Patents by Inventor Hsiang-Chen Wang
Hsiang-Chen Wang 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: 11962949Abstract: A method of performing air pollution estimation is provided. The method is to be implemented using a processor of a computer device and includes: generating a spectral image based on an original color image of an environment under test using a spectral transformation matrix; supplying the spectral image as an input into an estimating model for air pollution estimation; and obtaining an estimation result from the estimating model indicating a degree of air pollution of the environment under test.Type: GrantFiled: July 22, 2021Date of Patent: April 16, 2024Assignee: National Chung Cheng UniversityInventors: Hsiang-Chen Wang, Chia-Cheng Huang, Ting-Chun Men
-
Publication number: 20240094675Abstract: A method for inspecting authenticity of a hologram is provided. A computer device that stores a color image of the hologram transforms the color image into a hyperspectral image, converts the hyperspectral image into a grayscale image, and determines authenticity of the hologram based on multiple grayscale values in a region of interest in the grayscale image and multiple grayscale thresholds that respectively correspond to different wavelengths.Type: ApplicationFiled: March 1, 2023Publication date: March 21, 2024Inventors: Hsiang-Chen Wang, Yu-Ming Tsao, Arvind Mukundan
-
Patent number: 11928842Abstract: A method of measuring chromaticity of a target object is implemented using a computer device that stores a plurality of light source spectrum datasets each associated with a specific object. The method includes: obtaining a captured color image of the target object; generating a spectral image based on the captured color image using a spectral transformation matrix; obtaining one of the plurality of light source spectrum datasets that is associated with the target object; and calculating a chromaticity dataset of the target object based on the spectral image and the one of the plurality of light source spectrum datasets.Type: GrantFiled: April 26, 2022Date of Patent: March 12, 2024Assignee: National Chung Cheng UniversityInventors: Hsiang-Chen Wang, Yu-Ming Tsao, Yu-Lin Liu
-
Publication number: 20240027185Abstract: A method for measuring a thickness of a thin film layer disposed on a piece of glass is implemented using a computer device that stores a thin film image of the thin film layer, a surface dataset associated with a surface of the thin film layer, and a plurality of reference parameter sets each being associated with a specific thickness of the thin film layer, the method including: generating a spectral image dataset that includes spectral data associated with different pixels of the thin film image using a spectral transformation matrix; performing regression analysis on the surface dataset and the spectral image dataset, so as to obtain a thickness parameter set including a plurality of thickness parameters; and determining a thickness of the thin film layer using the thickness parameter set and the plurality of reference parameter sets.Type: ApplicationFiled: October 27, 2022Publication date: January 25, 2024Applicant: National Chung Cheng UniversityInventors: Hsiang-Chen Wang, Yu-Yang Chen, Yu-Ming Tsao, Yu-Lin Liu, Ching-Yi Huang
-
Patent number: 11810300Abstract: This application provides a method for detecting images of testing object using hyperspectral imaging. Firstly, obtaining a hyperspectral imaging information according to a reference image, hereby, obtaining corresponded hyperspectral image from an input image and obtaining corresponded feature values for operating Principal components analysis to simplify feature values. Then, obtaining feature images by Convolution kernel, and then positioning an image of an object under detected by a default box and a boundary box from the feature image. By Comparing with the esophageal cancer sample image, the image of the object under detected is classifying to an esophageal cancer image or a non-esophageal cancer image. Thus, detecting an input image from the image capturing device by the convolutional neural network to judge if the input image is the esophageal cancer image for helping the doctor to interpret the image of the object under detected.Type: GrantFiled: August 5, 2021Date of Patent: November 7, 2023Assignee: National Chung Cheng UniversityInventors: Hsiang-Chen Wang, Tsung-Yu Yang, Yu-Sheng Chi, Ting-Chun Men
-
