Determining Amount An Image Is Rotated Or Skewed Patents (Class 382/289)
-
Patent number: 6597817Abstract: This patent describes a print roll for use in an instant camera device, the print roll having a ink return tray for collecting excess waste ink from the printing process. The return tray can comprises a sponge-like strip affixed to a leaf portion of the print roll.Type: GrantFiled: July 10, 1998Date of Patent: July 22, 2003Assignee: Silverbrook Research Pty LtdInventor: Kia Silverbrook
-
Publication number: 20030128895Abstract: A method of determining image skew in a scanned document includes scanning the image and determining on a pixel-by-pixel basis whether or not pixels are ON or OFF on scan lines and columns along both the fast and slow scan directions for a particular document rotation angle. Through one read of the image, image data is sampled simultaneously at a plurality of predetermined document rotation angles From the sampled data, the second order moment of the number of ON pixels is calculated as a function of document rotation angle for scan lines along both the fast and slow scan directions, yielding two independent skew angle estimates. Skew angle estimates corresponding to valid second order moment data sets are compared and combined to provide a resultant skew angle estimate for the document.Type: ApplicationFiled: January 7, 2002Publication date: July 10, 2003Applicant: XEROX CORPORATIONInventor: Stuart A. Schweid
-
Publication number: 20030128298Abstract: A method and apparatus for tracking a color-based object in video sequences are provided. According to the method, an initial object area in one frame of video sequences desired to be tracked is assigned, and an initial object effective window containing the initial object area is assigned. A frame following the frame containing the assigned initial object area is received as a newly input image, and an object search window containing the initial object area for tracking and the initial object effective window in the newly input image is assigned. Then, the model histogram of the initial object area corresponding to a predetermined bin resolution value and the input histogram of the image in the object search window are calculated. From the calculated object probability image, using a predetermined method, a new object area to which the initial object area moved is obtained in the next frame in which the initial object area of the frame desired to be tracked is given as a previous (tracked) object area.Type: ApplicationFiled: December 27, 2002Publication date: July 10, 2003Applicant: Samsung Electronics Co., Ltd.Inventors: Young-Su Moon, Chang-Yeong Kim
-
Patent number: 6591005Abstract: A method of determining the vertical axis of an image, including the steps of: detecting a set of vanishing points related to the image; selecting a vanishing point based on a predetermined criteria; and identifying the vertical axis with the selected vanishing point.Type: GrantFiled: March 27, 2000Date of Patent: July 8, 2003Assignee: Eastman Kodak CompanyInventor: Andrew C. Gallagher
-
Publication number: 20030123753Abstract: A technique for determining the slope of a field pixel is described. According to the technique, one or more sets of diagonal field pixels are downscaled (or downsampled) before they are provided to respective edge detector circuits. By downscaling the sets of diagonal field pixels before they are provided to respective detector circuits, the edge detector circuits detect diagonal edges and, in particular, shallow diagonal edges with greater accuracy. As such, the slopes assigned to the field pixels are more likely to be correct. This ultimately results in a high quality progressive video signal that can be used to generate an image that is completely or substantially free from objectionable artifacts.Type: ApplicationFiled: December 27, 2001Publication date: July 3, 2003Applicant: ZORAN CORPORATIONInventor: Wing-Chi Chow
-
Patent number: 6584236Abstract: An image processing apparatus for detecting the inclination of an object is provided. This image processing apparatus has a read means which reads the object and outputs image data, an amount of change calculation means which calculates the sum of the amounts of change of the image data of the object in at least one direction, and an inclination calculation means which calculates the inclination of the object based on the sum calculated by the amount of change calculation means.Type: GrantFiled: October 7, 1999Date of Patent: June 24, 2003Assignee: Advantest CorporationInventors: Kazuyuki Maruo, Takahiro Yamaguchi, Masayoshi Ichikawa
-
Publication number: 20030103685Abstract: A method of comparing a two-dimensional image of an object to library images of that object as seen from a variety of predetermined orientations. The method further includes a rating of the accuracy of fit of the object image to each library image to determining the overall best fit and, thus, the orientation of the object.Type: ApplicationFiled: December 4, 2001Publication date: June 5, 2003Inventor: Thomas P. Weismuller
-
Publication number: 20030099395Abstract: The described arrangements and procedures identify an image's orientation by extracting features from peripheral portions of the image. The procedure evaluates the extracted features based on training image feature orientation classification models to identify the image's orientation.Type: ApplicationFiled: November 27, 2001Publication date: May 29, 2003Inventors: Yongmei Wang, Hong-Jiang Zhang
-
