Color Image Processing Patents (Class 382/162)
-
Patent number: 9734164Abstract: The invention provides a method, server apparatus and terminal apparatus for providing an image, which can achieve an image search in accordance with a color, helps to make a user obtain an image of a color desired thereby, and can help a buyer to obtain a product of a color desired thereby in a comparatively accurate manner upon an application to the e-commerce field. The method comprises: a server receiving analysis data of color main components of an image to be inquired transmitted by a terminal device, then comparing the analysis data of the color main components of the image to be inquired with analysis data of color main components of a plurality of images in an image database, and transmitting identifications of the plurality of images having the greatest degree of similarity of a main color tone to the image to be inquired in the image database to the terminal device so that the terminal device acquires the images in accordance with the identifications.Type: GrantFiled: May 9, 2014Date of Patent: August 15, 2017Assignees: BEIJING JINGDONG SHANGKE INFORMATION TECHNOLOGY CO, LTD., BEIJING JINGDONG CENTURY TRADING CO., LTD.Inventors: Yongzhou Gan, Zhengang Jing, Huiman Hou, Yuhong Xiong, Jianming Jin
-
Patent number: 9736410Abstract: An image pickup apparatus includes an image pickup element including a plurality of pixels corresponding to a plurality of respective micro lenses and the first photoelectric conversion portion and the second photoelectric conversion portion that are included in each of the pixels and share a corresponding one of the micro lenses, and a signal processing unit configured to correct an addition signal of outputs from the first photoelectric conversion portion and the second photoelectric conversion portion included in each of the pixels and a first signal generated from a plurality of signals of the first photoelectric conversion portions corresponding to the micro lenses, and the signal processing unit corrects the addition signal for each of the pixels and corrects the first signal for the first photoelectric conversion portions.Type: GrantFiled: June 16, 2014Date of Patent: August 15, 2017Assignee: CANON KABUSHIKI KAISHAInventor: Mineo Uchida
-
Patent number: 9723169Abstract: An imaging apparatus is configured to capture an object image, generate a RAW image, perform simple development on the RAW image during the image capturing operation, and store not only the developed image but also the RAW image in a storage medium. If the imaging apparatus displays an image during the image capturing operation and immediately after the image capturing operation, the imaging apparatus displays the image processed by the simple development. When the imaging apparatus completes processing of high-quality image development, the imaging apparatus replaces the image processed by the simple development with the image processed by the high-quality image development and displays the image processed by the high-quality image development.Type: GrantFiled: March 6, 2014Date of Patent: August 1, 2017Assignee: Canon Kabushiki KaishaInventors: Shingo Nozawa, Masamichi Ito
-
Patent number: 9721187Abstract: A system, method, and computer program product for providing a lasso selection tool for a stereoscopic image is disclosed. The method includes the steps of obtaining a lasso region of a stereoscopic image pair based on a path defined by a user using a lasso selection tool. An object in a first image of the stereoscopic image pair is identified, where the object is at least partially included within the lasso region and the object is identified in a second image of the stereoscopic image pair.Type: GrantFiled: August 30, 2013Date of Patent: August 1, 2017Assignee: NVIDIA CorporationInventor: David R. Cook
-
Patent number: 9710885Abstract: An image processing apparatus includes a region determiner configured to receive image data and perform a region determination by determining whether each of a plurality of sub-pixels included in the image data is included in an in-focusing region that is focused or an out-focusing region that is not focused; and an interpolator configured to perform demosaicing with respect to a sub-pixel included in the in-focusing region by using a first algorithm and perform the demosaicing with respect to a sub-pixel included in the out-focusing region by using a second algorithm, according to a result of the region determination, wherein, when the demosaicing with respect to the sub-pixel included in the in-focusing region is performed, one or more peripheral sub-pixels having phases that are different from a phase of the sub-pixel, on which the demosaicing is performed, are used.Type: GrantFiled: December 1, 2015Date of Patent: July 18, 2017Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Jee-hong Lee, Nyeong-kyu Kwon
-
Patent number: 9710928Abstract: A computer implemented method, system and computer program product for identifying the Main Colors and the matching colors of a visual object, and then viewing on a mobile device select items comprising the matching colors, such as from a merchant's catalogue. A visual object is analyzed for color content, and the results are stored on a system database located on the device or on a remote server. The color analysis of the objects comprise advanced image processing techniques, such as Main Color extraction using color space transformation comprising HSV, RGB and CYMK to map between pixels in the image. The user can subsequently view a display on their mobile identifying the visual object's Main Colors and at least one Harmonic Color; and then select and view all items (i.e. products in a database) comprising one Harmonic Color, and/or all items of a specific type and Harmonic Color.Type: GrantFiled: August 7, 2016Date of Patent: July 18, 2017Inventors: Alon Atsmon, Dan Atsmon
