Raising Or Lowering The Image Resolution (e.g., Subpixel Accuracy) Patents (Class 382/299)
-
Patent number: 8965112Abstract: Systems and methods for sequence transcription with neural networks are provided. More particularly, a neural network can be implemented to map a plurality of training images received by the neural network into a probabilistic model of sequences comprising P(S|X) by maximizing log P(S|X) on the plurality of training images. X represents an input image and S represents an output sequence of characters for the input image. The trained neural network can process a received image containing characters associated with building numbers. The trained neural network can generate a predicted sequence of characters by processing the received image.Type: GrantFiled: December 17, 2013Date of Patent: February 24, 2015Assignee: Google Inc.Inventors: Julian Ibarz, Yaroslav Bulatov, Ian Goodfellow
-
Patent number: 8958661Abstract: Methods and apparatus to generate templates from web images for searching an image database are described. In one embodiment, one or more retrieved images (e.g., from the Web) may be used to generate one or more templates. The templates may be used to search an image database based on features commonly shared between sub-images of the retrieved images. Other embodiments are also described.Type: GrantFiled: March 30, 2007Date of Patent: February 17, 2015Assignee: Intel CorporationInventors: Navneet Panda, Yi Wu, Jean-Yves Bouguet, Ara Nefian
-
Publication number: 20150043836Abstract: An image processing method includes: storing a threshold matrix for quantization processing of input image data, applying mask processing to an abnormal recording element based on abnormal recording element information, correcting a correspondence relationship between a recording element and a threshold such that processing of a pixel to be formed by the abnormal recording element subjected to mask processing is excluded and the continuity of a pattern of the threshold matrix is maintained, and performing quantization processing using a corrected threshold matrix.Type: ApplicationFiled: October 22, 2014Publication date: February 12, 2015Applicant: FUJIFILM CORPORATIONInventor: Hiroyuki SHIBATA
-
Publication number: 20150042717Abstract: An image processing method includes: applying mask processing to an abnormal recording element based on abnormal recording element information; converting input image data such that a pixel to be formed by the abnormal recording element is excluded; applying quantization processing that converts the converted input image data to image data having a gradation number less than a gradation number of the converted input image data; and assigning each pixel forming image data after quantization processing to a normal recording element.Type: ApplicationFiled: October 22, 2014Publication date: February 12, 2015Applicant: FUJIFILM CORPORATIONInventor: Hiroyuki SHIBATA
-
Patent number: 8948537Abstract: Methods and apparatus according to various aspects take as input image data in a lower-dynamic-range (LDR) format and produce as output enhanced image data having a dynamic range greater than that of the input image data (i.e. higher-dynamic range (HDR) image data). In some embodiments, the methods are applied to video data and are performed in real-time (i.e. processing of video frames to enhance the dynamic range of the video frames is completed at least on average at the frame rate of the video signal).Type: GrantFiled: February 20, 2014Date of Patent: February 3, 2015Assignee: Dolby Laboratories Licensing CorporationInventors: Allan G. Rempel, Wolfgang Heidrich, Helge Seetzen, Gregory John Ward, Lorne A. Whitehead
-
Patent number: 8942491Abstract: A binary image downsampling method, including the steps of generating a gray-scale image from a binary image having a background and one or more foreground portions, locating skeleton pixels in the one or more foreground portions, manipulating values of certain foreground pixels in the gray-scale image such that the differences between the values of the skeleton pixels and the background pixels become more significant, downsampling the gray-scale image with the manipulated values of the certain foreground pixels, and generating a downsampled binary image from the downsampled gray-scale image.Type: GrantFiled: November 29, 2012Date of Patent: January 27, 2015Assignee: Konica Minolta Laboratory U.S.A., Inc.Inventor: Yibin Tian
-
Patent number: 8938130Abstract: A method for the alignment of pairs of complex images of a region, such as may be produced by separate passes of a synthetic aperture radar, is disclosed. The method selects a subset of each image in the form of a plurality of tiles, and calculates a correlation value between corresponding pairs of tiles. Shifts in x and y for each pair where the correlation value exceeds a threshold are then used to calculate values for overall shift, stretch and shear to be applied to one of the images to align it with the other. An iterative least squares approach may be used. As both phase and amplitude information is used in the correlation the technique is suitable for aligning images having little intensity variation. The invention may be used to align images prior to coherent change detection analysis of the images.Type: GrantFiled: July 25, 2011Date of Patent: January 20, 2015Assignee: Qinetiq LimitedInventors: Christopher Paul Moate, Keith Derek Copsey
-
