Patents by Inventor Kuang-Huei Lee
Kuang-Huei Lee has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240144467Abstract: A hot spot defect detecting method and a hot spot defect detecting system are provided. In the method, hot spots are extracted from a design of a semiconductor product to define a hot spot map comprising hot spot groups, wherein local patterns in a same context of the design yielding a same image content are defined as a same hot spot group. During runtime, defect images obtained by an inspection tool performing hot scans on a wafer manufactured with the design are acquired and the hot spot map is aligned to each defect image to locate the hot spot groups. The hot spot defects in each defect image are detected by dynamically mapping the hot spot groups located in each defect image to a plurality of threshold regions and respectively performing automatic thresholding on pixel values of the hot spots of each hot spot group in the corresponding threshold region.Type: ApplicationFiled: January 8, 2024Publication date: May 2, 2024Applicant: Taiwan Semiconductor Manufacturing Company, Ltd.Inventors: Chien-Huei Chen, Pei-Chao Su, Xiaomeng Chen, Chan-Ming Chang, Shih-Yung Chen, Hung-Yi Chung, Kuang-Shing Chen, Li-Jou Lee, Yung-Cheng Lin, Wei-Chen Wu, Shih-Chang Wang, Chien-An Lin
-
Patent number: 11372914Abstract: The description relates to diversified hybrid image annotation for annotating images. One implementation includes generating first image annotations for a query image using a retrieval-based image annotation technique. Second image annotations can be generated for the query image using a model-based image annotation technique. The first and second image annotations can be integrated to generate a diversified hybrid image annotation result for the query image.Type: GrantFiled: March 26, 2018Date of Patent: June 28, 2022Assignee: Microsoft Technology Licensing, LLCInventors: Yokesh Kumar, Kuang-Huei Lee, Houdong Hu, Li Huang, Arun Sacheti, Meenaz Merchant, Linjun Yang, Tianjun Xiao, Saurajit Mukherjee
-
Patent number: 11093560Abstract: The present concepts relate to matching data of two different modalities using two stages of attention. First data is encoded as a set of first vectors representing components of the first data, and second data is encoded as a set of second vectors representing components of the second data. In the first stage, the components of the first data are attended by comparing the first vectors and the second vectors to generate a set of attended vectors. In the second stage, the components of the second data are attended by comparing the second vectors and the attended vectors to generate a plurality of relevance scores. Then, the relevance scores are pooled to calculate a similarity score that indicates a degree of similarity between the first data and the second data.Type: GrantFiled: September 21, 2018Date of Patent: August 17, 2021Assignee: Microsoft Technology Licensing, LLCInventors: Kuang-Huei Lee, Gang Hua, Xi Chen, Houdong Hu, He Xiaodong
-
Patent number: 10997468Abstract: Non-limiting examples described herein relate to ensemble model processing for image recognition that improves precision and recall for image recognition processing as compared with existing solutions. An exemplary ensemble model is configured enhance image recognition processing through aggregate data modeling processing that evaluates image recognition prediction results obtained through processing that comprises: nearest neighbor visual search analysis, categorical image classification analysis and/or categorical instance retrieval analysis. An exemplary ensemble model is scalable, where new segments/categories can be bootstrapped to build deeper learning models and achieve high precision image recognition, while the cost of implementation (including from a bandwidth and resource standpoint) is lower than what is currently available across the industry today.Type: GrantFiled: February 24, 2020Date of Patent: May 4, 2021Assignee: Microsoft Technology Licensing, LLCInventors: Arun Sacheti, Fnu Yokesh Kumar, Saurajit Mukherjee, Nikesh Srivastava, Yan Wang, Kuang-Huei Lee, Surendra Ulabala
-
Publication number: 20200193237Abstract: Non-limiting examples described herein relate to ensemble model processing for image recognition that improves precision and recall for image recognition processing as compared with existing solutions. An exemplary ensemble model is configured enhance image recognition processing through aggregate data modeling processing that evaluates image recognition prediction results obtained through processing that comprises: nearest neighbor visual search analysis, categorical image classification analysis and/or categorical instance retrieval analysis. An exemplary ensemble model is scalable, where new segments/categories can be bootstrapped to build deeper learning models and achieve high precision image recognition, while the cost of implementation (including from a bandwidth and resource standpoint) is lower than what is currently available across the industry today.Type: ApplicationFiled: February 24, 2020Publication date: June 18, 2020Inventors: Arun Sacheti, FNU Yokesh Kumar, Saurajit Mukherjee, Nikesh Srivastava, Yan Wang, Kuang-Huei Lee, Surendra Ulabala
-
Patent number: 10607118Abstract: Non-limiting examples described herein relate to ensemble model processing for image recognition that improves precision and recall for image recognition processing as compared with existing solutions. An exemplary ensemble model is configured enhance image recognition processing through aggregate data modeling processing that evaluates image recognition prediction results obtained through processing that comprises: nearest neighbor visual search analysis, categorical image classification analysis and/or categorical instance retrieval analysis. An exemplary ensemble model is scalable, where new segments/categories can be bootstrapped to build deeper learning models and achieve high precision image recognition, while the cost of implementation (including from a bandwidth and resource standpoint) is lower than what is currently available across the industry today.Type: GrantFiled: December 13, 2017Date of Patent: March 31, 2020Assignee: Microsoft Technology Licensing, LLCInventors: Arun Sacheti, FNU Yokesh Kumar, Saurajit Mukherjee, Nikesh Srivastava, Yan Wang, Kuang-Huei Lee, Surendra Ulabala