-
Patent number: 9704069Abstract: The present invention discloses an image processing evaluating apparatus and image processing method. The processing apparatus comprising: a confidence generation means for generating a classification confidence for each region in the image, the classification confidence represents the probability of an region belonging to a predefined class; and a classification means for classifying the regions in the image, which are obvious to be classified by their classification confidences, to respective classes based on the calculated confidences.Type: GrantFiled: March 9, 2015Date of Patent: July 11, 2017Assignee: Canon Kabushiki KaishaInventors: You Lv, Yong Jiang, Bo Wu
-
Patent number: 9697592Abstract: The present invention provides a method for converting a low dynamic range (LDR) image to a high dynamic range (HDR) image, including obtaining an input LDR image; and in an HDR image database, selecting one or more HDR images that match the input LDR image as candidate images. Further, the candidate images are warped according to a spatial correspondence between the candidate images and the input LDR image. The input LDR image is decomposed to an illumination component and a texture component. The illumination component and the texture component are reconstructed respectively based on the warped candidate images. The reconstructed illumination component and the reconstructed texture component are combined to produce an output HDR image.Type: GrantFiled: December 30, 2015Date of Patent: July 4, 2017Assignee: TCL RESEARCH AMERICA INC.Inventors: Qiqin Dai, Xiaobo Ren, Haohong Wang
-
Patent number: 9697796Abstract: Techniques related to generating downscaled image or image frame data in a luma chroma separated color space for an image or video pipeline architecture are discussed. Such techniques may include converting input image data to the luma chroma separated color space based on adaptive color coefficients determined based on an illumination indicator associated with the input image data and storing downscaled color converted image data to an input image buffer of the image or video pipeline.Type: GrantFiled: March 26, 2015Date of Patent: July 4, 2017Assignee: Intel CorporationInventors: Nir Darshan, Gilad Michael, German Voronov
-
Patent number: 9686446Abstract: An image forming apparatus includes a control unit with a reduction mode using a reduced consumption of the color material. The reduction rule includes a rule of conversion configured to, in a constant hue plane of the input color value, move all color values on a straight line passing through a lowest brightness color value and the input color value in a direction from a highest saturation color value to a highest brightness color value, so as to convert into color values on a straight line passing through the lowest brightness color value and a converted input color value where the input color value is converted, the lowest brightness color value being indicative of a color value of lowest brightness, the highest saturation color value being indicative of a color value of highest saturation, the highest brightness color value being indicative of a color value of highest brightness.Type: GrantFiled: September 17, 2015Date of Patent: June 20, 2017Assignee: KYOCERA Document Solutions Inc.Inventor: Yuka Miyanaga
-
Patent number: 9686435Abstract: An imaging apparatus is configured to capture an object image, generate a RAW image, perform simple development on the RAW image during the image capturing operation, and store not only the developed image but also the RAW image in a storage medium. If the imaging apparatus displays an image during the image capturing operation and immediately after the image capturing operation, the imaging apparatus displays the image processed by the simple development. When the imaging apparatus completes processing of high-quality image development, the imaging apparatus replaces the image processed by the simple development with the image processed by the high-quality image development and displays the image processed by the high-quality image development.Type: GrantFiled: March 6, 2014Date of Patent: June 20, 2017Assignee: Canon Kabushiki KaishaInventors: Shingo Nozawa, Masamichi Ito
-
Patent number: 9679032Abstract: A device information providing system has a search request receiving unit that receives, as a search request for searching for a device, a search request including an output requirement for specifying a desired output result, a processing module DB in which information concerning a processing module that receives, as inputs, outputs from one or a plurality of other devices and combines the inputs to generate a new output is registered with respect to a plurality of the processing modules together with at least an input requirement for specifying an input of a processing module and an output requirement for specifying an output of the processing module, and a device DB in which information concerning the device is registered with respect to a plurality of the devices together with at least an output requirement for specifying an output of the device.Type: GrantFiled: February 26, 2014Date of Patent: June 13, 2017Assignee: OMRON CorporationInventors: Toru Uenoyama, Atsushi Hisano
-