Publication number: 20150016748Abstract: Image processing apparatus, an image processing system, and an image processing method. The image processing apparatus includes: an input image processing unit for outputting global information of sample data obtained by sampling first image data and dividing and outputting the first image data into an N (where N is a positive integer equal to or greater than 2) number of split image data; and a frame rate conversion unit including an N number of frame rate converters, wherein each of the N number of frame rate converters converts a frame rate of corresponding split image data among the N number of split image data synchronized with the global information and outputs the frame rate converted split image data as split display data, wherein the split display data is to be displayed on one of an N number of display regions.Type: ApplicationFiled: June 17, 2014Publication date: January 15, 2015Inventors: Yoon-ho KO, Hwa-hyun CHO, Jong-seon KIM, Seung-joon LEE
-
Patent number: 8934737Abstract: A system and method to process an image file from an image source before storage on a physical storage medium. The image file can include an image data and an identifier data of a person. The system can comprise a receiver connected in communication to receive the image file from the image source. The receiver can be configured to de-identify the identifier data from each part of the image file as presented to the receiver prior to being subsequently stored on the physical storage medium.Type: GrantFiled: October 10, 2012Date of Patent: January 13, 2015Assignee: General Electric CompanyInventor: Jeffrey Dale Solliday-McRoy
-
Image processing apparatus and method for synthesizing a high-resolution image and a refocused image
Patent number: 8929677Abstract: An image processing apparatus and image processing method capable of providing a high-resolution image for a desired position by use of light field data are provided. The image processing apparatus may determine a position of a portion of light field data among light field data corresponding to a scene, according to a desired focusing position, generate a refocusing first image by use of the position determined portion of light field data, generate a high-resolution image having a predetermined setting ratio relative to the refocusing first image, determine a ratio for local synthesis between the high-resolution image and an enlarged image of the refocusing first image by use of a similarity with respect to the position determined portion of light field data, and generate a synthesized image by synthesizing the high-resolution image and the enlarged image of the refocusing first image according to the local synthesis ratio.Type: GrantFiled: November 29, 2010Date of Patent: January 6, 2015Assignee: Samsung Electronics Co., Ltd.Inventors: Jae-Guyn Lim, Joo-Young Kang, Byung-Kwan Park, Seong-Deok Lee, Won-Hee Choe -
Patent number: 8929594Abstract: An image processing apparatus comprising a storage unit configured to store image data; a readout unit configured to read out the image data stored in the storage unit; a detection unit configured to detect a target object from the image data read out by the readout unit; a conversion unit configured to convert a resolution of the image data read out by the readout unit; and a write unit configured to write the image data having the resolution converted by the conversion unit in the storage unit, wherein the readout unit outputs the readout image data in parallel to the detection unit and the conversion unit.Type: GrantFiled: April 13, 2012Date of Patent: January 6, 2015Assignee: Canon Kabushiki KaishaInventor: Kinya Osa
-
Patent number: 8929670Abstract: Provided is an image processing apparatus including: a prediction portion to perform an inter-magnification-ratio blur-compensation prediction with respect to a reduced-size reference focus face image, to thereby generate an inter-magnification-ratio blur-compensation predicted image at each of a plurality of focus positions, the reduced-size reference focus face image being obtained by reducing a size of a reference focus face image to be a reference of a plurality of focus face images obtained by imaging a subject at the plurality of focus positions; a differential data generation portion to generate, for each of the plurality of focus positions, differential data between the focus face image and the inter-magnification-ratio blur-compensation predicted image generated by the prediction portion; and an encoding portion to encode the reduced-size reference focus face image and the differential data generated by the differential data generation portion.Type: GrantFiled: December 2, 2010Date of Patent: January 6, 2015Assignee: Sony CorporationInventors: Takeshi Uemori, Ohji Nakagami, Takuya Kitamura, Yoichi Yagasaki
-
Patent number: 8923653Abstract: Super-resolution processing is regarded as a kind of intersample interpolation process and performed by using a linear interpolation filter designed according to sampled-data control theory. In an error-system model used in the process of designing the filter, a pre-filter is disposed before a sampler and a post-filter is disposed after the zero-order hold in a signal restoration system. At least either one of the characteristic Q(s) of the pre-filter or the characteristic P(s) of the post-filter is designed to be a low-pass characteristic, whereby the gain of the characteristic K(z) of a digital filter within a middle-to-high frequency range is raised. Raising the gain makes jaggies more prominent. To reduce this effect, in an actual processing system, the image to be processed is passed through a low-pass filter to reduce high-frequency components before the linear interpolation is performed.Type: GrantFiled: February 3, 2012Date of Patent: December 30, 2014Inventors: Yutaka Yamamoto, Kengo Zenitani