Patent number: 6556725Abstract: A column address is decoded by each column decoder, and an arrangement of pixels to be written to a memory cell array is rotated by a rotation circuit. The rotation result is written to the memory cell array in accordance with the decoding result of the column address. Then, the column address is decoded by each column decoder to a decoding result which is different from the decoding result of the column address at the time of writing. In accordance with the decoding result, pixels stored in the memory cell array are read. The arrangement of the read pixels is rotated by the rotation circuit and then outputted. Thus, rearrangement of pixels constituting an image can be carried out quickly while avoiding any increase in the size of the device.Type: GrantFiled: May 8, 2000Date of Patent: April 29, 2003Assignee: Sony CorporationInventors: Tetsujiro Kondo, Akihiro Okumura, Hiroshi Sato, Tsutomu Ichikawa
-
Publication number: 20030072499Abstract: A paper detecting apparatus includes a transfer base, a first and a second linear sensors, and a data processor. The transfer base transfers a paper in a predetermined transfer direction, and the paper includes a first and a second side edges in parallel to each other. The first linear sensor includes a first linear reading region for detecting the first side edge of the paper. The second linear sensor includes a second linear reading region for detecting the second side edge of the paper. The data processor processes the data obtained by the first and the second sensors. The first and the second sensors are arranged in a manner such that the first and the second linear reading regions are positioned transversely to the transfer direction. The data processor detects the tilt angle between the paper and the transfer direction based on the positional information of the first and the second side edges obtained by the first and the second sensors.Type: ApplicationFiled: August 30, 2002Publication date: April 17, 2003Applicant: ROHM CO., LTD.Inventors: Hideki Sawada, Motoshi Uehara, Hiroshi Fukumoto
-
Patent number: 6549680Abstract: A method and apparatus for determining skew in an image. The method and apparatus sample portions of an image using windows that are projected on the image. Connected components are generated from the sampled image data and projected. Based on the direction of the projected connected components, the skew of the image in at least one direction is determined.Type: GrantFiled: June 23, 1998Date of Patent: April 15, 2003Assignee: Xerox CorporationInventor: Shriram V. Revankar
-
Patent number: 6531959Abstract: A position detecting device for a vehicle detects the position of an object in a real space coordinate system. A plurality of objects are extracted from an image obtained by cameras, and a pitching-dependent correction amount is calculated based on amounts of displacement in position of the plurality of objects in a direction of height. Positions of the plurality of objects are corrected based on the pitching-dependent correction amount.Type: GrantFiled: July 10, 2000Date of Patent: March 11, 2003Assignee: Honda Giken Kogyo Kabushiki KaishaInventors: Nobuharu Nagaoka, Takayuki Tsuji, Masahito Watanabe, Hiroshi Hattori
-
Patent number: 6532303Abstract: A line-direction deciding device that can decide the direction of lines in an image having a complicated layout of characters as well as line directions other than vertical and horizontal line directions. The present invention provides a line-direction deciding device that extracts character elements (image components) from an image, examines in which direction the character elements are most densely distributed and decides by majority the direction of lines of characters within a processable area as well as an image inclination correcting device that corrects an image for inclination according to a processing result made by the line-direction deciding device provided with image-inclination detecting means.Type: GrantFiled: July 29, 1998Date of Patent: March 11, 2003Assignee: Sharp Kabushiki KaishaInventor: Hisashi Saiga
-
Patent number: 6529643Abstract: A system for generating a warped contone image that compensates for beam scan trajectory distortions. The system includes an image buffer for storing a portion of a received contone image. An interpolation coefficient generator provides interpolation coefficients associated with a warped pixel within the warped contone image in response to an input identifying the warped pixel. A pixel interpolator is coupled to the image buffer and the interpolation coefficient generator and provides an output signal that identifies the warped pixel within the warped contone image. The pixel interpolator further retrieves pixels from the contone image stored in the image buffer using the interpolation coefficients and generates the warped pixel by combining the retrieved pixels into a single pixel value.Type: GrantFiled: December 21, 1998Date of Patent: March 4, 2003Assignee: Xerox CorporationInventors: Robert P. Loce, Martin E. Banton, Steven J. Harrington
-