Patent number: 9672442Abstract: A method for detecting differences between two digital images includes the steps of: transforming the images by resizing the images in order to get identical image sizes, by aligning pixels of the images and by normalizing colors of the images; determining plural binary masks from the pixels of the transformed images, each binary mask being composed of one element per couple of pixels of the transformed images having same coordinates; determining plural energy functions, each energy function being the sum of a first term representative of transformed images and of one binary mask and of a second term which is only dependent on said one binary mask; minimizing the energy function over other plural energy functions; and selecting the binary mask corresponding to the minimized energy function.Type: GrantFiled: September 21, 2012Date of Patent: June 6, 2017Assignee: LTU TECHNOLOGIESInventors: Régis Behmo, Fabien Freling, Yannick Allusse, Simon Dolle
-
Patent number: 9669585Abstract: A computer implemented method and apparatus for embedding a 2D image in a 3D model. The method comprises generating a 3-dimensional (3D) print matrix representing a 2-dimensional (2D) image, wherein the print matrix comprises a plurality of sub-regions, the base plane of each sub-region angled with respect to a top surface of the print matrix so as to produce a plurality of shades, each shade representing a shade of the 2D image; and embedding the print matrix in a (3D) model.Type: GrantFiled: February 11, 2014Date of Patent: June 6, 2017Assignee: ADOBE SYSTEMS INCORPORATEDInventors: Mayur Hemani, Abhishek Kumar, Naveen Prakash Goel
-
Patent number: 9667836Abstract: A color conversion apparatus to output image data to a printer obtains roughness data to indicate the roughness of each pixel in an image expressed by the image data, derives a reduction ratio of a color gamut in each pixel according to a roughness of each pixel in the roughness data, changes color gamut data indicating for the printer on a substantially flat surface according to the derived reduction ratio to derive color gamut data in each pixel, and then performs color conversion on each pixel in the image data using the derived color gamut data.Type: GrantFiled: March 11, 2016Date of Patent: May 30, 2017Assignee: CANON KABUSHIKI KAISHAInventor: Kimitaka Arai
-
Patent number: 9661331Abstract: Methods of optimal encoding of signals to be compatible with characteristics of target receivers while meeting constraints pertinent to sizes of encoded signals or capacities of paths communicating signals to the target receivers are disclosed. The methods are based on analytical modeling of the encoding process guided by experimental data relating measured performance indicators of encoded signals of diverse classifications to respective encoding parameters. A computationally-efficient technique is devised to determine optimal encoding parameters based on pre-processed data derived from the analytical models. The methods may be implemented at an encoder of original signals or a transcoder of pre-encoded signals.Type: GrantFiled: March 17, 2014Date of Patent: May 23, 2017Assignee: Vantrix CorporationInventors: Didier Joset, Stéphane Coulombe, Maged E. Beshai
-
Patent number: 9652687Abstract: An image processing apparatus capable of performing development by adjusting the saturation level of each color signal, without losing gradation in a high-luminance area. Saturation levels of color signals of three colors are calculated on photographed data. Color signal values in each pixel of the photographed data are acquired as pixel information. If it is determined, based on the saturation levels and the pixel information, to perform substitution, substitution for a color signal having the second highest saturation level is performed according to a color signal having the highest saturation level, and substitution for a color signal having the lowest saturation level is performed according to the color signals having the highest and second highest saturation levels. Predetermined processing is performed on photographed data on which substitution processing has been performed to thereby generate the developed data.Type: GrantFiled: February 19, 2015Date of Patent: May 16, 2017Assignee: CANON KABUSHIKI KAISHAInventor: Noriaki Sato
-
Patent number: 9646368Abstract: Methods, systems and computer program products for automatic color correction of image and video content are provided. A computer-implemented method may include generating an auto-level linear transform and a histogram equalization transform of a color distribution histogram for an original image among a set of sequential images. The auto-level linear transform and the histogram equalization transform are blended to create a modified image. Pixel color is adjusted in the modified image so that a color difference between a pixel and neighboring pixels in the modified image corresponds to a color difference between respective pixels in the original image.Type: GrantFiled: August 13, 2014Date of Patent: May 9, 2017Assignee: Google Inc.Inventor: William Brendel
-
Patent number: 9645831Abstract: A guide is configured in an authoring program to aid the user in editing objects on a document. The guide can be a horizontally or vertically oriented guide line and can be created from a single ruler, either a vertical or horizontal ruler displayed on the workspace. To create a horizontal guide, the user can position the cursor on a horizontal ruler. The user can click-and-hold and drag the cursor to create and position a horizontal guide over the workspace. To create a vertical guide, the user can position the cursor in the horizontal ruler and click and release. The user can create both vertical and horizontal guides using the vertical ruler in a corresponding manner, where clicking on the vertical ruler creates a horizontal guide, and click-and-hold and dragging creates a vertical guide. Guides can be individually configured or altered in their visual characteristics.Type: GrantFiled: September 29, 2014Date of Patent: May 9, 2017Assignee: Microsoft Technology Licensing, LLCInventor: Daniel John Altin