-
Patent number: 8917956Abstract: A method of enhancing spatial resolution of an image. An image is accessed. The image comprises a set of confident pixels and an unconfident pixel positioned adjacent to each confident pixel of the set of confident pixels. The set of confident pixels comprises four or fewer pixels and corresponds to a plurality of known depth values, the unconfident pixel comprises an unknown depth value. A best depth hypothesis for the unconfident pixel is determined using a filter module in which the plurality of known depth values are used as depth hypotheses. The unconfident pixel is updated as a confident pixel using the best depth hypothesis.Type: GrantFiled: August 12, 2009Date of Patent: December 23, 2014Assignee: Hewlett-Packard Development Company, L.P.Inventors: Qingxiong Yang, Kar-Han Tan
-
Patent number: 8917354Abstract: A method for detecting motion in video fields of video data, comprises the steps of: calculating texture information for a pixel in the video fields; determining a threshold value as a function of the calculated texture information; calculating a differential value for the pixel; and detecting motion in the video fields as a function of the determined threshold value and the calculated differential value.Type: GrantFiled: September 30, 2013Date of Patent: December 23, 2014Assignee: Amlogic Co., Ltd.Inventors: Dongjian Wang, Xin Hu, Xuyun Chen
-
Patent number: 8913149Abstract: Disclosed are systems and methods for synthesizing a high resolution image associated with a large imaging aperture using an optical imaging apparatus having a smaller aperture. In certain implementations, introduction of a coherent homodyne reference beam to a coherent imaging of an object can result in formation of a Fourier space side lobe that includes information about a portion of a spectrum representative of the object's Fourier spectrum. Images can be obtained at a number of different orientations to yield a number of such side lobe images so as to allow construction of the object's spectrum. A synthesized image corresponding to such a constructed spectrum can have an improved resolution that exceeds the performance limit imposed by the aperture of the optical imaging apparatus.Type: GrantFiled: November 30, 2011Date of Patent: December 16, 2014Assignee: Integrity Applications IncorporatedInventor: James A. Georges, III
-
Patent number: 8907974Abstract: When a single pixel is displayed by four color sub-pixels, or R (red), G (green), B (blue), and G, in a Bayer array, this invention sets the scaling rate of a scaling process to 3/2 times when executing the scaling process on image data having three color components, or R, G, and B, and then executes a color conversion process for finding four color components from the three color components; after this, a decimation process for reducing the number of pixels is carried out. Setting the scaling rate of the scaling process to an integer proportion, moirés caused by the scaling process can be made less noticeable. Note that it is desirable for the scaling rate of the scaling process to be close to ?2 and for the denominator of the integer proportion to be lower.Type: GrantFiled: October 3, 2012Date of Patent: December 9, 2014Assignee: Seiko Epson CorporationInventor: Hiroshi Yoshimoto
-
Patent number: 8903195Abstract: An image processing system produces highly accurate determination of a local area that does not conform to an assumed change. Positional displacement amount calculation element 91 calculates a positional displacement amount between a target image and a reference image. Pixel operation element 95 relates a pixel in the target image to a pixel in the reference image by specifying the pixel in the reference image nearest a position of the pixel in the target image when the target image is corrected so as to resolve the positional displacement, calculates a relative pixel differential vector which is a differential vector of respective vectors of the relative pixels, and determines whether or not the pixel in the target image is a pixel of the local area, based on the relative pixel differential vector and an ellipsoid in a predetermined space, the ellipsoid relating to the pixel in the reference image.Type: GrantFiled: February 19, 2010Date of Patent: December 2, 2014Assignee: NEC CorporationInventor: Takashi Shibata
-
Publication number: 20140348425Abstract: An apparatus comprising one or more processors configured to process a first image at a first resolution to generate a first solved image at the first resolution, determine a difference between the first solved image and a function of the first image, and generate a second solved image at a second resolution higher than the first resolution based at least in part on the difference between the first solved image and the function of the first image.Type: ApplicationFiled: May 23, 2014Publication date: November 27, 2014Applicant: Futurewei Technologies, Inc.Inventors: Jun Tian, Wenjun Zeng
-
Patent number: 8897584Abstract: An image processing apparatus may be configured to detect motion based on a first block image within a first frame image included in first reduced image data sampled at a first sampling point and a first reference block image within a first reference frame image included in the first reduced image data; and extract a second block image when detecting that the first block image and the first reference block image are not moving and generate first image data corresponding to the first block image based on the first block image and the second block image. The second block image is in a second frame image included in second reduced image data sampled at a second sampling point that is different from the first sampling point and is at substantially the same time as the time of the first block image or the first reference block image.Type: GrantFiled: January 9, 2012Date of Patent: November 25, 2014Assignee: Fujitsu LimitedInventor: Kiyonori Morioka
