Patents Examined by Bhavesh M. Mehta
  • Patent number: 10140529
    Abstract: A method for detecting a lane line is provided. The method includes: determining candidate lane line regions in a lane image by filtering the lane image; extracting center points for each candidate lane line region; obtaining a fitting curve of each candidate lane line region by performing curve fitting on the center points of each candidate lane line region; classifying the candidate lane line regions as rectilinear and curvilinear candidate lane line regions according to a slope angle of the fitting curve of each candidate lane line region; dividing the candidate lane line regions into groups based on the classifying result; and determining two groups, which meet a first predetermined condition, as target groups, and recognizing candidate lane line regions in the target groups as lane line regions. Besides, an apparatus and a device for detecting a lane line are further provided.
    Type: Grant
    Filed: November 25, 2016
    Date of Patent: November 27, 2018
    Assignees: NEUSOFT CORPORATION, TECHNOLOGY (SHANGHAI) CO., LTD.
    Inventors: Wenjing Bai, Yingfang Du, Wei Liu, Huai Yuan
  • Patent number: 10108879
    Abstract: The present disclosure includes techniques for selecting a candidate presentation style for individual documents for inclusion in an aggregate training data set for a document type that may be used to train an OCR processing engine prior to identifying text in an image of a document of the document type. In one embodiment, text input corresponding to a text sample in a document is received, and an image of the text sample in the document is received. For each of a plurality of candidate presentation styles, an OCR processing engine is trained using a training data set corresponding to the given candidate presentation style, and the OCR processing engine is used, as trained, to identify text in the received image. The OCR processing results for each candidate presentation style are compared to the received text input. A candidate presentation style for the document is selected based on the comparisons.
    Type: Grant
    Filed: September 21, 2016
    Date of Patent: October 23, 2018
    Assignee: Intuit inc.
    Inventors: Eugene Krivopaltsev, Sreeneel K. Maddika, Vijay S. Yellapragada
  • Patent number: 9342674
    Abstract: This application relates to devices, methods and computer readable media that allow users using a first device to be easily authenticated. For example, while the first device is proximate to a second device, the first device requests user authentication using the one or more biometric sensors. After requesting the user authentication, the first device detects biometric information associated with the user with the one or more biometric sensors. In response to detecting the biometric information associated with the user, in accordance with a determination that the detected biometric information associated with the user meets authentication criteria, the first device provides credentials associated with the user to the second device. In accordance with a determination that the detected biometric information associated with the user does not meet the authentication criteria, the first device forgoes providing the credentials associated with the user to the second device.
    Type: Grant
    Filed: March 5, 2015
    Date of Patent: May 17, 2016
    Assignee: APPLE INC.
    Inventors: David S. Abdallah, Barry W. Johnson
  • Patent number: 8649633
    Abstract: An image registration system includes a memory storing digital data representing a first image and a second image, an image processing unit configured to register the second image onto a coordinate system of the first image to obtain a registered second image, and a user interface device adapted to display one of the first image or the registered second image, and a movable region having a periphery. The user interface is adapted to display the first image or the registered second image within the periphery and the other image outside the periphery. The image processing unit is adapted to determine a similarity in alignment of a feature of the registered image with a corresponding feature of the first image, and the user interface is adapted to provide a visual indication to indicate the similarity of the alignment.
    Type: Grant
    Filed: December 3, 2010
    Date of Patent: February 11, 2014
    Assignee: Siemens Aktiengesellschaft
    Inventors: Palanisamy Onankuttai Subbian, Manivannan Sundarapandian
  • Patent number: 8644597
    Abstract: Methods and apparatus are provided for generating 3D image files based on 2D image media standards. First and second image data are photographed, pre-processed, and stored. The first and second image data are encoded. A 3D image file is generated. The 3D image file includes a first area having the first and second image data synchronized with the first image data so as to be used for generating a 3D image, a second area including at least information on a number of frames and a size of each frame for the first image data, and a third area, separate from the second area, having information on a number of frames and a size of each frame for the second image data. Information stored in third area is for regenerating the 3D image and not for regenerating a 2D image.