Patent number: 6529616Abstract: A special test pattern and image quality analysis system and process for evaluating the test pattern are provided to accurately measure color-color registration in an image output device that prints in CMYK color. The process is robust even when using relatively low-resolution CCD-based scanners and also is unique in that the process automatically factors out errors originating from skew between the detector and the subject of measurement. Further, registration of each of C, M, and Y relative to K are independently determined. The test pattern includes an upper part and a lower part, with both the upper and lower parts having a black K component and the upper part also including color components for C, M and Y. The system and method have potential for being built in to color printers or copiers to allow measurement of color misregistration within the paper path and automatically correct for color registration errors.Type: GrantFiled: November 29, 1999Date of Patent: March 4, 2003Assignee: Xerox CorporationInventors: D. Rene Rasmussen, Edul N. Dalal, Susan June Zoltner
-
Publication number: 20030035593Abstract: The registration and skew information of a document about to be scanned are detected prior to capturing the entire image of the document. Two sensors, a fixed distance apart, are used to detect the document skew. A third sensor is used to detect the edge position of the document. Paper sensors in the Automatic Document Feeder (ADF) are used to determine the document size. The data from the skew sensors are used to calculate the required skew correction angle and direction by which to rotate the image. The document edge position information together with skew information is used to determine the exact location of a corner of the document. This information is used to correct skewed image in real-time, during scanning the document.Type: ApplicationFiled: May 17, 2000Publication date: February 20, 2003Inventors: Gregory Rombola, Mark J. Jablonski, Larry L. Christensen, Thomas J. Wetzel
-
Publication number: 20030031359Abstract: A sphere having a plurality of marks given to the surface thereof is photographed at a plurality of times to obtain a plurality of two-dimensional images of said sphere. An imaginary sphere having a plurality of marks given to the surface thereof is generated in a three-dimensional coordinate space by a computer. In making the imaginary sphere placed in a reference posture coincident with the posture of the two-dimensional image, an optimum displacement amount of said posture of said imaginary sphere is determined by using a computation based on Genetic Algorithms. A rotation matrix is derived from the posture of the sphere measured for each dimensional image thereof and a computation is performed on the rotation matrix to thereby obtain the rotational amount of the sphere and the direction of its rotational axis.Type: ApplicationFiled: April 16, 2002Publication date: February 13, 2003Inventors: Mitsunori Miki, Masaya Tsunoda, Masahide Onuki
-
Patent number: 6515769Abstract: An image forming apparatus and method in which, when a recording medium on which a gray-scale pattern has been formed is placed upon a platen in a skewed attitude, the resulting offset is corrected and image forming conditions are adjusted to obtain an ideal image. In one one such apparatus, a 256-tone pattern image of a designated color is formed on a recording medium. If the recording medium has been placed upon a platen in a skewed attitude when the pattern is to be read, the position of the pattern image is corrected, the gamma characteristics of a LUT are calculated based upon the correct pattern image and the calculated values for the LUT are set.Type: GrantFiled: February 20, 1997Date of Patent: February 4, 2003Assignee: Canon Kabushiki KaishaInventors: Yuichi Ikeda, Nobuatsu Sasanuma
-
Publication number: 20030016883Abstract: The present invention includes a system and method for the correction of user induced inadvertent orientation errors in captured digital images before the digital image is saved to a storage media or memory. A system of the present invention checks a user-selectable input to determine if the orientation correction has been enabled, enables a tilt determining mechanism which senses orientation errors when the feature is enabled, corrects the orientation errors in the viewed image, displays a corrected digital image to the user and allows the user to store a digital representation of the corrected image into a memory. The method of the present invention includes receiving a digital representation of an image, identifying vertical or horizontal lines contained within the image, determining an orientation error, rotating the digital representation of the image to reduce the orientation error and displaying a corrected digital image.Type: ApplicationFiled: July 20, 2001Publication date: January 23, 2003Inventor: John M. Baron
-
Publication number: 20020196979Abstract: Systems and methods for automatically extracting a graphical bar code (i.e., an image that contains inconspicuous graphical modulations that encode embedded information) are described. In accordance with this automatic extraction scheme, a graphical bar code may be isolated from a composite image in a way that preserves the information-containing graphical modulations encoding the embedded information and avoids corrupting artifacts, such as markings contained in the composite image. The resulting extracted graphical bar code readily may be processed into a format that is tailored to the requirements of a decoding system that may be particularly sensitive to noise, such as extraneous markings and image corruption. In addition, this automatic extraction scheme robustly handles missed and incorrect detections.Type: ApplicationFiled: June 7, 2001Publication date: December 26, 2002Inventors: Jonathan Yen, Doron Shaked, Avraham Levy, Renato Keshet
-
