Abstract: The contrast determination apparatus includes illuminating light sources (12) and an image sensor (26) i.e. a 2-D CCD for capturing a two-dimensional image of e.g. a marked wire (32) on a holder (34), the captured image being sampled over the mark and the background. The sensor includes an optical system (28,30) selected with regard to the character size of the marks so that the field of view of the sensor is sufficient to contain a complete character as well as a generous amount of background. An area of the captured image is designated in which the samples for contrast measurement are to be taken, and a processor (24) takes the pixel values from the image which are thresholded to categorise them as “black”, or “white”, thus forming a two-tone image.

Abstract: A method for composition of two digital images which overlap in an overlapping pixel region, including adjusting the pixel color values of at least one of the digital images so as to produce resulting digital images including at least one modified digital image, and combining the resulting digital images in the overlapping pixel region by taking weighted averages of their pixel color values.

Abstract: A computing device to classify, manipulate, store, search, and selectively retrieve items from image databases, using a method & apparatus including a computer processor to analyze the configured disposition of a multiplicity of linear motion paths that constitute a glyph delineated within a defined planar rendering area and to process, manipulate, and compare data representing said configured disposition of said linear motion paths, comprising (a) a template analytic lattice constituted of a predetermined multiplicity of cell partitions, the totality of the analytic lattice being coextensive with the defined rendering area of the glyph and in the plane of motion of the linear motion paths of the glyph; (b) means of interpreting each linear motion path as a sequence of displacement vectors, determining which displacement vectors intersect specific boundaries of specific cells of the analytic lattice, and registering each cell boundary intersection by both recording the intersecting vector inclination grad

Abstract: A biometric input device, system and method includes a biometric input device having a scanning window surrounded by a ridge for ensuring positive positioning of a biometric sample such as a thumb. The biometric input device includes an optical assembly having a prism with a focusing lens disposed on a side thereof and optionally integrally formed therewith. A biometric comparison method is provided for comparing data from said biometric input device with data from a database using both directional image comparison and clusterized minutia location and direction comparison. A further system is provided for allowing access to computer functions base on the outcome of the comparison method.

Abstract: A printed or handwritten character image is recognized by training (301) a plurality of lookup tables with a set of known referent characters; obtaining (302) a bitmap of a character image to be recognized; mapping (303) the bitmap onto a standardized character matrix; partitioning (304) the matrix into a plurality of sub-matrices; (305) determining a set of candidates for each sub-matrix; and selecting (306) a preferred candidate from among the set of candidates responsive to at least one pre-defined selection criterion. The invention is implemented by means of a scanner (102), a character mapper (104), a matrix partitioner (106), a candidate set builder (108), and a character selector (110).

Abstract: A sensing device and method for determining the proximity and lateral movement of a second object relative to a first object. To determine proximity and lateral movement, the second object is illuminated to create light contrasts on that second object that correspond to unique structural and/or printed features of that second object. Light contrast data is compared to reference data to determine proximity and lateral movement of the second object relative to the first object. The invention typically utilizes an illumination source, imaging optics, and a sensor array mounted to the first object. This invention can be used in the end-effectors of a robotic arm to manage handling of a payload. It can also be used as a contact sensor to gate the operation of a manual scanning device when the scanner is brought into contact with the surface of a document.

Abstract: Image-dependent tone and color reproduction processing of digital images is accomplished by creating a spatially blurred and sub-sampled version of the original image, and applying knowledge of the capture device physical characteristics to obtain statistics related to the scene or original captured. The statistics are used for image-dependent linearization of the captured image data based on an OECF model, and in conjunction with information about the output medium, to calculate image-specific preferred tone reproduction curves based on a preferred reproduction model. These curves may be applied to the red, green, and blue channels of RGB-type images to produce preferred tone and color reproduction, or to the luminance channel of luminance-chrominance type images to produce preferred tone reproduction. Alternately, the linearized image data may be reproduced directly.

Abstract: A method, apparatus, and article of manufacturing employing lexicon reduction using key characters and a neural network, for recognizing a line of cursive text. Unambiguous parts of a cursive image, referred to as “key characters,” are identified. If the level of confidence that a segment of a line of cursive text is a particular character is higher than a threshold, and is also sufficiently higher than the level of confidence of neighboring segments, then the character is designated as a key character candidate. Key character candidates are then screened using geometric information. The key character candidates that pass the screening are designated key characters. Two-stages of lexicon reduction are employed. The first stage of lexicon reduction uses a neural network to estimate a lower bound and an upper bound of the number of characters in a line of cursive text. Lexicon entries having a total number of characters outside of the bounds are eliminated.

Abstract: A method for controlling a scheduler on a computer display including the steps of: a) dislaying a calendar in a calendar area on the computer display; b) choosing at least one date on the calendar; and c) displaying a schedule in a schedule area on the computer display for the chosen date or dates, where both the calendar and the schedule remain active and within a single window. In one embodiments, the method is implemented on a pen-based computer system, where a stylus can choose a desired date or dates on the calendar to automatically display the schedules for that date or dates.

Abstract: An image-processing method is provided with the first step of dividing an input image having n(n>1) gray scales into a plurality of matrixes, the second step of carrying out at least either a resolution-converting process or a variable magnification process for each of the divided matrixes, by using a hierarchical neural network that can execute a learning process for each input image, and the third step of outputting the image processed in the second step as an output image having n gray scales. Thus, the weights adjustment of the network can be carried out on each input image whatever image is inputted thereto; therefore, it is possible to always provide an optimal converting process.