    Type: Grant
    Filed: June 4, 2013
    Date of Patent: February 4, 2014
    Assignee: Samsung Electronics Co., Ltd
    Inventors: Gun-Ill Lee, Kwang-Cheol Choi, Jae-Yeon Song
  • Patent number: 8457439
    Abstract: A system and method of the present disclosure provides a region based error diffusion algorithm or function for reducing artifacts in images. The system and method utilizes knowledge of a region of interest (ROI) in an image and applies effects like dithering or error diffusion to the area or region that shows the artifacts, e.g., a banding phenomenon. The system and method provide for defining a region in at least one first image, the defined region having at least one artifact, tracking the defined region to at least one second image, and applying an error diffusion function to the defined region to mask the at least one artifact in the at least one first and second images.
    Type: Grant
    Filed: June 19, 2007
    Date of Patent: June 4, 2013
    Assignee: Thomson Licensing
    Inventors: Xueming Henry Gu, Ju Guo
  • Patent number: 8401231
    Abstract: Provided herein are systems and methods for outdoor lighting, which generally include two or more light sources. One light source is a monochromatic light source producing a light with a peak wavelength of about 580 nm or above. A second light source is a polychromatic light source producing a green-tint white light. During a standby operational mode, a control system maintains the first light source illuminated. The control system, which includes an integrated imaging system, illuminates both the first light source and the second light source when the imaging system identifies a target in an illumination area. Methods of preparing and using such outdoor lighting system are also provided.
    Type: Grant
    Filed: November 9, 2010
    Date of Patent: March 19, 2013
    Assignee: Biological Illumination, LLC
    Inventors: Fredric S. Maxik, David E. Bartine, Robert R. Soler, Valerie Ann Bastien, James Lynn Schellack, Eliza Katar Grove
  • Patent number: 8254695
    Abstract: Disclosed is a method for determining the absence or presence of one or more instances of a predetermined pattern in an image, and for determining the location of each found instance within a multidimensional space. A model represents the pattern to be found, the model including a plurality of probes. Each probe represents a relative position at which a test is performed in an image at a given pose, each such test contributing evidence that the pattern exists at the pose. The method further includes a comparison of the model with a run-time image at each of a plurality of poses. A match score is computed at each pose to provide a match score surface. Then, the match score is compared with an accept threshold, and used to provide the location any instances of the pattern in the image.
    Type: Grant
    Filed: December 31, 2004
    Date of Patent: August 28, 2012
    Assignee: Cognex Corporation
    Inventors: William M. Silver, E. John McGarry, Sanjay Nichani, Adam Wagman
  • Patent number: 8121340
    Abstract: A method is provided for decoding an encoded point matrix image including a first set of real grid points aligned along a first axis, a second set of real grid points aligned along a second axis intersecting the first axis, and a plurality of encoded data points distributed throughout the encoded point matrix image. The method includes: locating the first and second axes according to a first predetermined principle; finding a set of virtual grid points according to a second predetermined principle, each of the virtual grid points being located at an intersection of a corresponding first virtual line parallel to the first axis and a corresponding second virtual line parallel to the second axis; and decoding each of the encoded data points based on positional relation thereof with a closest one of the virtual grid points so as to obtain information encoded in the encoded point matrix image.
    Type: Grant
    Filed: February 7, 2007
    Date of Patent: February 21, 2012
    Assignee: PixArt Imaging Inc.
    Inventors: Shou-Der Wei, Hsin-Chia Chen, Tzu-Yi Chao
  • Patent number: 8116589
    Abstract: An image processing apparatus includes a partial image memory unit for reading partial image data from an image pickup device and sequentially storing the partial image data, and an image composition unit for generating the composite image data by synthesizing the partial image data from the partial image memory unit. Only when a composition incomplete signal does not exist, the partial image memory unit stores the partial image data and generates a storage completion signal upon completing storage of the partial image data. The image composition unit generates the composition incomplete signal when the composite image data is generated, on condition that the storage completion signal is present. The image composition unit reads at least one of the partial image data from the partial image memory unit and starts the generation of the composite image data using the partial image data when the composite image data is not generated.
