Patents Examined by Edward F. Urban
-
Patent number: 12045953Abstract: ROI (Region of Interest) detection is an important step in extracting relevant information from a document image. Such images are very high-resolution images in nature and size of images is in order of megabytes, which makes text detection pipeline very slow. Traditional methods detect and extract ROI from images, but these work only for specific image types. Other approaches include deep learning (DL) based methods for ROI detect which need intensive training and require high end computing infrastructure/resources with graphical processing unit (GPU) capabilities. Systems and methods of the present disclosure perform ROI extraction by partitioning input image into parts based on its visual perception and then classify the image in first or second category. Region of interest is extracted from a resized image based on the classification by applying image processing techniques. Further, the system determines whether the input image is a pre-cropped image or a normal scanned image.Type: GrantFiled: August 3, 2021Date of Patent: July 23, 2024Assignee: TATA CONSULTANCY SERVICES LIMITEDInventors: Amit Kumar Agrawal, Mantu Prasad Gupta, Tanmay Suhas Jagtap, Devang Jagdishchandra Patel, Pushp Kumar Jain, Dinesh Yadav, Prabhat Ranjan Mishra, Rajdeep Chatterjee, Prosenjit Mondal
-
Patent number: 12039758Abstract: The present disclosure provides an image processing apparatus capable of efficiently generating a learning model having a high accuracy. An image processing apparatus (1) includes a data acquisition unit (2), a data generation unit (4), a recognition accuracy calculation unit (6), and a learning data output unit (8). The data acquisition unit (2) acquires input image data. The data generation unit (4) converts the input image data by using a data conversion parameter and newly generates image data. The recognition accuracy calculation unit (6) calculates a recognition accuracy of the image data generated by the data generation unit (4) by using a learning model stored in advance. The learning data output unit (8) outputs, as learning data, the image data of which the recognition accuracy calculated by the recognition accuracy calculation unit (6) is lower than a first threshold.Type: GrantFiled: January 10, 2020Date of Patent: July 16, 2024Assignee: NEC CORPORATIONInventor: Tetsuo Inoshita
-
Patent number: 12039753Abstract: An information processing apparatus according to an embodiment of the present technology includes a first acquisition section, a second acquisition section, and a determination section. The first acquisition section acquires a camera-based position indicating a position of a real object, the camera-based position being determined on the basis of a captured image of a real space in which there exists the real object. The second acquisition section acquires an output-wave-based estimation position indicating the position of the real object, the output-wave-based estimation position being determined on the basis of an output wave that is output to the real space from a position that corresponds to the real object. The determination section determines a reference position used to represent virtual content related to the real object, on the basis of the camera-based position and the output-wave-based estimation position.Type: GrantFiled: August 2, 2019Date of Patent: July 16, 2024Assignee: SONY CORPORATIONInventors: Hidenori Aoki, Fujio Arai, Keijiroh Nagano, Shintaro Tsutsui, Naoyuki Sato
-
Patent number: 12033339Abstract: A method for localizing, in a space containing at least one determined object, an object element associated to a particular 2D representation element in a determined 2D image of the space, may have: deriving a range or interval of candidate spatial positions for the imaged object element on the basis of predefined positional relationships); restricting the range or interval of candidate spatial positions to at least one restricted range or interval of admissible candidate spatial positions, wherein restricting includes at least one of: limiting the range or interval of candidate spatial positions using at least one inclusive volume surrounding at least one determined object; and limiting the range or interval of candidate spatial positions using at least one exclusive volume surrounding non-admissible candidate spatial positions; and retrieving, among the admissible candidate spatial positions of the restricted range or interval, a most appropriate candidate spatial position on the basis of similarity metricsType: GrantFiled: July 28, 2021Date of Patent: July 9, 2024Assignee: Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.Inventors: Joachim Keinert, Thorsten Wolf
-
Patent number: 12026600Abstract: Systems and methods for target region evaluation and feature point evaluation are provided. The methods may include obtaining an image including a target region and extracting a plurality of feature points associated with the target region. The methods may further include, for each of the plurality of feature points, determining a sub-region including the feature point. The methods may further include performing a first grouping operation on the plurality of feature points to generate a plurality of first groups of sub-regions according to a first rule, and determining, based on the plurality of first groups of sub-regions, a confidence level associated with the target region using a plurality of trained models for processing the plurality of first groups of sub-regions, respectively. Each of the plurality of trained models may be associated with a set of model parameters. At least two sets of model parameters may be different.Type: GrantFiled: June 25, 2021Date of Patent: July 2, 2024Assignee: ZHEJIANG DAHUA TECHNOLOGY CO., LTD.Inventor: Xufeng Yu
-