Publication number: 20020196977Abstract: A method for locating symbols arranged in one or more rows in an image includes smearing the image, and fitting line segments through edge points of features in the smeared image. A group is found of the line segments that are in mutual proximity and are mutually substantially parallel. A region of the image that contains the group of the line segments is identified as a possible location of the symbols.Type: ApplicationFiled: June 25, 2001Publication date: December 26, 2002Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventor: Yaakov Navon
-
Publication number: 20020191850Abstract: The present invention provides a method for detecting an object. The method includes capturing a binary image of the object, and determining a projection of the binary image to a first axis. The method further includes determining a difference between a profile of a target object to the first axis and the projection at a plurality of positions along the first axis, and detecting the object by determining if the difference between the profile and the projection is less than a threshold at one of the plurality of positions.Type: ApplicationFiled: June 15, 2001Publication date: December 19, 2002Inventors: Claus Neubauer, Ming Fang
-
Patent number: 6493470Abstract: An image processor which corrects tilt of an input image without operator intervention. Projections of two partial images of an original are obtained at check points determined from input image information. A tilt angle of the original is obtained from a correction position of the projections of each partial area. The image is divided into belt-shaped small areas and shifted in accordance with the obtained tilt angle to form an image in which the tilt of the input image is corrected.Type: GrantFiled: June 19, 1996Date of Patent: December 10, 2002Assignee: Canon Kabushiki KaishaInventors: Hiroaki Ikeda, Toru Niki
-
Publication number: 20020168093Abstract: A prescreen filtering method and algorithm based upon Attributed Relational Graph (ARG) techniques are employed in a node-by-node matching to individually determine a best alignment of the sets of minutia of a pair of search and file fingerprints. First, the directional components of each and every different pair of minutia from the two sets are compared to ensure that they are within a given angular tolerance, which is selected to allow for a reasonable variation in possible rotational misalignments. After this directional alignment tolerance criteria has been passed, a Distance Matrix (DM) score is generated for each passed [u,v] minutia pair by performing a virtual alignment of the [u,v] minutia pair in location and direction, and then by comparing the distances and relative orientations between each of four pairs of minutia neighbors in each of the four local quadrants, which represents how well each different [u,v] minutia pair match each other.Type: ApplicationFiled: April 24, 2001Publication date: November 14, 2002Applicant: LocKheed Martin CorporationInventors: Albert R. Sanders, James F. Curtis, Holger Findling
-
Publication number: 20020164087Abstract: Disclosed is a system and method for fast rotation of an original image having a skew angle. The image rotation system includes a PMP generation unit for generating PMPs with respect to bit patterns of a block, and a buffer for storing the PMPs. The system further includes an image division unit for dividing the original image to blocks, a bit pattern extraction unit for extracting the bit patterns for the blocks, a PMP address generation unit for calculating addresses of the buffer for storing the corresponding PMPs with respect to the bit patterns, and an output unit for fetching and outputting the PMPs from the addresses onto an output plane.Type: ApplicationFiled: February 28, 2002Publication date: November 7, 2002Inventors: Sung Chien, Yung Mok Baek, In Cheol Kim
-
Patent number: 6466340Abstract: An image reading apparatus includes: an image reading device for reading an image in a reading area including an inside and an outside of an original document area to obtain image data; a memory for storing the image data obtained by the image reading device; an edge detector for detecting a plurality of edges in the original document area according to the image data obtained by the image reading device; a calculator for calculating an inclination of an original document on the basis of the plurality of edges detected by the edge detector; and a correcting device for correcting the inclination of the original document on the basis of the inclination calculated by the calculator with respect to at least the image data in the original document area among the image data stored in the memory.Type: GrantFiled: February 25, 1999Date of Patent: October 15, 2002Assignee: Konica CorporationInventor: Koji Washio
-
Patent number: 6463184Abstract: A process for measuring the alignment of different layers on a semiconductor wafer (33) includes forming repetitive alignment marks (14, 24) having substantially the same period on the different layers on the wafer (33). The images of the overlay alignment marks (14, 24) are converted from space domain to frequency domain through Fourier transformations. The alignment measurements are performed by calculating the phase difference between the images corresponding to the repetitive patterns (14, 24) on different layers.Type: GrantFiled: June 17, 1999Date of Patent: October 8, 2002Assignee: International Business Machines CorporationInventors: Chris Gould, K. Paul Muller, V. C. Jai Prakash, Robert van den Berg
-
