Pixart Imaging Incorporated

Tsinghua University

National Applied Research Laboratories

National Taiwan University

Providence University

Wei-Chung Wang

Chi-Hung Huang

Hui-Hsuan Chen

Yung-Hsiang Chen

Hsin-Chia Chen

Chao-Chien Huang

Po-Chi Sung

Po-Ting Chen

Chu-Hung Nien

Wei-Chih Liao

Kao-Lang Liu

Sen-Huang Huang

Tai-Shan Liao

Kai-Shun Chen

Guo-Zhen Wang

Chi-Chieh Liao

Chun-Wei Chen

Yu-Han Chen

Ting-Yang Chang

Kuo-Hsiung Li

Po-Chuan Wang

Shih-Chin Lin

Chih-Wei Huang

Ming-Hsing Shen

Ting-Hui Wu

Da-Wei Chang

Chih-Hung Lu

Chuan-Wei Wang

Po-Yu Chen

Hsin-Hui Hsu

Hung-Ching Lai

Sheng-Ta Lee

Wei-Ren Chen

Cheng-Kuang Lee

Yu-Cheng Tseng

Cheng-Ying Chou

Chun-Li Chang

Jyh-Rou Sze

Chuan-Yi Tang

Wen-Yi Kang

Ya-Hsin Chang

Hsuan-Hao Hsu

Meng-Hsiu Li

Hsiao-Yu Chou

Tzi-Hung Chung

Guan-Ting Lai

Holger Roth

Tzung-Dau Wang

Wen-Jeng Lee

Yu-Cheng Huang

Chiu-Wang Tseng

Zheng-Yong Lu

Ching-Huan Kuo

Yu-Liang Yeh

Yu-An Chiang

Te-Heng Hung

Provided are a system and a method for cardiovascular risk prediction, where artificial intelligence is utilized to perform segmentation on non-contrast or contrast medical images to identify precise regions of the heart, pericardium, and aorta of a subject, such that the adipose tissue volume and calcium score can be derived from the medical images to assist in cardiovascular risk prediction. Also provided is a computer readable medium for storing a computer executable code to implement the method.

System and method for cardiovascular risk prediction and computer readable medium thereof

A medical image analyzing system and a medical image analyzing method are provided and include inputting at least one patient image into a first model of a neural network module to obtain a result having determined positions and ranges of an organ and a tumor of the patient image; inputting the result into a second model of a first analysis module and a third model of a second analysis module, respectively, to obtain at least one first prediction value and at least one second prediction value corresponding to the patient image; and outputting a determined result based on the first prediction value and the second prediction value. Further, processes between the first model, the second model and the third model can be automated, thereby improving identification rate of pancreatic cancer.

Medical image analyzing system for identifying pancreatic cancer using machine learning and method thereof

A system for obstacle detection adapted to a self-guiding machine is provided. The system includes a controller, a linear light source and a light sensor. The linear light source and the light sensor are set apart at a distance. When the linear light source emits an indicator light being a vertical linear light projected onto a path the self-guiding machine travels toward, the light sensor senses the indicator light. The vertical linear light is segmented into a first segment projected to a ground and a second segment projected to a floating obstacle when the self-guiding machine approaches the floating obstacle with a height from the ground and the indicator light is projected to the floating obstacle, in which the second segment of the light sensed by the light sensor is determined as the floating obstacle in front of the self-guiding machine.

System for obstacle detection

A medical image analyzing system and a medical image analyzing method are provided and include inputting at least one patient image into a first model of a first neural network module to obtain a result having determined positions and ranges of an organ and a tumor of the patient image; inputting the result into a plurality of second models of a second neural network module, respectively, to obtain a plurality of prediction values corresponding to each of the plurality of second models and a model number predicting having cancer in the plurality of prediction values; and outputting a determined result based on the model number predicting having cancer and a number threshold value. Further, processes between the first model and the second models can be automated, thereby improving identification rate of pancreatic cancer.

Medical image analyzing system and method thereof

An optical detection device includes a substrate, a housing, an optical modulating component, an optical sensor and a cover. The housing is disposed on the substrate and includes a first aperture. The housing is unvaried due to inspection standard or design requirement of the optical detection device. The optical modulating component is disposed on the housing and aligning with the first aperture. The optical sensor is disposed on the substrate and adapted to receive an optical signal passing through the optical modulating component and the first aperture. The cover is disposed on the housing to cover the first aperture. The cover is replaceable for attaching the cover varied for the inspection standard or the design requirement to the unvaried housing in response to a surface of the cover opposite to the housing matched and engaged with a light penetrating area on the optical navigation apparatus.

Optical detection device and optical navigation apparatus

A pressure detection device of detecting a forced state of a deformable object includes a body, an image sensor and a processor. The body is a deformable hollow structure. The body has an inner surface and an outer surface, and an identifiable vision feature is disposed on the inner surface. The image sensor is disposed inside the body and faces the inner surface of the body, and is adapted to capture a frame containing the identifiable vision feature on the inner surface. The processor is electrically connected with the image sensor, and adapted to analyze position variation of the identifiable vision feature within the captured frame for identifying a motion type of a gesture applied to the outer surface of the body.

