Showing papers on "Standard test image published in 1996"

Method and apparatus for generating a composite image using the difference of two images

Abstract: An electronic imaging system useful for compositing images includes an electronic camera for capturing multiple images, including a first image of a subject plus background and a second image of the background only. The first and second images are subtracted to generate a difference image, and the difference image is processed to generate a mask image. The mask image is then applied to the first image to select an area in which the subject is located, whereby the selected subject area is used in the compositing of a new image.

Quantitative measures of change based on feature organization: eigenvalues and eigenvectors

Abstract: We propose four measures of image organizational change which can be used to monitor construction activity The measures are based on the thesis that the progress of construction will see a change in the individual image feature attributes as well as an evolution in the relationships among these features This change in the relationship is captured by the eigenvalues and eigenvectors of the relation graph embodying the organization among the image features We demonstrate the ability of the measures to differentiate between no development, the onset of construction, and full development, on the available real test image set

Method of combining two digital images

Abstract: A method of combining at least one customer generated digital image to form a merged image and/or text with at least one prestored digital image. The prestored digital image has a predetermined location where the customer generated digital image may be placed. A design characteristic is determined from an item to be associated with the merged image. The customer generated digital image or the prestored digital image is modified in accordance with the design characteristic so as to form a first modified digital image that is then combined with the other of the customer generated digital image or the prestored digital image so as to form a newly merged digital image. The newly merged digital image is the merged image sent to an output device for printing. Alternatively, a product to be used with or associated with the merged image is automatically selected in accordance with predetermined color relationship with respect to the color of the customer generated image, the prestored digital image and/or merged digital image.

Method and apparatus for merging real and synthetic images

Abstract: A method for merging real and synthetic images in real time is comprised of the steps of providing a first signal containing depth and image information per pixel about a real image. A second signal containing depth and image information per pixel about a synthetic image is provided. The depth information corresponding to the real image and the depth information corresponding to the synthetic image for each pixel are compared. Based on the comparison, either the image information corresponding to the real image or the image information corresponding to the synthetic image is selected and combined. Because the image information is compared based on depth, any interaction such as occluding, shadowing, reflecting, or colliding can be determined and an appropriate output generated

Robust search for image features across image sequences exhibiting non-uniform changes in brightness

Abstract: An apparatus and method for two-dimensional search for a model image within atest image that exploits edge-based matching of edge maps, followed by area-based matching of at least coarse resolution edge maps of respective multi-resolution edge-maps, to efficiently and accurately provide the position of at least one instance of the model image. The invention can find a location of the model image within each test image of a sequence of test images, even when there are non-uniform brightness changes in the test image due to process steps or lighting changes. The postion of each verified instance of the model image within the test image can be provided to an alignment device, a measurement device, or any other device that can use such position information.

Image processing apparatus for discriminating image characteristics using image signal information obtained in an image scanning operation

Abstract: An image processing apparatus generates color image signals representing an image of a scanned original document. A series of image discriminating units are provided. An edge discrimination unit discriminates edge regions with respect to each pixel. Further discrimination units discriminate other image regions, such as half tone regions, white background regions, photograph regions, or color regions, with respect to each pixel block. Discriminating results are stored in a memory to be used for subsequent image scans.

Digital storage of echocardiograms offers superior image quality to analog storage, even with 20:1 digital compression: Results of the digital echo record access study

Abstract: A large interobserver and intraobserver variability study was performed comparing both digitally compressed and uncompressed echocardiographic images with the same images recorded onto super-VHS video-cassette tape (the current standard). In a blinded, randomized fashion, 179 observers scored the diagnostic and image quality of 20 pairs of echocardiographic loops representing various pathologic conditions. Overall, the digital images were preferred to the S-VHS images both for image quality and diagnostic content (p < 0.0001) regardless of the background or experience level of the observer. Furthermore, uncompressed digital images and those compressed by the Joint Photographic Experts Group (JPEG) algorithm at ratios of 20:1 were judged equivalent. These findings show that digital compression may be used routinely in echocardiography, resulting in improved image and diagnostic quality over present standards.