-
Patent number: 9646352Abstract: Methods, systems, and devices are described for associating comments with playback of media content. At an input device, a parallel echo version of media content being played on a second device is provided, and a selection is received of a portion of the parallel echo version of the media content. A comment associated with the selected portion of the parallel echo version of the media content is received, and the received comment is associated with a portion of the media content associated with the selected portion of the parallel echo version. At an output device, a parallel echo version of media content being played on a second device is provided, a current point in the parallel echo version of the media content is determined, and an indicator of a comment associated with a point in the media content corresponding to the current point in the parallel echo version is displayed.Type: GrantFiled: December 12, 2011Date of Patent: May 9, 2017Assignee: Quib, Inc.Inventor: James Burns McClements, IV
-
Patent number: 9639740Abstract: The present invention provides, in at least one aspect, methods and systems that detect at least one face in at least one digital image, determine and store area co-ordinates of a location of the at least one detected face in the at least one digital image, apply at least one transformation to the at least one detected face to create at least one portrait of the at least one detected face, rotate the at least one portrait at least until the at least one portrait is shown in a vertical orientation and a pair of eyes of the at least one face shown in the at least one portrait are positioned on a horizontal plane; and store the rotated at least one portrait.Type: GrantFiled: November 12, 2013Date of Patent: May 2, 2017Assignee: APPLIED RECOGNITION INC.Inventors: Ray Ganong, Donald Craig Waugh, Yong Man Ro, Konstantinos Plataniotis, Chris Studholme
-
Patent number: 9633249Abstract: A data processing system for performing face detection on a stream of frames of image data, the data processing system comprising: a skin patch identifier configured to identify one or more patches of skin color in a first frame and characterize each patch in the first frame using a respective patch construct of a predefined shape; a first search tile generator configured to generate one or more first search tiles from the one or more patch constructs; and a face detector configured to detect faces in the stream by performing face detection in one or more frames of the stream within the first search tiles.Type: GrantFiled: October 23, 2014Date of Patent: April 25, 2017Assignee: Imagination Technologies LimitedInventors: Szabolcs Cséfalvay, Paul Brasnett
-
Patent number: 9626744Abstract: Techniques to generate global tone-mapping operators (G-TMOs) that, when applied to high dynamic range images, visually approximate the use of spatially varying tone-mapping operators (SV-TMOs) are described. The disclosed G-TMOs provide substantially the same visual benefits as SV-TMOs but do not suffer from spatial artifacts such as halos and are, in addition, computationally efficient compared to SV-TMOs. In general, G-TMOs may be identified based on application of a SV-TMO to a down-sampled version of a full-resolution input image (e.g., a thumbnail). An optimized mapping between the SV-TMO's input and output constitutes the G-TMO. It has been unexpectedly discovered that when optimized (e.g., to minimize the error between the SV-TMO's input and output), G-TMOs so generated provide an excellent visual approximation to the SV-TMO (as applied to the full-resolution image).Type: GrantFiled: August 31, 2015Date of Patent: April 18, 2017Assignee: Apple Inc.Inventors: Graham D. Finlayson, Jakkarin Singnoo
-
Patent number: 9619901Abstract: An image processing apparatus includes an image information acquisition unit, an elimination color setting unit, and a processing unit. The image information acquisition unit acquires image information of a document image in which multiple colors that are different from a predetermined document color are added to an image which is rendered in the predetermined document color. The elimination color setting unit sets a color which is defined as an elimination color from among the multiple colors. The processing unit performs predetermined processing for a color among the multiple colors that is different from the elimination color set by the elimination color setting unit.Type: GrantFiled: September 8, 2015Date of Patent: April 11, 2017Assignee: FUJI XEROX CO., LTD.Inventors: Hiroshi Mikuriya, Taro Mori
-
Patent number: 9607404Abstract: A system for normalizing, codifying and categorizing divergent color systems into a universal color system. A server connected to a communications network receives, processes, codifies and categorizes divergent color data from a merchant system. A middleware engine of the server receives a data feed comprising a plurality of color swatches or images from the merchant system, and normalizes the data feed into a common format. A server processor extracts image data comprising a plurality of product images from the normalized data feed, identifies and converts at least one dominant product color in each product image to a digital value, and assigns a hexadecimal code of the universal color system to each product image that is closest to the digital value of each product image based on color component intensity values of at least one dominant product color in each product image. A product categorization engine categorizes each product image into one of a plurality of product categories.Type: GrantFiled: September 6, 2016Date of Patent: March 28, 2017Assignee: ZENCOLOR CORPORATIONInventors: Dann Gershon, David Robinson, Jonathan Wilder, Maurice W. Schonfeld
