Abstract: An outlier IC detection method includes acquiring first measured data of a first IC set, training the first measured data for establishing a training model, acquiring second measured data of a second IC set, generating predicted data of the second IC set by using the training model according to the second measured data, generating a bivariate dataset distribution of the second IC set according to the predicted data and the second measured data, acquiring a predetermined Mahalanobis distance on the bivariate dataset distribution of the second IC set, and identifying at least one outlier IC from the second IC set when at least one position of the at least one outlier IC on the bivariate dataset distribution is outside a range of the predetermined Mahalanobis distance.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.