-
Patent number: 8897581Abstract: A visual dynamic range (VDR) coding system creates a sequence of VDR prediction images using corresponding standard dynamic range (SDR) images and a prediction function. For each prediction image, an encoder identifies one or more areas within the prediction image suitable for post-prediction filtering. For each identified post-prediction area, a post-prediction filtering mode is selected among one or more post-prediction filtering modes. The selected post-prediction filtering mode is applied to output a filtered prediction image. Information related to the post-prediction filtering areas and the selected corresponding post-prediction filtering modes may be communicated to a receiver (e.g., as metadata) for guided post-prediction filtering. Example post-prediction filtering modes that use low-pass averaging filtering or adaptive linear interpolation are also described.Type: GrantFiled: December 5, 2012Date of Patent: November 25, 2014Assignee: Dolby Laboratories Licensing CorporationInventors: Guan-Ming Su, Tao Chen, Peng Yin, Sheng Qu
-
Patent number: 8897602Abstract: An electronic device may have a camera module and a host subsystem. The camera module may include a camera sensor and associated image processing and data formatting circuitry. The image processing and data formatting circuitry may include an image processor that produces unscaled images frames using data from the camera sensor. Unscaled image frames may be processed in multiple paths between the image processor and the host subsystem such as a path that includes an image compression circuit block, a parallel path that includes a preview scaler, and a parallel path that includes a multiframe scaler and a frame buffer and multiframe image processor circuitry. The multiframe scaler may scale unscaled frames for buffering and processing by the frame buffer and multiframe image processor circuitry to produce analysis results. The analysis results may be appended to compressed unscaled image frames sent to the host subsystem.Type: GrantFiled: May 20, 2010Date of Patent: November 25, 2014Assignee: Aptina Imaging CorporationInventor: Satish Kumar Bhrugumalla
-
Patent number: 8891905Abstract: Systems and methods which provide generation of high resolution depth maps from low resolution depth information using boundary-based processing techniques are disclosed. Boundary-based depth processing provided by embodiments implements boundary detection and boundary-based interpolation algorithms for providing high resolution depth information from low resolution depth information and high resolution image information. Boundary detection algorithms are implemented according to embodiments to detect object boundaries (e.g., depth discontinuities), where the low resolution depth samples are typically inaccurate and generally in need of refining. Boundary-based interpolation algorithms are implemented according to embodiments of the invention to refine intermediate upsampled depth information (e.g., spatially interpolated low resolution depth information), using the boundary information provided by a boundary detection algorithm, and provide high resolution depth information.Type: GrantFiled: December 19, 2012Date of Patent: November 18, 2014Assignee: Hong Kong Applied Science and Technology Research Institute Co., Ltd.Inventor: Chunhui Cui
-
Patent number: 8885208Abstract: The present disclosure includes systems and techniques relating to processing of high resolution images, such as digital painting on high resolution images. In general, one aspect of the subject matter described in this specification can be embodied in a method that includes receiving input defining a modification to a target image; determining, at a first processor, a low resolution proxy result of the modification applied to the target image; determining, at a second processor, a higher resolution result of the modification applied to the target image; displaying the low resolution proxy result before completion of the determining at the second processor; and updating the displayed low resolution proxy result with the higher resolution result. Other embodiments of this aspect include corresponding systems, apparatus, and computer program products.Type: GrantFiled: July 21, 2006Date of Patent: November 11, 2014Assignee: Adobe Systems IncorporatedInventor: Jerry G. Harris
-
Patent number: 8885976Abstract: A method implemented in an image processing system for combining multi-exposure images comprises obtaining a plurality of images each having different exposure levels for a same scene. A merged weight map for at least one obtained image is constructed by determining at least one merged weight value for at least one pixel of each obtained image based on characteristics of the pixel, wherein the merged weight map comprises a weight map corresponding to the plurality of images. A Gaussian pyramid and a Laplacian pyramid of each obtained image are generated, and a Gaussian pyramid of the merged weight map is generated. A merged Gaussian pyramid and a merged Laplacian pyramid are generated based on the Gaussian pyramid of the merged weight map. An intermediate pyramid is generated based on the merged Laplacian pyramid, and a resultant image is constructed by blending the merged Gaussian pyramid with the intermediate pyramid.Type: GrantFiled: June 19, 2014Date of Patent: November 11, 2014Assignee: Cyberlink Corp.Inventors: Chia-Chen Kuo, Po-Yu Huang, Wei-Chung Huang, Chia-En Chiang