Abstract: A method of displaying images is based on both a first linearization and a second linearization. In one embodiment, the linearizations are performed by traversing two space-filling curves. In another embodiment, the linearizations are performed by traversing a cluster data structure. More than two linearizations may be displayed.

Abstract: A method for classifying and recognizing patterns which includes producing a pattern to be classified and recognized of an m-dimensional object. The object to be classified and recognized is provided in the form of an m-dimensional traverse. The method also acquires a property represented by an s-dimensional value for selected points of the traverse, whereby the s-dimensional value reflects a relationship between a respective selected point and a point preceding it and a point succeeding it on the traverse, links the s-dimensional values for the selected points of the traverse in such a manner that an overall property represented by a q-dimensional value characterizing the traverse is obtained, and smooths the traverse in order to form a new traverse.

Abstract: A color transformation look-up table is provided, which is to be referred to when image signals for a non-self-luminous displaying medium are to be transformed into image signals for a self-luminous displaying medium such that appearances of perceived colors may become identical between images displayed on the two displaying media. The look-up table includes a function for transforming a dynamic range of the image signals for the non-self-luminous displaying medium into a dynamic range of the image signals for the self-luminous displaying medium such that a range of brightness of an image, which the non-self-luminous displaying medium can display, may become approximately identical with a range of brightness of an image, which the self-luminous displaying medium can display.

Abstract: In order to change the positions of a plurality of nodes that constitute a line or a surface, following steps are executed: storing in a storage device data of a normal for each node; changing the position of each node and storing the position information into the storage device by (1) defining a virtual elastic member connected to each node in a direction of the normal of each node, and (2) stretching or shrinking the elastic members in the direction of each normal so as to balance each elastic member; and repeating the storing step and the changing step until a predetermined condition has been satisfied. As a result, a smooth curve or smooth surface is generated.

Abstract: In an image input/output system, a personal computer (PC) and a multi-function peripheral apparatus, containing a scanner device and a printer device, are connected by a single cable via respective parallel interfaces. If a detector device of the multi-function peripheral apparatus detects an error in the scanner device or the printer device, the multi-function peripheral apparatus transmits error information to the PC via the parallel interfaces. Despite the error in the printer or scanner device, the PC is able to output an ordinary operation instruction to the device that is free from the error. In accordance with such an instruction, the multi-function peripheral apparatus exchanges information or data with the PC, thereby allowing the device that has no error to operate normally.

Abstract: The pore-size distribution of a porous sample of variable porosity is modeled achievement of, allowing laboratory studies on the behavior of the medium modeled in relation to fluids. The porosity of the porous medium is modeled on one or more parting surfaces by means of a network (R) of intersecting channels (C) whose nodes form pores (P), the size of these channels showing physical properties of the medium and being selected from one or more discrete channel size distributions. In order to model the porosity of a heterogeneous sample exhibiting very different porosity zones, several discrete channel distributions are preferably used, these distributions being disjoint or not, and modeling with different zones, zones of low permeability and zones of higher permeability.

Abstract: A ruled line extracting apparatus obtains circumscribed rectangles of pixel concatenation regions included in an input pattern, and calculates the most frequent value of their heights. Additionally, the apparatus integrates segments by ignoring a wild card segment, and calculates the most frequent value of height/width of extracted straight lines and segments structuring the straight line. Next, it performs a process for integrating/deleting straight lines using each threshold value based on the highest frequency value. Then, it checks/deletes a straight line according to a distribution of black pixels around the straight line, and recognizes the remaining straight lines as ruled line candidates.

Abstract: In an image processing system having a primary image pickup device and a plurality of reference image pickup devices, a feature region consisting of a plurality of feature segments each defined by a pair of feature points is extracted from a primary image. Subsequently, a correspondence point candidate of each of the feature points is extracted from each of the reference images. Based on the feature points and the correspondence point candidate of each of the feature points for each of the reference images, three-dimensional coordinates corresponding to the feature points are calculated, and the feature region is extracted as a target object from the primary image based on the feature points and the three-dimensional coordinates corresponding to the feature points for each of the reference images.

Abstract: A low cost image transform device capable of converting an input image to the linear drawing style in real time is presented. An edge signal of the input image is detected and normalized. The normalized edge signal is then non-linear transformed to decrease the intermediate tone level of the edges so that lines can be seen more clearly. Inversion control is further used to reverse the lightness and darkness of the non-linear transformed edge signal. The inverted signal is subsequently level adjusted and then mixed with a delayed version of the input signal using an externally controlled ratio signal. The resulting output signal is a drawing or painting type image. Since these processes are executed by simple addition or multiplication, the linear drawing style image is obtained in real time, in which edges having high-light and shaded contrast are extracted from the input image.

Abstract: An image processing apparatus is provided with a linear processor array which includes a plurality of linearly coupled processing elements. The apparatus further includes a plurality of local memories each of which takes a form of one-dimensional pixel data memories. The local memories are respectively assigned to the plurality of processing elements. Further, the local memories are arranged so as to store in combination a two-dimensional pixel image to be processed. A plurality of buffers are respectively assigned to the processing elements. Each buffer stores pixel location information of at least one center pixel from which a unique pixel value is to be propagated if the center pixel exists on a corresponding local memory. With the arrangement mentioned above, in order to accelerate pixel data propagation in the two-dimensional pixel image, a plurality of register units are respectively assigned to the plurality of processing elements.