-
Patent number: 9609176Abstract: A method, apparatus and computer program product are provided to cause image content to be adjusted in a manner consistent with the corresponding viewing direction, such as the viewing direction of a user of a head-mounted display device. In regards to a method, one or more first anchor frames are determined within a multi-frame image, a user's viewing direction is determined relative to the multi-frame image and at least one second anchor frame is identified based on the user's viewing direction. The method also includes determining one or more tonal modification parameters of a frame in relation to the viewing direction based upon the one or more first anchor frames and the at least one second anchor frame. Further, the method generates a plurality of modified frames based on the one or more tonal modification parameters. A corresponding apparatus and computer program product are also provided.Type: GrantFiled: August 27, 2015Date of Patent: March 28, 2017Assignee: Nokia Technologies OyInventors: Veldandi Muninder, Daniel Vaquero
-
Patent number: 9591234Abstract: A digital camera accesses, processes and displays a combination image composed of visible light and near non-visible (“NNV”) light. A method can include accessing, by a digital camera, raw data having first information associated with a first electromagnetic spectrum range and second information associated with a second electromagnetic spectrum range. The first electromagnetic spectrum range is substantially within the visible spectrum and the second electromagnetic spectrum range is substantially within the NNV spectrum. The method can also include optimizing the raw data for the visible spectrum, thereby generating a first visual image representation, and optimizing the raw data for the NNV spectrum, thereby generating a second visual image representation. The method can also include combining the first visual image representation and the second visual image representation to generate a combination image. The digital camera can then initiate the display of the combination image.Type: GrantFiled: August 20, 2013Date of Patent: March 7, 2017Assignee: AT&T INTELLECTUAL PROPERTY I, L.P.Inventor: Dylan C. Reid
-
Patent number: 9576343Abstract: Systems and methods for a content-adaptive photo-enhancement recommender that produces multiple enhanced images based on content and color layout parameters derived from related high-quality images are disclosed. In some embodiments, a user-uploaded image is enhanced based on parameters learned from high-quality images similar in content to the user-uploaded image and obtained using content-based image retrieval techniques.Type: GrantFiled: November 10, 2015Date of Patent: February 21, 2017Assignee: Arizona Board of Regents on Behalf of Arizona State UniversityInventors: Baoxin Li, Parag Shridhar Chandakkar, Qiongjie Tian
-
Patent number: 9569088Abstract: A mobile terminal having a touch screen or a touch pad is disclosed. In a user environment, when a displayed menu list is moved according to a flicking operation, a feedback indicating the reaching of the end (the last item) of the menu list is issued in a visible, audible or tactile manner to a user, thereby increasing the user convenience of menu searching and the durability of the mobile terminal.Type: GrantFiled: September 2, 2008Date of Patent: February 14, 2017Assignee: LG ELECTRONICS INC.Inventors: Woo-Young Kwak, Seung-Jun Lee, So-Young Park
-
Patent number: 9569866Abstract: Techniques involving flexible video object boundary tracking are described. One or more curves, such as Bezier curves, are received as drawn by a user on an initial frame of video to define a boundary of an object in the frame. The curves are then mapped to a subsequent or previous frame of the video where the object is included but has a new or changed boundary. A segmentation boundary is determined for the object in the subsequent frame and endpoints of segments of the curves are snapped to the segmentation boundary. Additionally, confidence values are determined for subregions of the frame that include portions of the curves. These confidence values are used to update control points on the curve segments to fit the curve segments to the new or changed boundary of the object in the frame.Type: GrantFiled: March 10, 2015Date of Patent: February 14, 2017Assignee: Adobe Systems IncorporatedInventors: Xue Bai, Jue Wang, Yao Lu
-
Patent number: 9571696Abstract: A print data generating apparatus executes color conversion on image data using a color conversion profile to generate print data. In the color conversion profile, each of a plurality of sets of specific color data defined in a specific color space are associated with a set of first ink color data defined in an ink color space. A part of the plurality of sets of specific color data are further associated with a set of second ink color data defined in the ink color space. In bi-directional printing, a print executing unit uses the first ink color data to execute one of forward print and backward print, and uses both the first ink color data and the second ink color data to execute another of forward print and backward print.Type: GrantFiled: December 1, 2015Date of Patent: February 14, 2017Assignee: Brother Kogyo Kabushiki KaishaInventor: Shota Morikawa
