National Chung Cheng University

Hsiang-Chen Wang

Yu-ming Tsao

Chu-Chi Ting

Yu-Sheng Chi

Tsung-Yu Yang

Chun-Ping Jen

Fang-Hsuan Cheng

Fu-Jie Hsu

Zih-Hao Ye

Yu-Ming Tsao

Yuan-De Su

Ting-Chun Men

I-Chen Wu

Sian-hong Shih

Chia-Cheng Huang

Yu-Lin Liu

Chung-Yi Lin

Bing-hsuan Liang

Arvind Mukundan

Yu-Sin Liu

Chang-Hung Li

Yong-Song Chen

Jen-Feng Hsu

Yao-Ting Chiang

Guan-Huang Wu

Chia-Hao Tsai

Ching-Te Huang

Kai-Chun Li

Chiu-Jung Lai

Jhe-Ming Yang

Kai-Hsiang Ke

Chun-Wen Liang

Shin-Hua Chen

Tsung-Chih Lin

Hao-Yi Syu

Yao-Kuang Wang

Jung-Ming Yeh

Shih-Wun Liang

Zhi-Lin Hu

Kuan-Lin Chen

Chih-You Kuo

Ta-Wei Chien

Shin-Che Wang

Shih-Wei Huang

Ju-Hsiu Hsiao

Hong-Wei Fan

The present invention provides a method for detecting tissue hemorrhage with image analysis. A host produces a plurality of hyperspectral image information according to a plurality of reference images. An image extraction unit extracts an input image to the host. The host transforms the input image according to the plurality of hyperspectral image information to produce a hyperspectral input image. The host produces an input image spectrum according to the hyperspectral input image. The host performs a feature operation on the input image spectrum according to a preset cell band corresponding to a surface cell of small intestine for generating a plurality of corresponding feature bands. The host performs at least one convolution operation on the plurality of feature bands according to a plurality of kernels for producing a convolution result. The host matches and compares the convolution result with at least one hyperspectral sample band of at least one hyperspectral sample spectrum of at least one hyperspectral sample image for producing at least one comparison result. Finally the host judges if hemorrhage occurs on the surface layer of small intestine according to the comparison result.

Method for detect tissue hemorrhage with image analysis

A method for image analysis of predicted cell metastasis is provided. A host performs principle component analysis (PCA) for analysis and conversion of reference images into hyperspectral image information. Then an image capture unit sends input images to the host. The host converts the input images into hyperspectral images according to the hyperspectral image information and gets spectral information of the hyperspectral images. Next the host selects a plurality of wave bands corresponding to esophageal cancer cells and performs feature computation of the spectral information to generate corresponding features images. Then the host performs convolution of the feature images with kernels to get a convolution result. Later the host matches the convolution result with sample spectra of sample images to get a comparison result. Lastly the host determines whether metastasis of esophageal cancer cells occurs according to the comparison result.

Method for image analysis of predicted cell metastasis

The present application related to a method for deleting redundant images of an endoscope. Firstly, a host receives an input image datum from an endoscopy, hereby, capturing a plurality of corresponded input images from the input image data. Next, a plurality of dimension reduction data are obtained to operate with at least one adjacent dimension reduction datum, and then, a plurality of root mean squared error values are obtained to compare with an error threshold value. Hereby, at least one image unarrived the error threshold value are deleted to obtain a plurality of screened images. Thus, redundant images in the input image data of the endoscopy will be deleted to prevent from performing an image analysis of same images or approximated images.

Method for deleting redundant images of endoscope

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.

Method for detecting object image using hyperspectral imaging by band selection

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.

Method for detecting image by semantic segmentation

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.

Method for recognizing arteries and veins on a fundus image using hyperspectral imaging technique

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.

Method of air pollution estimation based on spectral image processing

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.

Method and apparatus for measuring chromaticity of a target object

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.

Method for detecting image of esophageal cancer using hyperspectral imaging

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.

Biosensing chip and method for distinguishing cancer lesion site and degree of cancer lesions

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.

Method for detecting image of object using convolutional neural network

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.

Method and system for analyzing 2D material thin film

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.

Laser headlight system and laser headlight optical module thereof

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.

Cancerous lesion identifying method via hyper-spectral imaging technique

A light-mixing flashlight has a body, three light-emitting diodes, three first reflectors, and three second reflectors. The body has a mounting surface formed in the body, a body opening opposite to the mounting surface, and three light recesses formed in an interior of the body. The light-emitting diodes are mounted in the light recesses, and are respectively a red light, a green light, and a blue light light-emitting diode. The first reflectors are formed as parabolic mirrors and are respectively mounted in the light recesses via a working angle. An opening of each first reflector faces toward the corresponding light-emitting diode. The second reflectors are formed as spherical mirrors, are mounted on the mounting surface, and respectively correspond in position to the first reflectors. Therefore, the light-mixing flashlight has an improved emitting efficiency.

Light-mixing flashlight

Growing community of inventors

Chiayi County, Taiwan

Hsiang-Chen Wang