-
Patent number: 8879872Abstract: A method and apparatus for restoring a resolution of a low resolution view image from a multi-view image. In the resolution restoration method, detailed information may be generated using a reference image neighboring a criterion image, and a resolution of the criterion image may be restored using the detailed information.Type: GrantFiled: June 6, 2012Date of Patent: November 4, 2014Assignee: Samsung Electronics Co., Ltd.Inventors: Seok Lee, Byung Tae Oh, Jae Joon Lee, Ho Cheon Wey, Seung Sin Lee
-
Publication number: 20140321741Abstract: An embodiment of the invention provides a method of processing a mosaicked image. First, the mosaicked image is up-sampled along a first direction to generate a first intermediate image. Then, the first intermediate image is resized along the first direction to generate a second intermediate image. Next, the second intermediate image is up-sampled along a second direction to generate a third intermediate image. Afterward, the third intermediate image is resized along the second direction to generate a resized and partly demosaicked image.Type: ApplicationFiled: April 25, 2013Publication date: October 30, 2014Applicant: MEDIATEK INC.Inventor: Ming-Chi Wei
-
Patent number: 8873889Abstract: An image processing apparatus comprises a processing unit for computing displacement amounts between a basis image and each reference image, a processing unit for generating multiple deformed images based on the displacement amounts, the basis image and multiple reference images, a processing unit for setting a threshold of a parameter, a processing unit for selecting image information from the reference image by the threshold, a processing unit for generating composed images and weighted images based on the basis image, the displacement amounts and the image information, a processing unit for generating high-resolution grid images by dividing the composed image by the weighted image, a processing unit for generating simplified interpolation images based on high-resolution grid images, a processing unit for generating assistance images, a display unit for displaying the assistance images and a control unit that controls the necessary processing as necessary.Type: GrantFiled: February 10, 2011Date of Patent: October 28, 2014Assignees: Tokyo Institute of Technology, Olympus CorporationInventors: Shunichi Koga, Masayuki Tanaka, Masatoshi Okutomi
-
Patent number: 8873887Abstract: In some instances, an image may have dimensions that do not correspond to a slot to display the image. For example, an image content item may have dimensions that do not correspond to a content item slot. The image may be resized using seam carving to add or remove pixels of the image. A saliency map for the image may be used having saliency scores for each pixel of the image. Evaluation metrics may be used before, during, and after, seam carving to determine whether salient content is affected by the seam carving. In some instances, a seam cost threshold value may be used for adaptive step size during the seam carving. The resized image may then be outputted, such as for an image content item to be served with a resource.Type: GrantFiled: January 24, 2013Date of Patent: October 28, 2014Assignee: Google Inc.Inventors: Mayur Datar, Huei-Hung Christopher Liao, Vivek Kwatra, Allen Huang
-
Patent number: 8873888Abstract: An system is described for managing bicubic downsampling in a constrained environment. The system may be configured to detect a request for a destination image, access a read-copy pattern for the ratio of downsampling, access the source image, and generate the destination image using the source image and the read-copy pattern.Type: GrantFiled: July 23, 2012Date of Patent: October 28, 2014Assignee: Adobe Systems IncorporatedInventor: Shiladitya Bose
-
Patent number: 8867864Abstract: There are provided a data processing apparatus which makes an I/F for data processing modules (processors) versatile to facilitate addition/modification on a data processing module basis in accordance with processing contents, an image processing apparatus, and a method for the apparatuses. A data processing module (3) includes a read address generator (11), read FIFO (7), write address generator (13), write FIFO (9), and arbiter (10) and is connected to a host arbiter (4) through a 1-channel port. The read address generator (11) and write address generator (13) generate interrupts upon acceptance of final access requests so as to control activation of each data processing module (8-1-8-m) in accordance with the state of each data processing module in interrupt processing. Note that data transfer among the respective data processing modules is performed on a RAM (6).Type: GrantFiled: March 13, 2012Date of Patent: October 21, 2014Assignee: Canon Kabushiki KaishaInventors: Hisashi Ishikawa, Ryoko Mise
-
Patent number: 8867863Abstract: High depth grayscale images, (e.g. <8 bits per pixel) are losslessly cross channel encoded to multi-channel image formats for transformation and display by display devices not capable of displaying high depth grayscale. DICOM and other images may be encoded and provided to web browser based client image viewers that leverage native code for handling multi-channel images. Transformations are applied to reconstitute the high depth grayscale images.Type: GrantFiled: April 18, 2013Date of Patent: October 21, 2014Assignee: Client Outlook Inc.Inventor: Steven Andrew Rankin