    Type: Grant
    Filed: June 20, 2008
    Date of Patent: February 14, 2012
    Inventor: Hideki Kamegawa
  • Patent number: 8081820
    Abstract: A method is provided for dividing a pattern into a plurality of sub-patterns, each sub-pattern being adapted for use with an image search method that can provide a plurality of sub-pattern search results. The method represents the pattern as a plurality of feature points, generates candidate partitions of the plurality of feature points, and then scores the candidate partitions by examining characteristics of each potential sub-pattern of each candidate partition. The highest-scoring partition is selected, and then it is applied to the plurality of feature points, creating one or more sub-pluralities of features. The invention advantageously provides a plurality of sub-patterns where each sub-pattern contains enough information to be located with a feature-based search method, where that information has been pre-evaluated as being useful and particularly adapted for running feature-based searches.
    Type: Grant
    Filed: July 22, 2003
    Date of Patent: December 20, 2011
    Assignee: Cognex Technology and Investment Corporation
    Inventors: Jason Davis, Juha Koljonen
  • Patent number: 8023769
    Abstract: An apparatus and method for selectively outputting image frames are provided. The apparatus includes a main topic frame extractor which extracts a main topic frame, which expresses a main topic selected by a user, from continuous image frames; a composite image frame creator which extracts a key object to realize the main topic from the main topic frames, and estimates a background object with respect to the key object to create a composite image frame using the key object and the background object; a wide-angle image frame creator which creates a wide-angle image frame, which includes the composite image frame and an image frame having common information to the composite image frame, among the continuous image frames; an attractive region setting unit which sets an attractive region with respect to the wide-angle image frame; and an output unit which outputs the attractive region.
    Type: Grant
    Filed: March 7, 2007
    Date of Patent: September 20, 2011
    Assignee: Samsung Electronics Co., Ltd.
    Inventors: You-sun Bang, Yun-tae Kim, Heui-keun Choh
  • Patent number: 8005304
    Abstract: An E8-VSB reception system, apparatus for generating data attribute and method thereof, and apparatus for channel encoding and method thereof are disclosed. In the present invention, E8-VSB data resulting from multiplexing a plurality of enhanced data encoded at different coding rates with main data is received. And, the main data and a plurality of the enhanced data are identified to be modulated from the received E8-VSB data. In particular, by generating M/E packet attribute information, enhanced packet attribute information, enhanced byte attribute information and E8-VSB symbol attribute information from the E8-VSB data attribute generating apparatus, the channel decoding apparatus can correctly identify to decode the main data, ½ enhanced data and ¼ enhanced data from one another.
    Type: Grant
    Filed: October 11, 2010
    Date of Patent: August 23, 2011
    Assignee: LG Electronics Inc.
    Inventors: In Hwan Choi, Kyung Won Kang
  • Patent number: 8005317
    Abstract: When an original image in which an object to be concealed is mosaicked is so reduced as to have a low resolution, the mosaic block size at the lowered resolution is computed. It is judged whether or not the concealed object can be perceived by the eye of a human even though the object is mosaicked with the reduced mosaic block size. If so, the concealed object is re-mosaicked with an adequate re-mosaic block size. With this, even for a reduced image reduced by lowering the resolution of the original image in which the object to be concealed is mosaicked, the privacy of the concealed object can be protected.
    Type: Grant
    Filed: January 30, 2006
    Date of Patent: August 23, 2011
    Assignee: NEC Corporation
    Inventor: Keiichi Chono
  • Patent number: 8000555
    Abstract: A method for detecting a defective image of the present invention includes obtaining an edge image by performing an edge tracking process on an original image, detecting an isolation point whose size is equal to or smaller than a predetermined size from a processed image obtained by performing an erosion process after an expansion process on the edge image, and detecting a defective image in the original image based on the isolation point.
