Industrial Technology Research Institute

Sen-Yih Chou

Hsin-Cheng Lin

Yi-Sha Ku

Deh-Ming Shyu

Hsin-Yi Chen

Chih-Chia Chang

Yu-Hsin Lin

Chia-Hung Cho

Shu-Ping Dong

Chia-Liang Yeh

Wei-Te Hsu

Yu-Ying Lan

Kai-Ping Chuang

Yi-Chen Hsieh

Yu-Shan Chang

Chia-Lin Wu

Ting-Hsun Cheng

Ming-Jhe Du

Yu-Ju Chao

Chun-Jen Lin

Hsiao-Wei Liu

Chang-Hai Sung

Tseng-Wei Lai

An electronic device and a method for determining medical images are provided. The method includes: obtaining an input image; inputting the input image into a first machine learning model to generate a labeled image, wherein the labeled image includes a plurality of area images; inputting the labeled image into a second machine learning model to generate a plurality of area determination data corresponding to the plurality of area images; and displaying a determination result including the plurality of area determination data.

Electronic device and method for determining medical images

An image recognition method, a training system for an object recognition model and a training method for an object recognition model are provided. The image recognition method includes the following steps. At least one original sample image of an object in a field and an object range information and an object type information in the original sample image are obtained. At least one physical parameter is adjusted to generate plural simulated sample images of the object. The object range information and the object type information of the object in each of the simulated sample images are automatically marked. A machine learning procedure is performed to train an object recognition model. An image recognition procedure is performed on an input image.

Image recognition method, training system for object recognition model and training method for object recognition model

A recognition system and an image augmentation and training method thereof are provided. The image augmentation and training method of a recognition system includes the following steps. A plurality of image frames are obtained, wherein each of the image frames includes an object pattern. A plurality of environmental patterns are obtained. The object pattern is separated from each of the image frames. A plurality of image parameters are set. The image frames, based on the object patterns and the environmental patterns, are augmented according to the image parameters to increase the number of the image frames. A recognition model is trained using the image frames.

Recognition system and image augmentation and training method thereof

An integrated system of a physical consumption environment and a network consumption environment and a control method thereof are provided. The control method of the integrated system of the physical consumption environment and the network consumption environment includes the following steps. A biological characteristic image of a consumer in the physical consumer environment is obtained. The biological characteristic image is identified to obtain an identity information from an identity database. An activity of the consumer in the physical consumption environment is detected. A product followed by the consumer and/or a physical behavior information are obtained according to the activity of the consumer in the physical consumption environment. A network behavior information of the consumer in the network consumer environment is obtained according to the identity information. A price of the product is dynamically adjusted according to the physical behavior information and the network behavior information.

Integrated system of physical consumption environment and network consumption environment and control method thereof

An object identification method includes: establishing a training data base including a photographing distance of a training image and a training camera parameter; in photographing a target test object, obtaining a test image, a depth image, an RGB image and a test camera parameter; and based on the training database, the depth image and the test camera parameter, adjusting the RGB image wherein the adjusted RGB image having a size equivalent to the training image of the training database.

Object identification method and device

A sight vector detecting method includes: capturing a user image by an image capture unit and a depth capture unit to obtain a first image and a distance information; based on the first image and the distance information, finding an eye center location of the user; predicting a user sight location by a gaze model to find a target sight location of the user on a target; based on the eye center location of the user, finding a first word coordinate of the eye center location of the user; based on the target sight location of the user, finding a second word coordinate of the target sight location of the user; and based on the first word coordinate of the eye center location of the user and the second word coordinate of the target sight location of the user, calculating a sight vector of the user.

Sight vector detecting method and device

An image recognition method adapted to recognize a target image is provided. The method includes: providing the target image; training a learning database based on a plurality of feature blocks of the target image; randomly obtaining a plurality of incomplete feature blocks of the target image; adding the plurality of incomplete feature blocks into the learning database to form an enhancement learning database; and recognizing the target image based on the enhancement learning database. In addition, an image recognition device is also provided.