-
Patent number: 8867858Abstract: A method and system (30) generates an output image (21) of increased pixel resolution from an input image (20), which is non-dyadically upscaled to generate an upscaled image (22) having more pixels than the input image and is low-pass filtered to generate a smoothed image (23). A high detail image (24) is generated by subtraction and for each pixel in the upscaled image, a patch (25) containing the pixel is identified. A best-fit patch (26) within a localized region (27) of the smoothed image is found by searching in the smoothed image in close proximity to a mapped location of the patch in the upscaled image. Each pixel in the patch of the upscaled image is corrected by uniquely adding the value of the corresponding pixel in an equivalent patch of the high detail image corresponding to the best-fit patch, and the corrected upscaled image is stored for further processing.Type: GrantFiled: January 27, 2011Date of Patent: October 21, 2014Assignee: Yissum Research Development Company of the Hebrew University of Jerusalem, Ltd.Inventors: Raanan Fattal, Gilad Freedman
-
Publication number: 20140307982Abstract: A computer implemented method is provided for computing a two-way optical flow between a reference frame and one or more associated frames in an optical flow module. A forward warping operator and a backward warping operator can be generated between the reference frame and each of the one or more associated frames in a warping module. The forward warping operator and the backward warping operator provide motion compensation between the frames. Weights for each of the forward warping operators and the backward warping operators can be computed in a weight module. The weights correspond to uncertainty of motion estimation. A super resolution iteration algorithm can be calculated in a super-resolution iteration module.Type: ApplicationFiled: April 15, 2014Publication date: October 16, 2014Applicant: The government of the United States of America, as represented by the Secretary of the NavyInventors: Andrey V. Kanaev, Christopher W. Miller
-
Patent number: 8861846Abstract: An image processing apparatus includes a superimposition processing unit that performs a blending process for a plurality of continuously captured images, wherein the superimposition processing unit is configured to selectively input luminance signal information of a RAW image or a full color image as a processing target image and perform a superimposition process, and performs a process for sequentially updating data that is stored in a memory for storing two image frames so as to enable superimposition of any desired number of images.Type: GrantFiled: June 10, 2011Date of Patent: October 14, 2014Assignee: Sony CorporationInventors: Satoru Takeuchi, Hiroaki Takahashi, Teppei Kurita, Tomonori Masuno, Takefumi Nagumo, Yuhi Kondo
-
Patent number: 8861893Abstract: A method and apparatus for processing images. A portion of a selected image in which a moving object is present is identified. The selected image is one of a sequence of images. Pixels in a region of interest are identified in the selected image. First values are identified for a first portion of the pixels using the images and first transformations. The first portion of the pixels corresponds to the background in the selected image. A first transformation is configured to align features of the background between one image in the images and the selected image. Second values are identified for a second portion of the pixels using the images and second transformations. The second portion of the pixels corresponds to the moving object in the selected image. A second transformation is configured to align features of the moving object between one image in the images and the selected image.Type: GrantFiled: September 27, 2011Date of Patent: October 14, 2014Assignee: The Boeing CompanyInventors: Yang Chen, David R. Gerwe, Deying Zhang
-
Publication number: 20140301661Abstract: High quality upscaling and denoising are required in mobile imaging devices that do not contain high quality lenses. Such is also required in order to scale up standard-definition video content for display in high-definition television screens. The disclosed method uses contextual information obtained during upscaling and/or denoising of frames. Relevant correspondences between patches within a frame and between frames, are detected, managed and exploited. The correspondence information is simultaneously used and updated while video frames are being processed. Two approaches may be used: 1. keeping, searching for and updating a database of useful patches, by adding frequently visible similar patches, aggregating high-frequency, low-noise information associated with the similar patches, and removing less-observed patches; 2.Type: ApplicationFiled: October 30, 2013Publication date: October 9, 2014Applicant: SAMSUNG ELECTRONICS CO., LTD.Inventors: German Voronov, Shai Litvak, Tomer Yanir, Leonid Brailovsky
-