Publication number: 20230306720Abstract: A method for recognizing arteries and veins on a fundus image includes: executing a pre-process operation on the fundus image, so as to obtain a pre-processed fundus image; generating a fundus spectral reflection dataset associated with pixels of the pre-processed fundus image, based on the pre-processed fundus image, and a spectral transformation matrix; obtaining a plurality of principle component scores associated with the pixels of the pre-processed fundus image, respectively; and determining, for each of the pixels of the pre-processed fundus image that has been determined as a part of a blood vessel, whether the pixel belongs to a part of an artery or a part of a vein.Type: ApplicationFiled: July 22, 2022Publication date: September 28, 2023Inventors: Hsiang-Chen WANG, Yu-Ming TSAO, Yong-Song CHEN, Yu-Sin LIU, Shih-Wun LIANG
-
Patent number: 11761961Abstract: A biosensing chip is provided, including a substrate having a photoelectric conversion material, and an electrode disposed on the substrate and including two contact portions and an electrode pattern, wherein the photoelectric conversion material is a monocrystalline silicon material, and the electrode pattern includes micro-electrodes in the form of interdigitated sawtooth. The biosensing chip and the method using the same may distinguish a lesion site of cancer cells and the degree of cancer lesions.Type: GrantFiled: July 20, 2020Date of Patent: September 19, 2023Assignee: NATIONAL CHUNG CHENG UNIVERSITYInventors: Hsiang-Chen Wang, Chun-Ping Jen, Hong-Wei Fan, Shin-Che Wang
-
Publication number: 20230281818Abstract: The present application related to a method for detecting image using hyperspectral imaging by band selection. Firstly, obtaining a hyperspectral imaging information according to a reference image, hereby, obtaining corresponded hyperspectral image from an input image, and obtaining corresponded feature values by band selection for operating Principal components analysis to simplify feature values. Then, obtaining feature images by Convolution kernel, and then positioning an image of an object under detected by a default box and a boundary box from the feature image. By Comparing with the esophageal cancer sample image, the image of the object under detected is classifying to an esophageal cancer image or a non-esophageal cancer image. Thus, detecting an input image from the image capturing device by the convolutional neural network to judge if the input image is the esophageal cancer image for helping the doctor to interpret the image of the object under detected.Type: ApplicationFiled: January 31, 2023Publication date: September 7, 2023Inventors: HSIANG-CHEN WANG, YU-SHENG CHI, YU-MING TSAO, SIAN-HONG SHIH
-
Publication number: 20230282010Abstract: The present application discloses a method for detecting image by using semantic segmentation. To input an image with data augmentation, and then encode and decode using a neural network. At least one semantically divided, and finally the at least one semantically divided is compared with the sample to classify as a target or a non-target. In this way, the CNN is used to detect whether the image is the SCC image or not, and locate the section, thereby assisting the doctor in interpreting the esophagus image.Type: ApplicationFiled: January 31, 2023Publication date: September 7, 2023Inventors: HSIANG-CHEN WANG, KUAN-LIN CHEN, YU-MING TSAO, JEN-FENG HSU
-
Publication number: 20230281962Abstract: A method for detecting objects in hyperspectral imaging is revealed. First obtaining a hyperspectral imaging information by a reference image. Then converting an input image according to the hyperspectral imaging information to get a hyperspectral image. A plurality of hyperspectral eigenvalues is obtained after image analysis of the hyperspectral image. Next getting a plurality of dimensionality reduction eigenvalues by a principal component analysis (PCA). Then performing convolution operation on the dimensionality reduction eigenvalues to get a value of a convolution matrix for extracting a feature image from an image of an object to be detected in the input image. Generating an anchor box and a prediction box in the feature image to get a bounded image. Lastly matching and comparing the bounded image with a sample image to determine whether the input image is a target object image. Thereby the method provides assistance for physicians in gastrointestinal image diagnosis.Type: ApplicationFiled: February 7, 2023Publication date: September 7, 2023Inventors: HSIANG-CHEN WANG, TING-CHUN MEN, YU-MING TSAO, YU-LIN LIU
-