System for testing and evaluating driver situational awareness

Abstract: A system for testing and evaluating driver situational awareness incorporates a device for displaying road and traffic images to a subject being tested, road and traffic image data for simulating operation of a vehicle to be outputted on the display device, instruction data to be outputted at least on the display device, input devices for inputting response data from the test subject in response to road and traffic image data generated on the display means, and a control device for controlling the operation of the system The control device incorporates a vision test component for conducting a vision test of the subject and a driving reaction test component for conducting a driving reaction test of the subject Each of the vision and driving reaction tests includes generating road and traffic image data for simulating operation of a vehicle, generating instruction data in coordination with the image data for providing instructions for the subject, monitoring for inputting of response data, and determining whether the inputted response data is correct or incorrect The generated image data includes road and traffic video image data, test pattern image data and situation test image data The test pattern image data is structured to test static visual acuity, static visual contrast sensitivity, dynamic visual acuity, dynamic visual contrast sensitivity and angular motion sensitivity The situation test image data is structured to test divided attention capacity, selective attention capacity, attention switching, working memory functions, brake reaction time, and complex reaction time and decision making

Price determination system and method using digitized gray-scale image recognition and price-lookup files

Abstract: An item recognition system and method which is particularly suited for automating entry of items too small to carry readable bar code labels. The system includes a camera which digitizes the image to produce a digitized image and a gray-scale digitized image. A binary image of the gray-scale image is then produced from which the computer records an image of the item, and a computer coupled to the camera which digitizes the image to produce a digitized image and a gray-scale digitized image. A binary image of the gray-scale image is then produced from which the computer identifies the item from the binary image and obtains the price from a price-lookup file.

Zone segmentation for image display

Abstract: The present invention provides a method and apparatus for detecting in an image text-like portions and non-text-like portions. The method includes the steps of establishing a set of fuzzy detection rules for distinguishing text-like portions of an image from non-text-like portions of an image, dividing the test image into a plurality of segment, and applying the set of fuzzy detection rules to each segment of the test image to thereby classify each segment as text-like or non-text-like. Preferably, the establishing step includes the sub-steps of identifying a plurality of image features that distinguish different portions of an image, generating a plurality of fuzzy detection rules by applying different combinations of the features to a text-like learning image and to a non-text-like learning image, and minimizing the rules to exclude those rules not supported by a predetermined amount of the learning images, and allocating the non-excluded rules to the set. Optionally, the generating sub-step includes the sub-steps of normalising each image feature to have a value in the range 0 to 1, partitioning each input feature space into a plurality of equally spaced region, assigning each input feature to a label of one of the regions to maximize a membership value of the label in the one region, selecting for each the region the maximized label for each feature to thus form a respective fuzzy rule.

An efficient 3D deformable model with a self-optimising mesh

Abstract: Deformable models are a powerful and popular tool for image segmentation, but in 3D imaging applications the high computational cost of fitting such models can be a problem. A further drawback is the need to select the initial size and position of a model in such a way that it is close to the desired solution. This task may require particular expertise on the part of the operator, and, furthermore, may be difficult to accomplish in three dimensions without the use of sophisticated visualisation techniques. This article describes a 3D deformable model that uses an adaptive mesh to increase computational efficiency and accuracy. The model employs a distance transform in order to overcome some of the problems caused by inaccurate initialisation. The performance of the model is illustrated by its application to the task of segmentation of 3D MR images of the human head and hand. A quantitative analysis of the performance is also provided using a synthetic test image.

Photographic image retrieval system

Abstract: PROBLEM TO BE SOLVED: To speedily retrieve an image which is similar to or the same as an object image to be retrieved from many data base images by narrowing down the retrieval range according to information on a photography state and extracting the similar data base image according to image features. SOLUTION: Once a digital camera 101 photographs a subject P0 , a timer 21 specifies the photography time (season). A retrieval range narrowing-down means 3 acquires information S on the photography time and selects one of data base elements 71 to 74 of a host computer 301. An image feature extracting means 4 scans the retrieval object image P to extract image features C1 to Cm . An object image retrieval means 5 compares the extracted image features with image features of data base images of the selected data base element in order. Then data base images P1 to Pk which are similar to the retrieval object image P are downloaded from the data base 7 and displayed on a display 6 together with the retrieval object image P.