-
Patent number: 9558510Abstract: In various example embodiments, a system and method to provide services associated with an image is disclosed. The method includes receiving image data of an item of interest from a client device. The image data is used to identify a similar item from an image catalog based on the image data of the item. Attribute information associated with the similar item is retrieved and used to pre-populate a template. The pre-populated template is sent to the client device, and modified data from the client device is received in response, with the modified data resulting in a final template. A listing based on the final template is generated.Type: GrantFiled: September 14, 2009Date of Patent: January 31, 2017Assignee: eBay Inc.Inventors: Ryan Melcher, Dane Howard
-
Patent number: 9554109Abstract: Examples of the disclosure accurately define a gray region for automatic white balancing. Ratios corresponding to possible gray areas are white balanced before color distance metrics are calculated with respect to white points under different light sources. The color distance metrics of each point in the image data are compared with a predetermined threshold value to identify a gray region. Gray points within a captured image are identified using the gray region and input to any AWB method to accurately white balance the captured image.Type: GrantFiled: June 23, 2016Date of Patent: January 24, 2017Assignee: Microsoft Technology Licensing, LLCInventor: Meng Yao
-
Patent number: 9552442Abstract: A system and method for analyzing visual memes includes identifying visual memes associated with at least one topic in a data source. The visual memes propagated over time are tracked to extract information associated with identified visual memes. The information associated with the visual memes is analyzed to determine at least one of generation, propagation, and use of the identified memes.Type: GrantFiled: October 21, 2010Date of Patent: January 24, 2017Assignee: International Business Machines CorporationInventors: Matthew L. Hill, John R. Kender, Apostol I. Natsev, John R. Smith, Lexing Xie
-
Patent number: 9547678Abstract: An activity recognition system is disclosed. A plurality of temporal features is generated from a digital representation of an observed activity using a feature detection algorithm. An observed activity graph comprising one or more clusters of temporal features generated from the digital representation is established, wherein each one of the one or more clusters of temporal features defines a node of the observed activity graph. At least one contextually relevant scoring technique is selected from similarity scoring techniques for known activity graphs, the at least one contextually relevant scoring technique being associated with activity ingestion metadata that satisfies device context criteria defined based on device contextual attributes of the digital representation, and a similarity activity score is calculated for the observed activity graph as a function of the at least one contextually relevant scoring technique, the similarity activity score being relative to at least one known activity graph.Type: GrantFiled: June 17, 2015Date of Patent: January 17, 2017Assignee: Nant Holdings IP, LLCInventors: Kamil Wnuk, Nicholas J. Witchey
-
Patent number: 9542703Abstract: Disclosed are various embodiments for facilitating an electronic framing process. A virtual framing system may access a digital image provided by or otherwise selected by a user of the virtual framing system to be examined on a pixel-by-pixel basis to identify relevant and/or dominant colors located within the digital image. By utilizing the most relevant and/or the most dominant colors of the digital image, the virtual framing system may subsequently generate recommendations to be presented to the user by comparing the most relevant and/or most dominant colors to one or more predefined design templates, such as those created by an expert designer, that are stored in a data store.Type: GrantFiled: December 23, 2013Date of Patent: January 10, 2017Assignee: Larson-Juhl Inc.Inventors: Mark Clarence Marschke, James David Baker, Ginger Marissa Blisse Hartford, Brian Benjamin Maston, Molly O'Connell Montabert, Paul Edward Noble, Ramanath Subramanian
-
Patent number: 9544550Abstract: Described is a low power surveillance camera system for intruder detection. The system observes a scene with a known camera motion to generate images with various viewing angles. Next, a background learning mode is employed to generate a low rank matrix for the background in the images. Background null space projections are then learned, which provide a foreground detection kernel. A new scene with known viewing angles is then obtained. Based on the foreground detection kernel and the new input image frame, low power foreground detection is performed to detect foreground potential regions of interest (ROIs), such as intruders. To filter out minimal foreground activity, the system identifies contiguous ROIs to generate the foreground ROI. Focus measures are then employed on the ROIs using foveated compressed sensing to generate foveated measurements. Based on the foveated measurements, the foreground is reconstructed for presentation to a user.Type: GrantFiled: March 13, 2014Date of Patent: January 10, 2017Assignee: HRL Laboratories, LLCInventors: Kang-Yu Ni, Shankar R. Rao, Yuri Owechko
-