Patent number: 6449397Abstract: The present invention provides an image processing system for scanning a rectangular document. The system comprises a scanner with a scanning module and a computer. The computer has a memory, a processor, a scanner control program, and an image processing program. Depression of a start button generates a start signal that prompts the image processing system to rotate the document image from the scanned rectangular document by a tilting angle as well as to correct the image shape based on angle variation. This produces a straight and rectangular document image.Type: GrantFiled: April 5, 1999Date of Patent: September 10, 2002Assignee: Mustek Systems Inc.Inventor: Yang Che-Chu
-
Publication number: 20020113884Abstract: A warp corrector 201, which corrects warp in which the perspective is exaggerated when an image is captured with the user's face at close range, is included in a cellular phone 1 having an imaging portion 2. The warp corrector 201 performs processing to enlarge the peripheral areas of the image relative to the center, and generates corrected image data 232. As a result, a natural image of the user's face can be displayed on the display 11 of the cellular phone or sent.Type: ApplicationFiled: February 15, 2002Publication date: August 22, 2002Applicant: Minolta Co., Ltd.Inventors: Junichi Tanii, Minoru Kuwana
-
Patent number: 6433896Abstract: In an image processing apparatus, an image reading unit reads a document put on a platen glass to generate image data, and a detector in the image reading unit detects offset, tilt angle and document area of the document put on the platen glass. A rotation angle is set based on the image data of a document. The entire document area is determined based on a portion of the document which exists within the image reading area when the document extends beyond the image reading area. The document area can be detected even if a document is not rectangular. For example, a slope of the document is determined based on the detected longest segment. In order to solve the unequal reading pitch, the longest segment is selected in the segments having a slope smaller than a predetermined angle relative to the subscan direction. Then, the image data are corrected according to the above result.Type: GrantFiled: June 10, 1998Date of Patent: August 13, 2002Assignee: Minolta Co., Ltd.Inventors: Kazuhiro Ueda, Nobuhiro Mishima, Soh Hirota, Daisetsu Tohyama
-
Publication number: 20020106104Abstract: Certain forms of distortion make it difficult to recover hidden data embedded in an audio or image signal by quanitzation techniques. To compensate for this distortion, an embedded data reader analyzes a statistical distribution (e.g., a histogram) of feature samples in an audio or image signal suspected of having hidden auxiliary data to derive an estimate of quantizers used to encode a reference signal. The estimated quantizers then recover the reference signal, and the reader uses the reference signal to determine and compensate for geometric or temporal distortion, like spatial scaling and rotation of image data, and time scale and speed changes of audio data. After compensating for such distortion, the reader can then more accurately recover hidden message data using quantization techniques to extract the message. The reference signal is preferably repeated in blocks of the image or audio data to enable synchronization at many points in an image or audio data stream.Type: ApplicationFiled: June 28, 2001Publication date: August 8, 2002Inventors: Hugh L. Brunk, Ravi K. Sharma
-
Publication number: 20020106134Abstract: A method, system, and computer readable medium are disclosed for detecting and removing defects using images captured at multiple orientations. Defects in a physical medium in which an image is formed can hamper attempts to record representations of the original image. To lessen the effects of these physical defects on captured images, multiple images are captured using multiple different orientations of the physical medium in which the image is formed. The physical defects obscure different image information when viewed from different angles. By capturing images at multiple orientations and combining these images, almost all of the desired image information from the original image can be recovered, despite imperfections in the physical medium. The present invention finds application in image capturing devices, such as flatbed scanners, photocopiers, and the like.Type: ApplicationFiled: September 21, 2001Publication date: August 8, 2002Inventors: Thomas A. Dundon, Albert D. Edgar, Leland A. Lester
-
Patent number: 6430320Abstract: A system and method is described for automatically determining in a scanned document image the presence of unwanted extraneous information caused by an extraneous device and scanner background information. Once the presence of this information is determined, the system and method of the present invention can compute, for instance, skew and crop statistics. From this, the image can be automatically deskewed and cropped appropriately without the background and extraneous information. The system and method accomplishes this by first determining the presence of unwanted extraneous and background information and then appropriately processing the document image. The extraneous information is ignored during deskew and crop computations. Also, the scanner background and the extraneous information are prevented from being included in the final digital representation of the image.Type: GrantFiled: April 10, 2000Date of Patent: August 6, 2002Assignee: Hewlett-Packard CompanyInventors: Charles Chi Jia, Anne-Marie Woodson, Cindy Sansom-Wai, Daniel R Tretter