Publication number: 20140301665Abstract: Provided is an image data generating apparatus includes a position data obtaining unit and a display data generating unit. The position data obtaining unit obtains position data of a plurality of regions of interest (ROIs). The display data generating unit generates first data for displaying the plurality of pieces of position data on a display device and second data which enables a part of the captured image to be enlarged and a plurality of such enlarged parts to be displayed on the display device. The part of the captured image includes the ROI corresponding to position data specified by the user among the plurality of pieces of position data displayed on the display device. As a result, a screening operation for specifying a plurality of regions of interest and detailed observation can be performed in association with, and independently of, each other.Type: ApplicationFiled: December 18, 2012Publication date: October 9, 2014Inventors: Hiroshi Saito, Hidetoshi Tsuzuki, Shuji Murakami, Kazuyuki Sato
-
Publication number: 20140301664Abstract: Method, systems, and media for processing a digital slide image. In an embodiment, an identification of a macro, representing a plurality of algorithms, and an identification of digital slide image(s) are received over a network. Parameter data is obtained for the identified macro, and the digital slide image(s) are retrieved. The plurality of algorithms represented by the identified macro are executed on the digital slide image(s) according to the parameter data.Type: ApplicationFiled: June 20, 2014Publication date: October 9, 2014Inventors: Ole Eichhorn, Allen Olson
-
Patent number: 8855445Abstract: An image processing apparatus includes: an acquisition unit configured to acquire original image data expressing an original image that comprises a first type pixel and a second type pixel; and an enlargement processing unit configured to execute enlargement processing for the original image data to generate enlarged image data expressing an enlarged image that is obtained by enlarging the original image in a first direction. The enlargement processing unit includes: a pixel group selection unit configured to select a pixel group extending in a second direction intersecting with the first direction in the enlarge image when a specific pattern configured by the first type pixel and the second type pixel is included in the original image; and a setting unit configured to set a pixel configuring the pixel group in the enlarged image as the second type pixel.Type: GrantFiled: February 11, 2013Date of Patent: October 7, 2014Assignee: Brother Kogyo Kabushiki KaishaInventor: Ryuji Yamada
-
Patent number: 8849059Abstract: The invention relates to a method for generating images having a reduced error rate, high resolution and improved contrast from image sequences containing images having lower resolutions, which can be obtained from an image sensor having adjustable recording parameters. According to the invention, the image sequences of the images (K, R) having low resolutions are subjected to a combination of super-resolution processing (SR) and high dynamic range reconstruction processing (HDR) in order to obtain images having a reduced error rate, high resolution and improved contrast on the basis of redundant and complementary image information contained in the images having low resolution.Type: GrantFiled: July 11, 2009Date of Patent: September 30, 2014Assignee: Eads Deutschland GmbHInventors: Klaus Scherteler, Falk Schubert
-
Patent number: 8842938Abstract: Methods and systems for performing resolution expansion with high quality edge enhancement capability utilizing an edge detector and a color estimator. An edge tag with respect to an input image can be detected via an edge detector and an edge detection approach. A resolution expansion can be separately applied to the edge tag and a binary output generated by other processing functions. Multiple output lines corresponding to the input image from the color estimator with different threshold array values for an edge pixel can be generated by a halftoning module. A binary domain resolution expansion can be applied for a non-edge pixel. A final output for each pixel can be selected from a resolution expanded result and/or from the result of the halftoning for the edge based on the edge tag with respect to that pixel.Type: GrantFiled: June 27, 2012Date of Patent: September 23, 2014Assignee: Xerox CorporationInventors: Xing Li, David Metcalfe, Barbara Lynn Farrell
-
Patent number: 8837839Abstract: Described is a system for multiple-object recognition in visual images. The system is configured to receive an input test image comprising at least one object. Keypoints representing the object are extracted using a local feature algorithm. The keypoints from the input test image are matched with keypoints from at least one training image stored in a training database, resulting in a set of matching keypoints. A clustering algorithm is applied to the set of matching keypoints to detect inliers among the set of matching keypoints. The inliers and neighboring keypoints in a vicinity of the inliers are removed from the input test image. An object label and an object boundary for the object are generated, and the object in the input test image is identified and segmented. Also described is a method and computer program product for multiple-object recognition in visual images.Type: GrantFiled: November 3, 2010Date of Patent: September 16, 2014Assignee: HRL Laboratories, LLCInventors: David J. Huber, Deepak Khosla
-
Patent number: 8837854Abstract: An image processing method for boundary resolution enhancement is disclosed. Firstly, an image is transferred into an image layer. Noise of the image layer is removed by a bilateral filter and crisp edges are retained at the same time. Moreover, the image layer is interpolated by an interpolation filter for resolution enhancement. The image processing method of the present invention can lower the image blur degree substantially, enhance the image resolution and be widely implemented in all sorts of image/video processing hardware devices.Type: GrantFiled: December 18, 2012Date of Patent: September 16, 2014Assignee: Corel Software, LLCInventors: Lihua Zhu, Haihua Wu, Chung-Tao Chu, Richard Hua