Patent number: 12016696Abstract: This method for qualitatively evaluating human livers comprises: a step (301) of computing normalized histograms of colour channels from a portion of a photograph of a liver; a step (304) of loading coefficients obtained at the end of a training phase; a step (305) of extracting from the histograms values corresponding to variables retained at the end of the training phase; a step (306) of computing a linear combination of the extracted values weighted with the loaded coefficients; and a step (308, 309) of displaying information representative of the result of the computation of the linear combination.Type: GrantFiled: September 5, 2021Date of Patent: June 25, 2024Assignee: STELLA SURGICALInventor: Clément Labiche
-
Patent number: 12020408Abstract: Systems, apparatuses, and methods for performing optimized sharpening of images in non-linear and linear formats are disclosed. A system includes a blur filter and a sharpener. The blur filter receives an input image or video frame and provides blurred output pixels to a sharpener unit. The sharpener unit operates in linear or non-linear space depending on the format of the input frame. The sharpener unit includes one or more optimizations to generate sharpened pixel data in an area-efficient manner. The sharpened pixel data is then driven to a display.Type: GrantFiled: June 22, 2021Date of Patent: June 25, 2024Assignee: ATI Technologies ULCInventors: Vladimir Lachine, Keith Lee
-
Patent number: 12020481Abstract: A sports event video processing method is provided. The processing method includes: receiving a sports event input video; performing SOI detection on the sports event input video to obtain at least one SOI; performing logo detection and extraction on the at least one SOI to detect at least one logo; performing pixel-level rearrangement on the at least one detected logo; and outputting a sports event output video having completed pixel-level rearrangement.Type: GrantFiled: October 21, 2021Date of Patent: June 25, 2024Assignee: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTEInventors: Feng-Sheng Lin, Sheng-Han Wu, Ruen-Rone Lee
-
Patent number: 12014542Abstract: A computer-implemented method for selecting representative frames for videos is provided. The method includes receiving a video and identifying a set of features for each of the frames of the video. The features including frame-based features and semantic features. The semantic features identifying likelihoods of semantic concepts being present as content in the frames of the video. A set of video segments for the video is subsequently generated. Each video segment includes a chronological subset of frames from the video and each frame is associated with at least one of the semantic features. The method generates a score for each frame of the subset of frames for each video segment based at least on the semantic features, and selecting a representative frame for each video segment based on the scores of the frames in the video segment. The representative frame represents and summarizes the video segment.Type: GrantFiled: December 14, 2020Date of Patent: June 18, 2024Assignee: Google LLCInventors: Sanketh Shetty, Tomas Izo, Min-Hsuan Tsai, Sudheendra Vijayanarasimhan, Apostol Natsev, Sami Abu-El-Haija, George Dan Toderici, Susana Ricco, Balakrishnan Varadarajan, Nicola Muscettola, WeiHsin Gu, Weilong Yang, Nitin Khandelwal, Phuong Le
-
Patent number: 12014477Abstract: An image processing method and device, an image detecting method and system, and a storage medium are provided. The image processing method comprises: acquiring a target image; counting pixels of the target image to obtain a count value; adding compensation data at a peripheral position of an edge pixel of the target image according to the count value, to obtain pixel data of the compensated target image.Type: GrantFiled: October 14, 2021Date of Patent: June 18, 2024Assignee: BOE Technology Group Co., Ltd.Inventors: Dawei Tang, Jijing Huang, Qiong Wu, Ge Ou, Chuqian Zhong, Zhiliang Wang
-
Patent number: 12008769Abstract: Provided is an image processing apparatus including a memory storing one or more instructions, and a processor executing the one or more instructions stored in the memory, wherein the processor retargets a current frame image, based on a first scale factor for a previous frame image, a second scale factor for the current frame image, and a weight determined based on previous frame image data and current frame image data.Type: GrantFiled: November 11, 2019Date of Patent: June 11, 2024Assignee: SAMSUNG ELECTRONICS CO., LTD.Inventors: Dubok Park, Kwanghyun Won, Tammy Lee
-
Patent number: 12008737Abstract: Embodiments disclosed herein are generally related to a system for noise reduction in low signal to noise ratio imaging conditions. A computing system obtains a set of images of a specimen. The set of images includes at least two images of the specimen. The computing system inputs the set of images of the specimen into a trained denoising model. The trained denoising model is configured to output a single denoised image of the specimen. The computing system receives, as output from the trained denoising model, a single denoised image of the specimen.Type: GrantFiled: August 5, 2021Date of Patent: June 11, 2024Assignee: Nanotronics Imaging, Inc.Inventors: Denis Sharoukhov, Tonislav Ivanov, Jonathan Lee
-
Patent number: 11995831Abstract: A method of establishing a quantitative measure of contrast enhancement in contrast medical imaging through computer analysis of baseline and enhanced images allows statistical comparison of protocols and imaging parameters from routine hospital operations to enhance and evaluate such protocols and parameters.Type: GrantFiled: April 9, 2021Date of Patent: May 28, 2024Assignee: Wisconsin Alumni Research FoundationInventor: Timothy P. Szczykutowicz
-
Patent number: 11995869Abstract: Apparatus and methods for detecting an object in an image. One aspect of the method includes receiving a first image from an image sensor. The first image is obtained by the image sensor using a first focal length. A second image is received from the image sensor. The second image is obtained by the image sensor using a second focal length. One or more objects are detected in the first image and the second image. The one or more objects detected in the first image are combined with the one or more objects detected in the second image.Type: GrantFiled: September 28, 2021Date of Patent: May 28, 2024Assignee: Johnson Controls Tyco IP Holdings LLPInventors: Sourabh Singh Yadav, Rajkiran Kumar Gottumukkal