Marching cores: a method for extracting cores from 3D medical images

Abstract: The authors present an algorithm, called marching cores, that generates cores of 3D medical images and also generalizes to finding implicitly defined manifolds of codimension greater than one. As one marches along the core, one use medialness kernels to generate new medialness values and then find ridges in the extended medial space using the geometric definition of height ridges and mathematical models of manifold intersections. Results from both a test image and a CT image illustrate the algorithm.

Method and device for identifying fingerprints

Abstract: A method of identifying fingerprints, the method including the steps of: acquiring a test image formed by a number of test points characterized by different grey levels defining a test surface; determining significant points in the test image; and verifying the similarity between regions surrounding the significant points and corresponding regions of a reference image whose points present different grey levels defining a reference surface. The similarity between the regions is verified by computing the integral norm of portions of the test and reference surfaces; and the integral norm is computed using flash cells programmed with a threshold value correlated to the value of the grey levels in the reference region, by biasing the flash cells with a voltage value correlated to the grey level in the test region, and measuring the charge flowing through the flash cells.

X-ray examination apparatus including an image pick-up apparatus with a correction unit

Abstract: An X-ray examination apparatus (1) includes an X-ray image intensifier (5) for deriving an optical image from an X-ray image. The optical image is picked up by means of an image pick-up apparatus (6) which includes a correction unit (10) which is arranged to form a dark image signal and to derive test image signals from the optical image. Correction values are derived on the basis of the test image signals and the dark image signal. The correction unit (10) is arranged to form a dark image signal, to derive one or more test image signals from the optical image, and to derive the correction values from said test image signals and the dark image signal. The dark image signal is picked up in the absence of incident light on the image sensor (7, 8). The test image signals have a signal level which represents brightness values of the optical image which have been amplified by individual gain values.

An Experimental Comparison of Appearance and Geometric Model Based Recognition

Abstract: This paper describes an experimental investigation of the recognition performance of two approaches to the representation of objects for recognition. The first representation, generally known as appearance modelling, describes an object by a set of images. The image set is acquired for a range of views and illumination conditions which are expected to be encountered in subsequent recognition. This image database provides a description of the object. Recognition is carried out by constructing an eigenvector space to compute efficiently the distance between a new image and any image in the database. The second representation is a geometric description based on the projected boundary of an object. General object classes such as planar objects, surfaces of revolution and repeated structures support the construction of invariant descriptions and invariant index functions for recognition.

Method for positional matching of images and system for testing products by using the same

Abstract: The present invention provides an image matching method which allows non-ear image positional shifts to be corrected on a real time basis, and an economical product testing system using this method. A two dimensional test image, consisting of pixels arranged as a matrix of bits distributed in both the vertical direction and the horizontal scanning direction, and an associated reference image are subjected to template matching at a cell matching arithmetic unit for each of line blocks consisting of a plurality of scan lines. The result of the template matching are quantitatively evaluated at an evaluation unit as being good or bad, and positional shifts are sequentially computed according to good evaluation results. Based on the positional shifts thus obtained, the comparative pixel addresses are accordingly corrected before the two images are compared at the comparator.

Ultrasound system for estimating the speed of sound in body tissue

Abstract: An ultrasound system (50) estimates the speed of sound in the tissue (60) under examination. The ultrasound system obtains a series of test images (150) using different estimates of the speed of sound in the body tissue. For each image produced, the ultrasound system computes a function that is indicative of image quality for one or more regions of interest (152) in the test image. The image quality function exhibits a minimum or maximum when computed for a region of interest obtained at a speed of sound substantially equal to a true speed of sound in the tissue. The ultrasound system selects the test image having the minimum or maximum function value and obtains subsequent images of the tissue using the speed of sound used to obtain the test image selected.

