Patents by Inventor Edzer Lienson Wu
Edzer Lienson Wu 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).
-
Patent number: 11600000Abstract: An image processing method includes: calculating an area of a first label of a first medical image of a plurality of medical images with a plurality of labels; obtaining a first determination result based on whether the area of the first label is greater than a threshold value; obtaining a second determination result based on whether a second medical image of the medical images adjacent to the first medical image includes a second label overlapping a first projection area of the first label on the second medical image; and selectively deleting the first label on the first medical image according to the first determination result and the second determination result. The present disclosure further provides an image processing system to perform the image processing method.Type: GrantFiled: December 23, 2020Date of Patent: March 7, 2023Assignee: HTC CorporationInventors: Hao-Jen Wang, Fu-Chieh Chang, Edzer Lienson Wu
-
Patent number: 11238374Abstract: The disclosure provides a method for verifying training data, a training system, and a computer program produce. The method includes: receiving a labelled result with a plurality of bounding regions, wherein the labelled result corresponds to an image, the bounding regions are labelled by a plurality of annotators, the annotators comprises a first annotator and a second annotator, and the bounding region comprises a first bounding region labelled by the first annotator and a second bounding region labelled by the second annotator; and determining the first bounding region and the second bounding region respectively corresponds to different two target objects or corresponds to one target object according to a similarity between the first bounding region and the second bounding region.Type: GrantFiled: August 23, 2019Date of Patent: February 1, 2022Assignee: HTC CorporationInventors: Hao-Cheng Kao, Chih-Yang Chen, Chun-Hsien Yu, Shan-Yi Yu, Edzer Lienson Wu, Che-Han Chang
-
Publication number: 20210192735Abstract: An image processing method includes: calculating an area of a first label of a first medical image of a plurality of medical images with a plurality of labels; obtaining a first determination result based on whether the area of the first label is greater than a threshold value; obtaining a second determination result based on whether a second medical image of the medical images adjacent to the first medical image includes a second label overlapping a first projection area of the first label on the second medical image; and selectively deleting the first label on the first medical image according to the first determination result and the second determination result. The present disclosure further provides an image processing system to perform the image processing method.Type: ApplicationFiled: December 23, 2020Publication date: June 24, 2021Inventors: Hao-Jen WANG, Fu-Chieh CHANG, Edzer Lienson WU
-
Publication number: 20200065623Abstract: The disclosure provides a method for verifying training data, a training system, and a computer program produce. The method includes: receiving a labelled result with a plurality of bounding regions, wherein the labelled result corresponds to an image, the bounding regions are labelled by a plurality of annotators, the annotators comprises a first annotator and a second annotator, and the bounding region comprises a first bounding region labelled by the first annotator and a second bounding region labelled by the second annotator; and determining the first bounding region and the second bounding region respectively corresponds to different two target objects or corresponds to one target object according to a similarity between the first bounding region and the second bounding region.Type: ApplicationFiled: August 23, 2019Publication date: February 27, 2020Applicant: HTC CorporationInventors: Hao-Cheng Kao, Chih-Yang Chen, Chun-Hsien Yu, Shan-Yi Yu, Edzer Lienson Wu, Che-Han Chang
-
Publication number: 20200065706Abstract: The disclosure provides a method for verifying training data, a training system, and a computer program produce. The method includes: providing a plurality of raw data to a plurality of annotators; retrieving a plurality of labelled results, wherein the labelled results includes a plurality of labelled data, and the labelled data are generated by the annotators via labelling the raw data; determining a plurality of consistencies by comparing the labelled results, and accordingly determining whether the labelled results are valid for training an artificial intelligence machine; in response to determining that the labelled results are valid, determining at least a specific part of the labelled results are valid for training the artificial intelligence machine.Type: ApplicationFiled: August 19, 2019Publication date: February 27, 2020Applicant: HTC CorporationInventors: Hao-Cheng Kao, Chih-Yang Chen, Chun-Hsien Yu, Shan-Yi Yu, Edzer Lienson Wu, Che-Han Chang
-