Image recognition method and device thereof

A temperature sensing apparatus configured to measure a temperature distribution of a surface to be measured is provided. The temperature sensing apparatus includes a lens set, a filtering module, a plurality of sensor arrays, and a processing unit. The lens set is configured to receive radiation from the surface to be measured. The filtering module is configured to filter the radiation from the lens set into a plurality of radiation portions respectively having different wavelengths. The sensor arrays are configured to respectively sense the radiation portions. The processing unit is configured to calculate an intensity ratio distribution of the radiation between the different wavelengths according to the radiation portions respectively sensed by the sensor arrays and determine the temperature distribution according to the intensity ratio distribution. A laser processing system and a temperature measuring method are also provided.

Temperature sensing apparatus, laser processing system, and temperature measuring method

A display measuring device for measuring a display, includes a photosensitive unit, a first rotation plane mirror, a second rotation plane mirror, a first lens module, a second lens module, and an optic reflecting unit. The first lens module projects a first incident image from the display to the first rotation plane mirror. The first rotation plane mirror reflects the projected first incident image from the first lens module to the optic reflecting unit. The second lens module projects a second incident image from the display to the second rotation plane mirror. The second rotation plane mirror reflects the projected second incident image from the second lens module to the optic reflecting unit. The optic reflecting unit reflects the reflected first incident image to the photosensitive unit, and reflects the reflected second incident image to the photosensitive unit.

Display measuring device

The present invention provides a method and system for high dynamic range image measurement which is configured to control the light intensity distribution through an optical modulating switch for adjusting the intensity of the light passing therethrough so as to control the light intensity distribution of the light projecting on an object or of the object light being sensed by a photo detector for preventing the optical sensing signals of the photo detector from over-saturating. After that, the optical sensing signals are compensated according to the optical intensity distribution modulated by the optical modulating switch so as to obtain an image data with high dynamic range.

Method and apparatus for high dynamic range image measurement

The present invention provides a scatterfield microscopical measuring method and apparatus, which combine scatterfield detecting technology into microscopical device so that the microscopical device is capable of measuring the sample whose dimension is under the limit of optical diffraction. The scatterfield microscopical measuring apparatus is capable of being controlled to focus uniform and collimated light beam on back focal plane of an objective lens disposed above the sample. By changing the position of the focus position on the back focal plane, it is capable of being adjusted to change the incident angle with respect to the sample.

Scatterfield microscopical measuring method and apparatus

A method and an apparatus are disclosed for scatterfield microscopical measurement. The method integrates a scatterometer and a bright-field microscope for enabling the measurement precision to be better than the optical diffraction limit. With the aforesaid method and apparatus, a detection beam is generated by performing a process on a uniform light using an LCoS (liquid crystal on silicon) or a DMD (digital micro-mirror device) which is to directed to image on the back focal plane of an object to be measured, and then scattered beams resulting from the detection beam on the object's surface are focused on a plane to form an optical signal which is to be detected by an array-type detection device. The detection beam can be oriented by the modulation device to illuminate on the object at a number of different angles, by which zero order or higher order diffraction intensities at different positions of the plane at different incident angles can be collected.

Method and apparatus for scatterfield microscopical measurement

A reflective scatterometer capable of measuring a sample is provided. The reflective scatterometer includes a paraboloid mirror, a light source, a first reflector, a second reflector and a detector. The paraboloid mirror has an optical axis and a parabolic surface, wherein the sample is disposed on the focal point of the parabolic surface and the normal direction of the sample is parallel with the optical axis. A collimated beam generated from the light source is reflected by the first reflector to the parabolic surface and then is reflected by the parabolic surface to the sample to form a first diffracted beam. The first diffracted beam is reflected by the parabolic surface to the second reflector and is then reflected by the second reflector to the detector.

Growing community of inventors

Hsinchu, Taiwan

Sen-Yih Chou