X-ray image system design using a human visual model

Abstract: Because of the complex response of the human visual system, typical measurements of image system quality such as the detective quantum efficiency, mean transfer function, and signal-to- noise ratio cannot always be used to determine conditions for optimal perceptual image quality. Using a model of the human vision system, the ViDEOS/Sarnoff Human Vision Discrimination Model (HVM), this work demonstrates that human vision models provide a promising quantitative measure of image perceptual quality. The model requires an image and a matching reference image in order to determine the perceptual difference between the images at each point. A simple model of a digital amorphous silicon medical x-ray system is used to create the necessary images as a function of various design parameters. The image pairs are then analyzed by the HVM. In all cases the dependence of perceived image quality closely follows measures of image quality as determined by the HVM for many image system design variations. Increasing the detector size actually increases the image quality in the presence of either readout or input noise. The model was also used to optimize the image system for a specific task optimization. As an example, the effect of system design parameters on tumor identification in mammographic images is determined.© (1996) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Digital image forming apparatus with test image optimization

Abstract: An image forming apparatus is provided which is immune to characteristic variations of a photoconductor and a developer material, which can detect the amount of toner adhering to a test toner image accurately, and which can always form a favorable image using an optimal image forming parameter. A predetermined test toner image is formed on the photoconductor using developing devices. The amount of toner adhering to the formed test toner image is detected by an AIDC sensor. A printer control unit determines grid potential Vg of a corona charger and development bias potential Vb of each developing device based on the detected amount of adhering toner. A predetermined image is formed using the determined grid potential and development bias potential. The printer control unit changes the image forming condition for the next test toner image based on the detected amount of adhering toner so that the amount of toner adhering to the next test toner image can be detected in a range of high detection sensitivity of the AIDC sensor.

Comparison of multiscale representations for a linking-based image segmentation model

Abstract: Different multiscale generators are qualitatively compared with respect to their performance within a multiscale linking model for image segmentation The linking model used is the hyperstack that was inspired by linear scale space theory The authors discuss which properties of this paradigm are essential to determine which multiscale representations are suited as input to the hyperstack If selected, one of the main problems the authors tackle is the estimation of the local scale such that the various stacks of images can effectively be compared For nonlinear multiscale representations, which cart be written as modified diffusion equations, an upper bound can be achieved by synchronizing the evolution parameter The synchronization is empirically verified by counting the number of elliptic patches at corresponding scales The authors compare the resulting stacks of images and the segmentation on a test image and a coronal MR brain image

Automatic extraction of human facial features

Abstract: This paper addresses a method of extracting human facial features from the head-and-shoulder images used in videophone communications. A basic idea behind the scheme is to make full use of the information in both the temporal and spatial domains to detect facial features. The new approach to facial feature extraction consists of a temporal and a spatial eye-mouth finder (EMF). The temporal technique eliminates the influence of background and gives a rough and reliable position estimation of the interesting objects, e.g. eyes and mouth, and the latter reaches an accurate result which is needed in videophone communications. Another characteristic of this method is its simplicity. Some basic operators can be used twice, i.e., they are used not only in the temporal domain but also in the spatial domain. The results on the test image sequences are satisfactory.