Publication number: 20230154049Abstract: A method of measuring chromaticity of a target object is implemented using a computer device that stores a plurality of light source spectrum datasets each associated with a specific object. The method includes: obtaining a captured color image of the target object; generating a spectral image based on the captured color image using a spectral transformation matrix; obtaining one of the plurality of light source spectrum datasets that is associated with the target object; and calculating a chromaticity dataset of the target object based on the spectral image and the one of the plurality of light source spectrum datasets.Type: ApplicationFiled: April 26, 2022Publication date: May 18, 2023Inventors: Hsiang-Chen WANG, Yu-Ming TSAO, Yu-Lin LIU
-
Patent number: 11580637Abstract: The present application related to a method for detecting an object image using a convolutional neural network. Firstly, obtaining feature images by Convolution kernel, and then positioning an image of an object under detected by a default box and a boundary box from the feature image. By Comparing with the sample image, the detected object image is classifying to an esophageal cancer image or a non-esophageal cancer image. Thus, detecting an input image from the image capturing device by the convolutional neural network to judge if the input image is the esophageal cancer image for helping the doctor to interpret the detected object image.Type: GrantFiled: October 27, 2020Date of Patent: February 14, 2023Assignee: National Chung Cheng UniversityInventors: Hsiang-Chen Wang, Hao-Yi Syu, Tsung-Yu Yang, Yu-Sheng Chi
-
Publication number: 20230015055Abstract: This application provides a method for detecting images of testing object using hyperspectral imaging. Firstly, obtaining a hyperspectral imaging information according to a reference image, hereby, obtaining corresponded hyperspectral image from an input image and obtaining corresponded feature values for operating Principal components analysis to simplify feature values. Then, obtaining feature images by Convolution kernel, and then positioning an image of an object under detected by a default box and a boundary box from the feature image. By Comparing with the esophageal cancer sample image, the image of the object under detected is classifying to an esophageal cancer image or a non-esophageal cancer image. Thus, detecting an input image from the image capturing device by the convolutional neural network to judge if the input image is the esophageal cancer image for helping the doctor to interpret the image of the object under detected.Type: ApplicationFiled: August 5, 2021Publication date: January 19, 2023Inventors: HSIANG-CHEN WANG, TSUNG-YU YANG, YU-SHENG CHI, TING-CHUN MEN
-
Patent number: 11555996Abstract: A method for analyzing 2D material thin film and a system for analyzing 2D material thin film are disclosed. The detection method includes the following steps: capturing sample images of 2D material thin films; measuring the 2D material thin films by a Raman spectrometer; performing a visible light hyperspectral algorithm on the sample images by a processor to generate a plurality of visible light hyperspectral images; performing a training and validation procedure, performing an image feature algorithm on the visible light hyperspectral images, and establishing a thin film prediction model based on a validation; and capturing a thin-film image to be measured by the optical microscope, performing the visible light hyperspectral algorithm, and then generating a distribution result of the thin-film image to be measured according to an analysis of the thin film prediction model.Type: GrantFiled: April 20, 2021Date of Patent: January 17, 2023Assignee: NATIONAL CHUNG CHENG UNIVERSITYInventors: Hsiang-Chen Wang, Kai-Chun Li, Kai-Hsiang Ke, Chun-Wen Liang
-
Publication number: 20220303516Abstract: A method of performing air pollution estimation is provided. The method is to be implemented using a processor of a computer device and includes: generating a spectral image based on an original color image of an environment under test using a spectral transformation matrix; supplying the spectral image as an input into an estimating model for air pollution estimation; and obtaining an estimation result from the estimating model indicating a degree of air pollution of the environment under test.Type: ApplicationFiled: July 22, 2021Publication date: September 22, 2022Inventors: Hsiang-Chen WANG, Chia-Cheng HUANG, Ting-Chun MEN
-