-
Patent number: 11990137Abstract: Disclosed are an information processing method and a terminal device. The method comprises: acquiring first information, wherein the first information is information to be processed by a terminal device; calling an operation instruction in a calculation apparatus to calculate the first information so as to obtain second information; and outputting the second information. By means of the examples in the present disclosure, a calculation apparatus of a terminal device can be used to call an operation instruction to process first information, so as to output second information of a target desired by a user, thereby improving the information processing efficiency. The present technical solution has advantages of a fast computation speed and high efficiency.Type: GrantFiled: December 11, 2020Date of Patent: May 21, 2024Assignee: SHANGHAI CAMBRICON INFORMATION TECHNOLOGY CO., LTD.Inventors: Tianshi Chen, Shaoli Liu, Zai Wang, Shuai Hu
-
Patent number: 11989890Abstract: The invention relates to method and system for automatically generating and labelling reference images. In some embodiments, the method includes tracking a plurality of highlighted objects in a set of input images along with audio data associated with the plurality of highlighted objects. The method further includes cropping each of the plurality of highlighted objects from each of the set of images based on tracking, contemporaneously capturing an audio clip associated with each of the plurality of highlighted objects from the audio data based on tracking, and labelling each of the plurality of highlighted objects based on text data generated from the audio clip associated with each of the plurality of objects to generate a labelled reference image.Type: GrantFiled: February 18, 2021Date of Patent: May 21, 2024Assignee: HCL Technologies LimitedInventors: Siva Sakthivel, Naveen Subramanian, Yuvarajan Shanmugasundaram, Sankareswari Amudhasidhanandham, Akhilesh Chandra Singh
-
Patent number: 11989948Abstract: Apparatuses, systems, and techniques to perform non-maximum suppression (NMS) with a bit-reduced radix sort to remove redundant bounding boxes are described. In at least one embodiment, one or more circuits perform i) a bit-reduced radix sort operation to sort a list of confidence scores associated with a set of bounding boxes corresponding to one or more objects within one or more digital images and ii) a non-maximum suppression (NMS) operation on the sorted list to remove one or more redundant bounding boxes from the set.Type: GrantFiled: October 13, 2021Date of Patent: May 21, 2024Assignee: Nvidia CorporationInventor: Zhimeng Fan
-
Patent number: 11983951Abstract: A human detection device configured to analyze a fisheye image obtained by a fisheye camera installed above a to-be-detected area to detect a person existing in the to-be-detected area includes a head detector configured to detect at least one head candidate from the fisheye image by using an algorithm for detecting a human head, a human body detector configured to detect at least one human body candidate from the fisheye image by using an algorithm for detecting a human body, and a determining unit configured to determine, as a person, a pair satisfying a prescribed condition among pairs of the head candidate and the human body candidate formed of a combination of a detection result from the head detector and a detection result from the human body detector.Type: GrantFiled: November 8, 2019Date of Patent: May 14, 2024Assignee: OMRON CORPORATIONInventors: Kiyoaki Tanaka, Ayana Tsuji, Jumpei Matsunaga
-
Patent number: 11978228Abstract: Embodiments for determining an orientation of a scanned image. In an exemplary embodiment, a method comprises receiving image data of an image of one or more objects. Each object of the one or more objects in the image includes a plurality of points on a surface of the object. The method further comprises generating a plurality of subsets of points of the plurality of points and fitting a parametric model to more than one subset of the plurality of subsets to generate a plurality of parametric models. Further, the method identifies a parametric model of the plurality of parametric models that includes the largest number of points and orients the image based on the parametric model that includes the largest number of points.Type: GrantFiled: November 21, 2019Date of Patent: May 7, 2024Assignee: KI MOBILITY LLCInventors: Douglas H. Munsey, Jr., Daniel H. Packard, Thomas J. Whelan, Patrick Abadi, William G. N. Coon, Robin D. Knight, Kimberly M. Wheeler
-
Patent number: 11972638Abstract: This application provides a face living body detection method performed by a computing device, the method including: obtaining a first face image of a target detection object in a first illumination condition and a second face image of the target detection object in a second illumination condition, determining a difference image according to the two images, decoupling an object reflectivity and an object normal vector corresponding to the target detection object from a feature map extracted from the difference image, and determining whether the target detection object is a living body according to the object reflectivity and the object normal vector. This method decouples texture information and depth information of a face, and performs living body detection by using decoupled information, which increases the defense capability against 3D attacks, thereby effectively defending against planar attacks and 3D attacks.Type: GrantFiled: October 28, 2021Date of Patent: April 30, 2024Assignee: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITEDInventors: Jian Zhang, Jia Meng, Taiping Yao, Ying Tai, Shouhong Ding, Jilin Li