Access and Retrieval from Image Databases Using Image Thumbnails

Abstract: The emerging role of thumbnail images in the selection of images for display from large image databases and via network access requires that the characteristics of thumbnails be seriously studied. We introduce a measure of effective compression Ceff(p) that is a function of the probability p that thumbnail access will be followed by the display of a full-scale image. For credible values of p, we deduce the need for the development of thumbnail-based image compression schemes, which efficiently and effectively use thumbnail data as part of the code for the fullscale image. We briefly discuss design features of thumbnailbased variants of the block-oriented coding schemes of vector quantization, fractal coding, and JPEG. 1. THUMBNAIL IMAGES Thumbnail images are now commonly used as WYSIWYG directory icons for the selection of images from directories and local databases. Notable systems for managing query of image databases, the QBIC system developed by Niblack and coworkers at IBM San Jose, [2] and the PhotoBook System developed at MIT Media Lab by Pentland et al, [3], feature arrays of small images for displaying the images most similar in content to the users query. A number of researchers, notably Picard[3], have stressed the important emerging role of very large image databases as in collections of compressed images stored on a CD ROM, or the far larger compilations available via the Internet. The needs for a user-friendly interface to these very large image albums and libraries requires the development of image compression schemes suitable and efficient for applications where the image thumbnails are more often required than full images, and full image display is invariably preceded by a data fetch of the thumbnail data. This entails that image compression schemes suitable for very large database applications should be so designed that thumbnail data is separately accessible, and that the information delivered in the thumbnail should be used with other image code for economical image synthesis or reconstruction. In this paper these considerations lead us to introduce a measure of image compression that gives an effective compression for image data accessed via thumbnails. We examine how traditional block-oriented vector quantization (VQ) and fractal coding based on Jacquin's scheme should be modified. Finally we discuss JPEG coding in this regard. 1.1 Gray-scale Thumbnails Although image thumbnails are now commonplace, a literature search failed to locate any previous formal description of thumbnails. The following general definition of a thumbnail image is proposed: An image thumbnail is produced after the partitioning of an image into rectangular (usually square) blocks of pixels, and constructing a thumbnail image comprising blocks, of single pixel-size or larger, of uniform pixel value. The blocks in the thumbnail are uniformly scaled with respect to those of the image. In the simplest case of the uniform partitioning of an image into constant-sized blocks each of R rows and C columns the image block at (rR, cC) in the image may be denoted by its block row number r and block column c as B[r][c]: the corresponding block in the thumbnail contains pixels of gray-scale or colour index

Automatic typing of raster images using density slicing

Abstract: A system for determining the type of graphical data within a scanned image. The system scans an image to obtain grayscale image data, and then performs a density slice operation on the grayscale image data, using a predetermined grayscale range, to produce binary image data. The system erodes the binary image data, and counts the number of black pixels remaining within the image data. If the count of the black pixels within the image exceeds a maximum acceptable pixel count, the area is considered to be continuous tone, such as a photograph, otherwise, the region is considered to be bi-tonal, such as line art or text. The system can also perform multiple density slices and erosions, using different grayscale ranges, OR the results, and then analyze the result of the OR operation to determine the type of image.

Image processor which manually and independently designates processing parameters for character data and image data

Abstract: An image processor includes an operation panel at which color adjustments for image data are set. A generation device generates a pattern signal which represents a state related to the set color and image data representing a test image. A processor processes the image data representing the test image on the basis of the set color adjustment. The processed image data and the pattern signal are then output by an output device such as a color printer.

Inter-pixel eudlidean pahts for image analysis

Abstract: Inter-pixel boundaries provide a robust and consistent description of segmented images but have a poor visual aspect, especially when being enlarged. Approximation curve are sometimes used to smooth discrete boundaries but they do not provide error free reconstruction and may be uneasy to use in this context. In this paper we show the advantages of using Euclidean paths in order to smooth inter-pixel boundaries and we demonstrate the interest of inter-pixel Euclidean paths for the purpose of image segmentation and analysis.

Digital image comparing system

Abstract: A system (1) for comparing digital images, whereby a first and second data processing block (5, 6) receive respective data streams (I, I') corresponding to a reference image (S) and a detected image (S') for comparison with the reference image (S). The data processing blocks (5, 6) detect reference points in the images, and generate data (P1, P4), which is supplied to a block (10) for determining a first approximation of the function A o (X,Y,alpha) relating the two images (S, S').The system also presents blocks (17, 27) for successively refining the function relating the reference image (S) to the detected image (S').

Digital image recording method and apparatus therefor and digital image processing apparatus

Abstract: A digital image recording method is to make high quality positive reproduction images from any types of originals by processing image data of each original based on an image characteristic value such as an average density of a prime subject portion of the original, which is derived from the image data. A basic image recording amount, which is used for every pixel, is determined based on the image characteristic value. Based on the basic image recording amount and a value of image data assigned to a pixel, recording data of that pixel is determined, and the recording data is converted into an image control amount with reference to a look-up table. The image control amount is used in an image recording device for recording the reproduction image.

Modified quantisation algorithm for dithering of colour images

Abstract: Although colour quantisation and dithering operations are always performed sequentially, quantisers are designed independently from ditherers. This leads to suboptimal results. A new quantiser design is proposed that takes the subsequent dithering into account, and better image quality is obtained.