged to be successful with respect to all the m biometrics, a judgment of identification success is given in the system as a whole.

Abstract: A method and apparatus for image processing to detect changes in a scene includes compressing by computing a wavelet transform of an image corresponding to the scene, thresholding coefficients associated with the transform, and comparing a subset of coefficients with values to detect and indicate a change in the image. Values such as averages and a standard deviation therefrom can be generated during training by processing N training images. Determining whether a change has occurred includes determining the value of image sets, standard deviation and training sets, and comparing these, based on the type of change to be ascertained, to statistical information.