Patent number: 10222442Abstract: A method and apparatus for single carrier wideband magnetic resonance imaging (MRI) data acquisition are provided. The method includes the following steps: exciting a slice or slab with the use of RF pulse and a slice/slab selection gradient; applying a phase encoding gradient along a phase encoding direction and reducing a FOV along the phase encoding direction by a factor of W through k-space subsampling; applying a frequency encoding gradient along a frequency encoding direction and increasing a FOV along the frequency encoding direction by a factor of Wf; and applying a separation gradient along the phase encoding direction during the frequency encoding duration and k-space data acquisition.Type: GrantFiled: April 17, 2014Date of Patent: March 5, 2019Assignee: NATIONAL TAIWAN UNIVERSITYInventors: Jyh-Horng Chen, Tzi-Dar Chiueh, Edzer Lienson Wu, Yun-An Huang
-
Patent number: 9632157Abstract: The present invention discloses a 3-dimension magnetic resonance imaging method which comprises: applying a slab selection gradient to a subject; transmitting a radiofrequency pulse to the subject, and exciting a slab of the subject to produce magnetic resonance signals with a continuous frequency bandwidth; performing a spatial encoding gradient across three dimensions to encode the magnetic resonance signals, wherein an equivalent encoded field of view which along the selected acceleration direction is controlled by the spatial encoding gradient, and the equivalent encoded field of view is shorter than the excited slab size of the subject; applying a separation gradient along with the spatial encoding gradient; and receiving and reconstructing the encoded magnetic resonance signals to produce 3D images.Type: GrantFiled: March 29, 2013Date of Patent: April 25, 2017Assignee: NATIONAL TAIWAN UNIVERSITYInventors: Jyh-Horng Chen, Tzi-Dar Chiueh, Edzer Lienson Wu, Yun-An Huang
-
Publication number: 20140312899Abstract: A method and apparatus for single carrier wideband magnetic resonance imaging (MRI) data acquisition are provided. The method includes the following steps: exciting a slice or slab with the use of RF pulse and a slice/slab selection gradient; applying a phase encoding gradient along a phase encoding direction and reducing a FOV along the phase encoding direction by a factor of W through k-space subsampling; applying a frequency encoding gradient along a frequency encoding direction and increasing a FOV along the frequency encoding direction by a factor of Wf; and applying a separation gradient along the phase encoding direction during the frequency encoding duration and k-space data acquisition.Type: ApplicationFiled: April 17, 2014Publication date: October 23, 2014Applicant: National Taiwan UniversityInventors: Jyh-Horng Chen, Tzi-Dar Chiueh, Edzer Lienson Wu, Yun-An Huang
-
Publication number: 20140292326Abstract: The present invention discloses a 3-dimension magnetic resonance imaging method which comprises: applying a slab selection gradient to a subject; transmitting a radiofrequency pulse to the subject, and exciting a slab of the subject to produce magnetic resonance signals with a continuous frequency bandwidth; performing a spatial encoding gradient across three dimensions to encode the magnetic resonance signals, wherein an equivalent encoded field of view which along the selected acceleration direction is controlled by the spatial encoding gradient, and the equivalent encoded field of view is shorter than the excited slab size of the subject; applying a separation gradient along with the spatial encoding gradient; and receiving and reconstructing the encoded magnetic resonance signals to produce 3D images.Type: ApplicationFiled: March 29, 2013Publication date: October 2, 2014Applicant: National Taiwan UniversityInventors: Jyh-Horng Chen, Tzi-Dar Chiueh, Edzer Lienson Wu, Yun-An Huang
-
Patent number: 8687133Abstract: A stereoscopic display device includes a display panel, two different polarized backlights and a synchronization module. The display panel is used to alternately generate first visible images and second visible images. The two different polarized backlights are to alternately illuminate the display panel so as to output the first visible images and second visible images, respectively. The synchronization module is used to synchronize the first visible images and second visible images with illumination periods of the respective polarized backlights.Type: GrantFiled: August 16, 2011Date of Patent: April 1, 2014Inventor: Edzer Lienson Wu
-
Publication number: 20130044274Abstract: A stereoscopic display device includes a display panel, two different polarized backlights and a synchronization module. The display panel is used to alternately generate first visible images and second visible images. The two different polarized backlights are to alternately illuminate the display panel so as to output the first visible images and second visible images, respectively. The synchronization module is used to synchronize the first visible images and second visible images with illumination periods of the respective polarized backlights.Type: ApplicationFiled: August 16, 2011Publication date: February 21, 2013Inventor: EDZER LIENSON WU
-
Publication number: 20120007856Abstract: A stereoscopic display device includes a display panel, two different polarized backlights and a synchronization module. The display panel is to alternately generate left-eye visible images and right-eye visible images. The two different polarized backlights are to alternately illuminate the display panel so as to output the left-eye visible images and right-eye visible images, respectively. The synchronization module is to synchronize the left-eye visible images and right-eye visible images with illumination periods of the respective polarized backlights.Type: ApplicationFiled: April 13, 2011Publication date: January 12, 2012Inventor: Edzer Lienson Wu