Publication number: 20210374949Abstract: The present application related to a method for detecting an object image using a convolutional neural network. Firstly, obtaining feature images by Convolution kernel, and then positioning an image of an object under detected by a default box and a boundary box from the feature image. By Comparing with the sample image, the detected object image is classifying to an esophageal cancer image or a non-esophageal cancer image. Thus, detecting an input image from the image capturing device by the convolutional neural network to judge if the input image is the esophageal cancer image for helping the doctor to interpret the detected object image.Type: ApplicationFiled: October 27, 2020Publication date: December 2, 2021Inventors: HSIANG-CHEN WANG, HAO-YI SYU, TSUNG-YU YANG, YU-SHENG CHI
-
Publication number: 20210349299Abstract: A method for analyzing 2D material thin film and a system for analyzing 2D material thin film are disclosed. The detection method includes the following steps: capturing sample images of 2D material thin films; measuring the 2D material thin films by a Raman spectrometer; performing a visible light hyperspectral algorithm on the sample images by a processor to generate a plurality of visible light hyperspectral images; performing a training and validation procedure, performing an image feature algorithm on the visible light hyperspectral images, and establishing a thin film prediction model based on a validation; and capturing a thin-film image to be measured by the optical microscope, performing the visible light hyperspectral algorithm, and then generating a distribution result of the thin-film image to be measured according to an analysis of the thin film prediction model.Type: ApplicationFiled: April 20, 2021Publication date: November 11, 2021Inventors: HSIANG-CHEN WANG, KAI-CHUN LI, KAI-HSIANG KE, CHUN-WEN LIANG
-
Publication number: 20210318313Abstract: A biosensing chip is provided, including a substrate having a photoelectric conversion material, and an electrode disposed on the substrate and including two contact portions and an electrode pattern, wherein the photoelectric conversion material is a monocrystalline silicon material, and the electrode pattern includes micro-electrodes in the form of interdigitated sawtooth. The biosensing chip and the method using the same may distinguish a lesion site of cancer cells and the degree of cancer lesions.Type: ApplicationFiled: July 20, 2020Publication date: October 14, 2021Applicant: NATIONAL CHUNG CHENG UNIVERSITYInventors: HSIANG-CHEN WANG, Chun-Ping Jen, Hong-Wei Fan, Shin-Che Wang
-
Patent number: 9958126Abstract: A laser headlight optical module is disclosed herein and comprises a laser light source, a convex lens, a substrate, a mirror set, supporting rods, and a driving member. The laser light source generates a laser light and the convex lens is located at a transmitting path of the laser light generated from the laser light source and configured to focus the laser light. Yellow fluorescent powders are coated on the substrate. The mirror set is located at a transmitting path of the laser light reflected from the substrate with the phosphor layer. The supporting rods are located behind the mirror set to support the mirror set. The driving member is located behind the mirror set and connected with the supporting rods. The driving member drives the supporting rods to change a light reflective surface of the mirror set to vary an optical field.Type: GrantFiled: December 29, 2015Date of Patent: May 1, 2018Assignee: National Chung Cheng UniversityInventors: Hsiang-Chen Wang, Yuan-De Su, Yao-Ting Chiang
-
Patent number: 9895112Abstract: A cancerous lesion identifying method via hyper-spectral imaging technique comprises steps of: acquiring a plurality of first pathology images via an endoscopy, wherein the first pathology images are cancerous lesion images respectively; importing the first pathology images into an image processing module to acquire a plurality of first simulating spectra of the first pathology images so as to generate a principle component score diagram in accordance with the first simulating spectra; defining a plurality of triangle areas in the principle component score diagram in accordance with the first simulating spectra; determining whether a principle component score of a second simulating spectrum of a second pathology image is within any one of the triangle areas; and confirming the second pathology image belongs to one of the cancerous lesion images when the principle component score of the second simulating spectrum is within any one of the triangle areas.Type: GrantFiled: May 4, 2016Date of Patent: February 20, 2018Assignee: National Chung Cheng UniversityInventors: Hsiang-Chen Wang, Shin-Hua Chen, Shih-Wei Huang, Chiu-Jung Lai, Chu-Chi Ting