Pressure detection device

Provided is a medical image analyzing system and a method thereof, which includes: acquiring a processed image having a segmentation label corresponding to a cancerous part of an organ (if present), generating a plurality of image patches therefrom, performing feature analysis on the image patches and model training to obtain prediction values, drawing a receiver operating characteristic curve using the prediction values, and determining a threshold with which determines whether the image patches are cancerous, so as to effectively improve the detection rate of, for example, pancreatic cancer.

There is provided a moving robot including a first light source module and a second light source module respectively project a first light section and a second light section, which are vertical light sections, in front of a moving direction, wherein the first light section and the second light section cross with each other at a predetermined distance in front of the moving robot so as to eliminate a detection dead zone between the first light source module and the second light source module in front of the moving robot to avoid collision with an object during operation.

Moving robot without detection dead zone

The disclosure is related to a system for obstacle detection adapted to a self-guiding machine. The system includes a controller for driving the system, a light emitter, and a light sensor. The light emitter and the light sensor are set apart at a distance. When the light emitter emits an indicator light being a vertical linear light projected onto a path the self-guiding machine travels toward, the light sensor senses the indicator light. The vertical linear light is segmented into a first segment projected to a ground and a second segment projected to a floating obstacle when the self-guiding machine approaches the floating obstacle with a height from the ground and the indicator light is projected to the floating obstacle, in which the second segment of the light sensed by the light sensor is determined as the floating obstacle in front of the self-guiding machine.

Provided are a medical image analyzing system and a method thereof, which mainly crop a plurality of image patches from a processed image including a segmentation label corresponding to a location of an organ, train a deep learning model with the image patches to obtain prediction values, and plot a receiver operating characteristic curve to determine a threshold which determines whether the image patches are cancerous, thereby effectively improving the detection rate of cancer.

An optical detection device is applied to an optical finger navigation apparatus and suitable for a variety of appearance demands in order to simplify product qualification procedure. The optical detection device includes a substrate, a housing, an optical sensor and a cover. The housing is disposed on the substrate and comprising a first aperture. The optical sensor is disposed on the substrate and adapted to receive an optical signal through the first aperture. The cover is disposed on the housing to cover the first aperture. The cover has a first surface and a second surface opposite to each other. The first surface with a contour matched with a shape of the housing is attached to the housing, and the second surface with a contour manufactured for a predefined appearance demand does not affect conjunction between the housing and the cover.

Optical detection device

There is provided a cleaning robot including a first light source module and a second light source module respectively project a first light section and a second light section, which are vertical light sections, in front of a moving direction, wherein the first light section and the second light section cross with each other at a predetermined distance in front of the cleaning robot so as to eliminate a detection dead zone between the first light source module and the second light source module in front of the cleaning robot to avoid collision with an object during operation.

Robot without detection dead zone

A joystick has a related control method to provide displayed object control function. The joystick includes a body, an image sensor and a processor. The body has a deformable bottom surface whereon a pattern is disposed. The image sensor is disposed under the body and adapted to capture a frame about the pattern. The processor is electrically connected with the image sensor and adapted to generate a displayed object control signal according to pattern variation within the frame.

Control method applied to a joystick

A method, an apparatus and a system for cell detection are provided. In the apparatus, a hyperspectrum module is used to capture information across electromagnetic spectrums from an image, a stereo camera module is used to capture three-dimensional image information, and the hyperspectrum module and the stereo camera module form a trinocular micro spectrometer. A microscopic optical module is provided for the two modules to form hyperspectrum and three-dimensional image information from a cell and its split cells via a lens. In the method, a series of continuous images are obtained within a time period. An observation image array with a plurality of observation image zones are provided to retrieve coordinates of a plurality of feature points at different times. Finally, a holistic cellular activity can be obtained by analyzing continuous hyperspectrum and 3D image information from the images over time.

Method, apparatus and system for cell detection

The disclosure is related to a method and a system for obstacle detection adapted to a self-guiding machine. The method is performed in the system including a controller for driving the system, a light emitter, a light sensor, an image processor and a central processor. The light emitter and the light sensor are set apart at a distance. When the light emitter emits an indicator light being projected onto a path the self-guiding machine travels toward, the light sensor senses the indicator light. An image containing the indicator light is generated. After analyzing the image, at least one feature of the indicator light being sensed can be obtained and used to obtain a spatial relationship between the self-guiding machine and an obstacle. The spatial relationship allows the system to determine if the self-guiding machine will collide with a wall or fall from a cliff.

Method, system for obstacle detection and a sensor subsystem

Growing community of inventors

Hsin-Chu, Taiwan

Wei-Chung Wang