-
Publication number: 20200097604Abstract: The present concepts relate to matching data of two different modalities using two stages of attention. First data is encoded as a set of first vectors representing components of the first data, and second data is encoded as a set of second vectors representing components of the second data. In the first stage, the components of the first data are attended by comparing the first vectors and the second vectors to generate a set of attended vectors. In the second stage, the components of the second data are attended by comparing the second vectors and the attended vectors to generate a plurality of relevance scores. Then, the relevance scores are pooled to calculate a similarity score that indicates a degree of similarity between the first data and the second data.Type: ApplicationFiled: September 21, 2018Publication date: March 26, 2020Applicant: Microsoft Technology Licensing, LLCInventors: Kuang-Huei LEE, Gang HUA, Xi CHEN, Houdong HU, He XIAODONG
-
Publication number: 20200019628Abstract: Representative embodiments disclose mechanisms to perform visual intent classification or visual intent detection or both on an image. Visual intent classification utilizes a trained machine learning model that classifies subjects in the image according to a classification taxonomy. The visual intent classification can be used as a pre-triggering mechanism to initiate further action in order to substantially save processing time. Example further actions include user scenarios, query formulation, user experience enhancement, and so forth. Visual intent detection utilizes a trained machine learning model to identify subjects in an image, place a bounding box around the image, and classify the subject according to the taxonomy. The trained machine learning model utilizes multiple feature detectors, multi-layer predictions, multilabel classifiers, and bounding box regression.Type: ApplicationFiled: July 16, 2018Publication date: January 16, 2020Inventors: Xi Chen, Houdong Hu, Li Huang, Jiapei Huang, Arun Sacheti, Linjun Yang, Rui Xia, Kuang-Huei Lee, Meenaz Merchant, Sean Chang Culatana
-
Publication number: 20190294705Abstract: The description relates to diversified hybrid image annotation for annotating images. One implementation includes generating first image annotations for a query image using a retrieval-based image annotation technique. Second image annotations can be generated for the query image using a model-based image annotation technique. The first and second image annotations can be integrated to generate a diversified hybrid image annotation result for the query image.Type: ApplicationFiled: March 26, 2018Publication date: September 26, 2019Applicant: Microsoft Technology Licensing, LLCInventors: Yokesh KUMAR, Kuang-Huei LEE, Houdong HU, Li HUANG, Arun SACHETI, Meenaz MERCHANT, Linjun YANG, Tianjun XIAO, Saurajit MUKHERJEE
-
Patent number: 10395370Abstract: A method and a wearable apparatus for disease diagnosis are provided. The method is applied to the wearable apparatus with an image capturing unit and a display unit. In this method, a plurality of input images in a field of view of the wearable apparatus are captured by using the image capturing unit, wherein each of the input images contains an array of pixels. The variations of the pixel values in a time domain are analyzed. The pixel variations within a specific frequency range are magnified and the magnified pixel variations are added onto the original ones to generate an output image. The output image is overlapped with a current image in the field of view of the wearable apparatus and displayed on the display unit.Type: GrantFiled: August 27, 2015Date of Patent: August 27, 2019Assignee: National Taiwan UniversityInventors: Hao-Ming Hsiao, Hsien-Li Kao, Kuang-Huei Lee, Dian-Ru Li
-
Publication number: 20190180146Abstract: Non-limiting examples described herein relate to ensemble model processing for image recognition that improves precision and recall for image recognition processing as compared with existing solutions. An exemplary ensemble model is configured enhance image recognition processing through aggregate data modeling processing that evaluates image recognition prediction results obtained through processing that comprises: nearest neighbor visual search analysis, categorical image classification analysis and/or categorical instance retrieval analysis. An exemplary ensemble model is scalable, where new segments/categories can be bootstrapped to build deeper learning models and achieve high precision image recognition, while the cost of implementation (including from a bandwidth and resource standpoint) is lower than what is currently available across the industry today.Type: ApplicationFiled: December 13, 2017Publication date: June 13, 2019Inventors: Arun Sacheti, FNU Yokesh Kumar, Saurajit Mukherjee, Nikesh Srivastava, Yan Wang, Kuang-Huei Lee, Surendra Ulabala
-
Publication number: 20160078622Abstract: A method and a wearable apparatus for disease diagnosis are provided. The method is applied to the wearable apparatus with an image capturing unit and a display unit. In this method, a plurality of input images in a field of view of the wearable apparatus are captured by using the image capturing unit, wherein each of the input images contains an array of pixels. The variations of the pixel values in a time domain are analyzed. The pixel variations within a specific frequency range are magnified and the magnified pixel variations are added onto the original ones to generate an output image. The output image is overlapped with a current image in the field of view of the wearable apparatus and displayed on the display unit.Type: ApplicationFiled: August 27, 2015Publication date: March 17, 2016Inventors: Hao-Ming Hsiao, Hsien-Li Kao, Kuang-Huei Lee, Dian-Ru Li