-
Patent number: 8837016Abstract: An image forming apparatus includes a resolution converting unit, an address generating unit, a density determining unit, and an image path selector. The resolution converting unit converts a resolution of image data into a higher resolution. The address generating unit performs a position determining process of determining a position of an additional pixel on the basis of main-scanning directional positions of pixels composing the converted image data and respective shift amounts of the pixels shifted to a sub-scanning direction. The density determining unit determines a density of the additional pixel on the basis of a density of a pixel located at a position corresponding to the determined position in the image data. The image path selector scales the image data up or down by controlling the address generating unit while adding the additional pixel having the determined density to the determined position.Type: GrantFiled: December 6, 2013Date of Patent: September 16, 2014Assignee: Ricoh Company, LimitedInventor: Nobuyoshi Kaima
-
Patent number: 8836714Abstract: A method, a system, and a computer-readable medium are provided which provide interactive editing of image data. Image data is sampled, by a computing device, at a first resolution. The first resolution is lower than a full resolution of the image data. Gradients for the sampled image data are calculated by the computing device. The computing device solves a system equation for color pixel data for each pixel of the sampled image data using the sampled image data and the calculated gradients. The computing device controls a display of the color pixel data on a display.Type: GrantFiled: October 29, 2010Date of Patent: September 16, 2014Assignee: The University of Utah Research FoundationInventor: Valerio Pascucci
-
Image processing device, image processing method and storage medium storing image processing program
Patent number: 8831372Abstract: An image processing device for performing edge-preserving smoothing includes a reducing unit for reducing an input image; a reduced image smoothing unit for performing a smoothing processing on a reduced image generated by the reducing unit with edges preserved; and an edge-preserving enlarging unit for enlarging an image generated by the reduced image smoothing unit with the edges preserved. The edge-preserving enlarging unit performs a filtering processing by determining a pixel value of a target pixel for the filtering processing based on weighted addition of pixel values of respective reference pixels. Weighting coefficients for the pixel values of the respective reference pixels is set based on differences between a pixel value of the input image corresponding to the target pixel and pixel values of the respective reference pixels and based on distances between the target pixel and the respective reference pixels.Type: GrantFiled: September 28, 2011Date of Patent: September 9, 2014Assignee: Olympus CorporationInventor: Naoyuki Akiyama -
Patent number: 8830395Abstract: Systems and methods are provided for upscaling a digital image. A digital image to be upscaled is accessed, where the digital image comprises a plurality of pixel values. A first half pixel value is computed for a first point in the digital image based on a plurality of pixel values of the digital image surrounding the first point and an activity level. A second half pixel value is computed for a second point in the digital image, and an interpolated pixel of an upscaled version of the digital image is determined using a plurality of the pixel values, the first half pixel value, and the second half pixel value.Type: GrantFiled: December 10, 2013Date of Patent: September 9, 2014Assignee: Marvell World Trade Ltd.Inventors: Yun Gong, Dam Le Quang
-
Patent number: 8830309Abstract: A hierarchical pattern matching process is improved for use in three-dimensional reconstruction by calculating a disparity field for low-resolution data, and using this low-resolution disparity field to estimate the disparity field for higher-resolution images. By pre-warping a template according to the estimated disparity field, improved correlation results can be obtained.Type: GrantFiled: January 4, 2009Date of Patent: September 9, 2014Assignee: 3M Innovative Properties CompanyInventors: Janos Rohaly, Ilya A. Kriveshko
-
Publication number: 20140248001Abstract: An image processor receives an image. The image processor creates a low-resolution copy of the image for distribution to one or more recipients. Prior to distribution, the image processor produces permission information specifying whether a recipient is enabled to retrieve a high-resolution copy of the image. In addition to transmitting the low-resolution copy of the image to the recipient, the image processor forwards the permission information to the recipient as well. The recipient uses the permission information to determine whether the recipient is enabled to retrieve the high-resolution copy of the image. If enabled, the recipient can retrieve the high-resolution copy of the image. If disabled, the recipient cannot retrieve the high-resolution copy of the image. Accordingly, the permission information transmitted with the low-resolution copy can be used as a way of preventing or allowing access to the higher resolution copy of the image.Type: ApplicationFiled: October 9, 2008Publication date: September 4, 2014Inventor: James Marlow Leask