    Type: Grant
    Filed: May 15, 2007
    Date of Patent: August 16, 2011
    Assignee: Seiko Epson Corporation
    Inventors: Keiji Hirose, Kon Ko
  • Patent number: 8000542
    Abstract: An apparatus for processing a non-interlaced image includes a wavelet transform part and a determination part. The wavelet transform part performs two-dimensional discrete wavelet transform of a level higher than or equal to level one on the data of the non-interlaced image. The determination part determines the movement speed of an object within the non-interlaced image based on at least the values of the wavelet coefficients of a 1LH sub-band of the wavelet coefficients obtained by the wavelet transform unit.
    Type: Grant
    Filed: September 19, 2008
    Date of Patent: August 16, 2011
    Assignee: Ricoh Company, Ltd.
    Inventors: Hiroyuki Sakuyama, Tooru Suino
  • Patent number: 8000494
    Abstract: A digital watermark detecting device includes an extracting unit to extract pixels embedded as a digital watermark from an input image and to output an extracted pixel value row, a generating unit to generate a set of orthogonal patterns, a detecting unit to calculate a correlation using an integration result of the orthogonal patterns and the extracted pixel value row, to determine detected values corresponding to the orthogonal patterns and a standard deviation for detected values excluding a maximum detected value with a maximum absolute value from the calculated detected values, to calculate a quotient by dividing the maximum detected value by the standard deviation, a discriminating unit to output information corresponding to the result of comparison between a threshold parameter and the quotient, and a unit to convert the detected value inputted from the detecting unit into predetermined information, when the reliability of the detected values satisfies a standard.
    Type: Grant
    Filed: September 27, 2006
    Date of Patent: August 16, 2011
    Assignee: Mitsubishi Electric Corporation
    Inventors: Koichi Magai, Hiroshi Ito, Ryousuke Fujii, Mitsuyoshi Suzuki, Kohtaro Asai, Tokumichi Murakami
  • Patent number: 8000514
    Abstract: The present invention relates to automated document processing and more particularly, to methods and systems for document image capture and processing using mobile devices. In accordance with various embodiments, methods and systems for document image capture on a mobile communication device are provided such that the image is optimized and enhanced for data extraction from the document as depicted. These methods and systems may comprise capturing an image of a document using a mobile communication device; transmitting the image to a server; and processing the image to create a bi-tonal image of the document for data extraction. Additionally, these methods and systems may comprise capturing a first image of a document using the mobile communication device; automatically detecting the document within the image; geometrically correcting the image; binarizing the image; correcting the orientation of the image; correcting the size of the image; and outputting the resulting image of the document.
    Type: Grant
    Filed: December 30, 2008
    Date of Patent: August 16, 2011
    Assignee: Mitek Systems, Inc.
    Inventors: Grigori Nepomniachtchi, James DeBello
  • Patent number: 7995861
    Abstract: The present disclosure includes systems and techniques relating to selecting a reference image for images to be joined in accordance with projective transformations.
    Type: Grant
    Filed: December 13, 2006
    Date of Patent: August 9, 2011
    Assignee: Adobe Systems Incorporated
    Inventors: Hailin Jin, Jen-Chan Chien
  • Patent number: 7995864
    Abstract: A method for performing image registration is provided. The method comprises obtaining a reference image dataset and a target image dataset and defining an image mask for a region of interest in the reference image dataset. The method further comprises registering a corresponding region of interest in the target image dataset with the image mask, using a similarity metric, wherein the similarity metric is computed based on one or more voxels in the region of interest defined by the image mask.
    Type: Grant
    Filed: July 3, 2007
    Date of Patent: August 9, 2011
    Assignee: General Electric Company
    Inventors: Rakesh Mullick, Sohan Rashmi Ranjan