-
Publication number: 20020097904Abstract: A system is disclosed for determining the rotational orientation of an object. An image of the object is digitally captured. The digital image is filtered through an edge detection operation to enhance the edge information contained in the image. The filtered image is rotated through a series of incremental angles to produce a series of rotated images. Each rotated image is projected onto an x-axis and y-axis defined by pixel grid axes defined by the original image. The projection of the rotated images produces projected pixel counts formed by the summation of pixel value differences of the x-axis and y-axis on the projected image. For each rotated image, a score corresponding to the sum of the difference of gray-scale values for adjacent projected pixels is computed. The scores for the projections of each rotated image are plotted on a score-angle graph. A curve which includes the highest score and the neighboring next highest scores is interpolated to determine the peak score.Type: ApplicationFiled: October 26, 2001Publication date: July 25, 2002Applicant: ELECTROGLAS, INC.Inventor: Raymond G. White
-
Publication number: 20020090109Abstract: A hidden watermark and methods of detecting and embedding such watermark is provided. The watermark is resistant to efforts to avoid the message thereof.Type: ApplicationFiled: January 11, 2001Publication date: July 11, 2002Applicant: SONY CORPORATIONInventor: Peter David Wendt
-
Patent number: 6418244Abstract: Inventive two-dimensional barcodes, each having encoded digital information in a bitmap representing preferably randomized encoded data bits, are printed onto a printed medium. Preferably, error correction codes are added to the digital information to ensure that the decoding process accurately reproduce the digital information. In one embodiment, the bitmap may further include “anchor” bits in each corner, which are used as part of the skew estimation and deskewing processes during decoding. In a second embodiment, no “anchor” bits are required. The encoded digital information is mapped into the two-dimensional barcode in such a way as to minimize the errors caused by damage to particular rows and/or columns, for example, row damage caused by faxing the printed barcode. To extract the encoded digital information from the printed medium, the printed medium is scanned, then the bitmap is located within the printed medium.Type: GrantFiled: January 23, 2001Date of Patent: July 9, 2002Assignee: Matsushita Electric Industrial Co., Ltd.Inventors: Jiangying Zhou, Daniel P. Lopresti, Andrew Tomkins
-
Patent number: 6415064Abstract: A skew correction apparatus and method enhance transmission efficiency or recognition efficiency in facsimile transmissions or optical character recognition (OCR) by correcting the format of the copy which is input and read in a skewed manner. The skew is corrected in accordance with the following steps or functions: counting the number of pixels in a main-scanning direction until copy discriminating data are met, starting from two spots of the read data in a sub-scanning direction; sensing a skew direction of the copy using the counted number of pixels; reading skew correction data corresponding to a difference between the number of pixels of the two spots in the main-scanning direction; and correcting the skew by reading in the main-scanning direction the changed coordinates by line units with respect to all lines of the copy in the sub-scanning direction according to the skew correction data and skew direction.Type: GrantFiled: May 26, 1999Date of Patent: July 2, 2002Assignee: Samsung Electronics, Co., Ltd.Inventor: Hyang-Su Oh
-
Publication number: 20020051573Abstract: An image data is inputted by using a device such as a document scanner. The input image data is scanned in a square block unit of M×N pixels, and blocks that satisfy specific conditions is detected based on the scanning process. In one example, a ratio of white pixels and black pixels falls within scanned blocks is used as the specific condition to detect those blocks. Then a region that neighbored by the other blocks is detected, and is extracted as a two-dimensional code region.Type: ApplicationFiled: April 17, 2001Publication date: May 2, 2002Inventors: Kenichiro Sakai, Tsugio Noda
-
Patent number: 6373997Abstract: A processor measures skew of lines in an image by obtaining a first, coarse approximation to skew direction and then using the first approximation to obtain a second, fine approximation that is more precise than the first. A third, even more precise approximation can be obtained using the second approximation, and further successive approximations can be similarly obtained. In an image of text, the first approximation can be obtained by finding the direction in which characters are closest together, since intercharacter distances are typically smaller than interline distances. This direction can be determined by measuring distances from selected pixels at edges of connected components across white pixels to edges of other connected components. The measured distances in each direction can be combined to obtain a central value for the direction, such as an average. The central values form a profile indicating central value as a function of direction.Type: GrantFiled: March 29, 1993Date of Patent: April 16, 2002Assignee: Xerox CorporationInventors: Peter C. Wayner, Daniel P. Huttenlocher, Michael J. Hopcroft, Todd A. Cass