Patent number: 9524541Abstract: Disclosed herein is a method. A set of pre-adjusted images including source images of the pre-adjusted images is provided. The pre-adjusted images include image filter parameters. Histogram information for each of the source images is computed. A learning algorithm is applied to the set. The learning algorithm is configured to map the histogram information to the image filter parameters. A real-time image is processed based on the mapping of the histogram information to the image filter parameters.Type: GrantFiled: February 4, 2014Date of Patent: December 20, 2016Assignee: HERE GLOBAL B.V.Inventor: Alan Heirich
-
Patent number: 9519826Abstract: A computer-implemented method of grouping faces in large user account for creating an image product includes adding the face images obtained from an image album in a user's account into a first chunk; if the chunk size of the first chuck is smaller than a maximum chuck value, keeping the face images from the image album into the first chunk; otherwise, automatically separating the face images from the image album into a first portion and one or more second portions; keeping the first portion in the first chunk; automatically moving the second portions to subsequent chunks; automatically grouping face images in the first chunk to form face groups; assigning the face groups to known face models associated with the user account; and creating a design for an image-based product based on the face images in the first chunk associated with the face models.Type: GrantFiled: November 4, 2015Date of Patent: December 13, 2016Assignee: Shutterfly, Inc.Inventors: Roman Sandler, Alexander M. Kenis
-
Patent number: 9514127Abstract: A computer implemented method, a program, and a system for effectively providing versatile non-text information suitable for use in a multi-language environment. The method includes the steps of: receiving search results of a database using a search criterion in a certain language and a search criterion in another language corresponding to the search criterion in which specific language attributes are associated with non-text elements that are included in the search results; scoring the non-text elements included in the search results depending on a similarity to another element with which a different language attribute is associated; and identifying at least one of the non-text elements included in the search results on the basis of the scores.Type: GrantFiled: September 12, 2013Date of Patent: December 6, 2016Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Yasuharu Katsuno, Kohtaroh Miyamoto, Ken Mizuno, Sachiko Yoshihama
-
Patent number: 9514526Abstract: An evaluation value indicative of the extent of lines in each direction is calculated for a pre-processed image in which 0s are filled in and extended in the lateral direction of the inputted image and which has been reduced ?th in the longitudinal direction. To obtain the angle of rotation of an image from the change in the evaluation value obtained while the angle relative to the lateral direction of the pre-processed image is modified in small steps, a parallel line is drawn for each direction, a projection is taken, and the sum of squares serves as the evaluation value of the direction. The direction having the highest evaluation value serves as the obtained direction of rotation from the normal position. The projection of each direction references the point of intersection between the parallel line drawn for each direction and the coordinate line of the horizontal axis.Type: GrantFiled: November 9, 2011Date of Patent: December 6, 2016Assignee: Hitachi High-Technologies CorporationInventors: Jun'ichi Taguchi, Mitsuji Ikeda, Yuichi Abe, Masahiro Kitazawa
-
Patent number: 9503615Abstract: Image processing systems and methods are disclosed, including an image processing system comprising a computer running image processing software causing the computer to receive an oblique aerial image having at least a first section and a second section, wherein the first section has a first color distribution and the second section has a second color distribution; receive at least two reference images having consistent color distributions; receive geographic information about the at least two reference images and the oblique aerial image; choose at least a one reference image for each of the first and second sections based on the geographic information; and create at least one color-balancing transformation for the first and second sections.Type: GrantFiled: February 26, 2015Date of Patent: November 22, 2016Assignee: Pictometry International Corp.Inventors: Stephen L. Schultz, Frank D. R. Giuffrida, Robert Gray
-
Patent number: 9497356Abstract: We propose new methods for creating color or achromatic images that are printed with classical cyan, magenta, yellow and a white diffusing ink on a metallic substrate. We optimize the surface coverages of the cyan, magenta, yellow and white inks in order to create color prints on a metallic surface that look bright and colorful under specular reflection and also look good under non-specular observation conditions. We also provide new means for the prevention of counterfeits. A first effect enables viewing on the same metallic print one achromatic image in specular viewing mode and a second independent achromatic image in non-specular viewing mode. The second effect enables hiding a pattern such as text, graphics or a grayscale image within the printed color image in one viewing mode, specular or non-specular and showing that pattern in the second viewing mode, non-specular or specular, respectively.Type: GrantFiled: June 23, 2015Date of Patent: November 15, 2016Assignee: ECOLE POLYTECHNIQUE FEDERALE DE LAUSANNE (EPFL)Inventor: Roger D. Hersch
-