-
Patent number: 6373590Abstract: An image processor (14) in a photocopier (10) takes composite input image (20a) that includes a plurality of skewed sub-images (22a, 24a, and 26a). It revises the image so as to produce an output composite image (20b) containing aligned sub-images (22b, 24b, and 26b). To identify the input image's sub-images, the image processor (14) identifies connected groups (44, 48 and 54) of pixels that meet certain criteria, and it eliminates from consideration each group (48) whose bounding box (50) is included within the bounding box (46) of another connected group (44). Skew angles for the different sub-images are determined by finding the best-fit lines through the outline pixels of their respective connected groups, and the sub-images are de-skewed by the negatives of those lines' angles.Type: GrantFiled: February 4, 1999Date of Patent: April 16, 2002Assignee: Seiko Epson CorporationInventors: Hakan Ancin, Sean Miceli, Sean Gugler, Anoop Bhattacharjya
-
Patent number: 6360026Abstract: Determining a skew angle of a bitmap image comprising of background and image pixels and de-skewing the bitmap image by the determined skew angle. The bitmap image skew angle is determined by calculating plural estimates of the skew angle with corresponding reliability indicators and thereafter selecting the estimate skew angle with the best reliability indicator as the bitmap image skew angle and then de-skew the bitmap image by the determined skew angle. Thereafter, auto-cropping the de-skewed image around a rectangle defined by a first and last column and first and last row of pixels which are not all white.Type: GrantFiled: March 10, 1998Date of Patent: March 19, 2002Assignee: Canon Kabushiki KaishaInventors: Manish Kulkarni, Timothy L. Kohler
-
Publication number: 20020031264Abstract: A document image tilt detection unit extracts a set of elements forming a character from a document image, extracts candidates for horizontal and vertical lines based on the character elements, estimates the reliability of each candidate for a line, and extracts a set of probable lines. Then, it estimates the tilt of the document image based on the arrangement of the character elements belonging to the line elements in the set of probable lines. A layout analysis unit extracts a set of lines in a fixed line direction from a set of basic elements forming the document image, and reciprocally performs the extraction of a column based on the correlation between lines and the extraction of a line based on the restrictions of the column. By providing the document image tilt detection unit and the layout analysis unit, the tilt of the document image containing both vertical and horizontal character lines can be detected, and lines and columns can be extracted at a high speed with high precision.Type: ApplicationFiled: September 4, 2001Publication date: March 14, 2002Applicant: Fujitsu LimitedInventors: Katsuhito Fujimoto, Hiroshi Kamada, Koji Kurokawa
-
Publication number: 20020028004Abstract: The invention aims at providing personal identification in environments where non-contact is required, with high accuracy even though using a finger vein pattern images unclear and susceptible to positional deviations, wherein it has: a means for acquiring finger vein patterns without contact; a means for carrying out rotational correction using the outline of a finger as a method of taking out a vein pattern contained in the acquired image; a means for normalizing the position of the finger image with reference to the fingertip; a means for acquiring an overall vein pattern statistically by repetitively tracking regions of dark luminance intensities for a desired length from a desired position in the image; a matching means for comparing regions where vein patterns manifest vivid features; and a means for independent matching of subregions and evaluating positional deviations where matching is recognized.Type: ApplicationFiled: September 5, 2001Publication date: March 7, 2002Inventors: Naoto Miura, Akio Nagasaka, Takafumi Miyatake
-
Publication number: 20020028027Abstract: A Hough transform unit executes Hough transform to HIGH pixels of outline binary image data inputted thereto, and stores the calculation result in a Hough space data storage. A Hough space data calculating/projecting unit sequentially reads out data stored in the Hough space data storage, executes a specific calculation, and thereafter stores the calculation result sequentially in a calculated projection data storage. An angle detector sequentially reads out calculated frequency data stored in the calculated projection data storage, calculates the maximal value of the data read out, and detects an angle that gives the maximal value as the skew angle. The image processing device, being thus configured, allows detecting and correcting the skew angle with high accuracy, even when the input image contains image elements such as photograph images and dot images.Type: ApplicationFiled: September 5, 2001Publication date: March 7, 2002Applicant: Fuji Xerox Co., Ltd.Inventor: Toshiya Koyama
-
Publication number: 20020025081Abstract: A document image processing device can correct the location of a document of an arbitrary format. The reference position of a document image is designated previously by a reference position designation unit. The document image is input per page and stored. A predetermined pixel block extraction unit extracts the predetermined pixel block appearing commonly on each page, and the coordinate value of the predetermined pixel block is supplied to a difference extraction unit. The difference extraction unit calculates the difference value between the position of the extracted predetermined pixel block and the reference position designated by the reference position designation unit, and supplies the difference value to an image shifting unit. The image shifting unit shifts the document image of that page based on the difference value, and corrects the location of the document image. The predetermined pixel block used for position correction can be set arbitrarily.Type: ApplicationFiled: July 31, 2001Publication date: February 28, 2002Inventor: Yukio Kumazawa
-
Publication number: 20020020747Abstract: A two-dimensional bar code reading method and apparatus search the finder pattern in a scanned image of a two-dimensional bar code symbol, find orientation modules, find data modules, and convert the symbol to data characters as part of the decoding process for the scanned image of a MaxiCode symbol. In the data module search part of a MaxiCode symbol decoding process, position and shape information is calculated for data modules on an orientation axis, assuming an orientation axis passing the finder pattern center point, inside orientation module center point, and outside orientation module center point (step to S1801). Based on pixel data corresponding to the calculated location of the center point in each module, a bit pattern is generated where black data cells are 1 bits and white cells are 0 bits (S1802). The locations of MaxiCode symbol data modules in the area between orientation axes are then calculated (S1803).Type: ApplicationFiled: April 6, 2001Publication date: February 21, 2002Inventors: Hitomi Wakamiya, Shinichi Arazaki, Fumio Koyama, Satoshi Yanagida, Haruyoshi Ohori
-
Publication number: 20020018582Abstract: Encoders as first detecting means detect rotations of a control body, and an acceleration sensor as second detecting means detects an acceleration applied to the control body. Based on the rotations and the acceleration, a ball displayed on a screen can be curved in the air. Consequently, an operator of a game can control the ball displayed on the screen or the like by controlling an impact, that is, an acceleration, a rotational direction, and a rotational speed.Type: ApplicationFiled: August 3, 2001Publication date: February 14, 2002Applicant: Alps Electric Co., LtdInventors: Yasuji Hagiwara, Youtaro Sakakura, Kazuhito Ooshita, Isao Sato, Masahiro Soma, Hiroshi Nakahama
-
Publication number: 20020006233Abstract: An image collation apparatus includes a collation unit, minimum coincidence ratio extraction unit, and determination unit. The collation unit obtains a coincidence ratio between first and second images within a printing element range for each collation unit by collating the first and second images with each other. The minimum coincidence ratio extraction unit obtains a minimum coincidence ratio from coincidence ratios obtained from the collation unit. The determination unit determines that the first and second images are identical, if the extracted minimum coincidence ratio is smaller than a predetermined threshold. An image collation method is also disclosed.Type: ApplicationFiled: June 6, 2001Publication date: January 17, 2002Inventors: Takuya Adachi, Satoshi Shigematsu, Takahiro Hatano, Mamoru Nakanishi, Katsuyuki Machida
-
Patent number: 6333997Abstract: A parameter input section inputs, as parameters, the luminance difference between a to-be-recognized object P and its background, conveyance conditions, etc. An endpoint detecting section uses the parameters to detect a plurality of border points between the object P and the background, without being influenced by external noise or a stain on the object P. A length detecting section detects vertical and horizontal lengths of the object P, and an entire-object position determining section determines the position of the entire object P using the lengths detected by the section. A recognizing section compares an image input by an image input section, with reference image data stored in a reference image data memory, thereby recognizing the object P.Type: GrantFiled: June 8, 1999Date of Patent: December 25, 2001Assignee: Kabushiki Kaisha ToshibaInventors: Kazuyo Hashiya, Osamu Kuratomi
-
Patent number: 6332046Abstract: A document image tilt detection unit extracts a set of elements forming a character from a document image, extracts candidates for horizontal and vertical lines based on the character elements, estimates the reliability of each candidate for a line, and extracts a set of probable lines. Then, it estimates the tilt of the document image based on the arrangement of the character elements belonging to the line elements in the set of probable lines. A layout analysis unit extracts a set of lines in a fixed line direction from a set of basic elements forming the document image, and reciprocally performs the extraction of a column based on the correlation between lines and the extraction of a line based on the restrictions of the column. By providing the document image tilt detection unit and the layout analysis unit, the tilt of the document image containing both vertical and horizontal character lines can be detected, and lines and columns can be extracted at a high speed with high precision.Type: GrantFiled: November 18, 1998Date of Patent: December 18, 2001Assignee: Fujitsu LimitedInventors: Katsuhito Fujimoto, Hiroshi Kamada, Koji Kurokawa