Patent number: 9495800Abstract: Using as a texture of an image to be placed in a virtual world an image included in a predetermined area in a captured image captured by a real camera, a virtual world image is generated, in which the object placed in the virtual world is viewed from a virtual camera. Then, the captured image captured by the real camera is combined with the virtual world image, and the combined image is displayed on a display device.Type: GrantFiled: March 11, 2011Date of Patent: November 15, 2016Assignee: NINTENDO CO., LTD.Inventor: Toshiaki Suzuki
-
Patent number: 9485386Abstract: A method for creating a scanner profile according to the present invention includes the steps of: by reading, by a scanner, a printed material of chart image data comprising a plurality of patches which are composed of C, M, Y, K values and differentiated in color and density from each other, acquiring a first color value for the patches; acquiring a K value for the patches of the chart image data; acquiring a second color value for the patches by color-measuring the printed material by the colorimeter; and creating a scanner profile describing a relationship of the second color value to the first color value and the K value, based on the acquired first color value, K value, and second color value for each of the plurality of patches.Type: GrantFiled: May 29, 2015Date of Patent: November 1, 2016Assignee: KONICA MINOLTA, INC.Inventor: Naoyo Suzuki
-
Patent number: 9479746Abstract: The present disclosure describes systems and techniques relating to demosaicking artifact suppression. According to an aspect of the described systems and techniques, a device includes: demosaicking circuitry configured to generate interpolated data from raw data received from an image sensor in a three color data format; first circuitry configured to filter a chrominance component of a luminance-chrominance data format version of the interpolated data to suppress false color; and second circuitry configured to filter a luminance component of the luminance-chrominance data format version of the interpolated data to suppress isolated dots.Type: GrantFiled: December 31, 2014Date of Patent: October 25, 2016Assignee: Marvell World Trade Ltd.Inventor: Huai Dong Li
-
Patent number: 9477649Abstract: Objects displayed on a display component of a multi-touch display device may be assigned to and displayed at various visual layers, with each visual layer corresponding to a different depth relative to a foreground (or background) of the display component of the multi-touch display device. One or more annotations may be generated in response to user interaction with the multi-touch display device, with each annotation being assigned to an appropriate visual layer.Type: GrantFiled: January 5, 2010Date of Patent: October 25, 2016Assignee: PERCEPTIVE PIXEL, INC.Inventors: Philip L. Davidson, Jefferson Y. Han
-
Patent number: 9471560Abstract: Various techniques for autocorrecting virtual keyboard input for various languages (e.g., Japanese, Chinese) are disclosed. In one aspect, a system or process receives a sequence of keyboard events representing keystrokes on a virtual keyboard. A hierarchical data structure is traversed according to the sequence of keyboard events to determine candidate words for the sequence of keyboard events. A word lattice is constructed using a language model, including deriving weights or paths in the word lattice based on candidate word statistics and data from a keyboard error model. The word lattice is searched to determine one or more candidate sentences comprising candidate words based on the path weights. Paths through the word lattice can be pruned (e.g., discarded) to reduce the size and search time of the word lattice.Type: GrantFiled: June 1, 2012Date of Patent: October 18, 2016Assignee: Apple Inc.Inventors: Yasuo Kida, Leland Douglas Collins, Jr.
-
Patent number: 9471209Abstract: Provided is a layout editing device, a layout editing method, and a recording medium. The layout editing device includes a layout editing unit editing a layout, which is displayed on an editing screen of a screen display unit, based on the instruction of a user, an image analysis unit performing image analysis of each of a plurality of images, a preference estimation unit estimating the preference of the user based on the layout editing result and the image analysis result, an image evaluation unit calculating the evaluation value of each of the plurality of images based on the preference of the user and the image analysis result, and an edit assisting unit displaying assist information, which is for assisting the editing work of the layout by the user, on the editing screen of the screen display unit based on the evaluation value of each of the plurality of images.Type: GrantFiled: March 12, 2014Date of Patent: October 18, 2016Assignee: FUJIFILM CorporationInventors: Kei Yamaji, Teruyoshi Nakashima
-
Patent number: 9466125Abstract: In an image-encoding scheme, an input image is decomposed into several image blocks comprising multiple image elements. The image blocks are encoded into encoded block representations. In this encoding, color weights are assigned to the image elements in the block based on their relative positions in the block. At least two color codeword are determined, at least partly based on the color weights. These codewords are representations of at least two color values. The original colors of the image elements are represented by color representations derivable from combinations of the at least two color values weighted by the assigned color weights.Type: GrantFiled: May 12, 2015Date of Patent: October 11, 2016Assignee: TELEFONAKTIEBOLAGET LM ERICSSON (PUBL)Inventor: Jacob Ström