Abstract: A method for predicting clinical severity of a neurological disorder includes steps of: a) identifying, according to a magnetic resonance imaging (MRI) image of a brain, brain image regions each of which contains a respective portion of diffusion index values of a diffusion index, which results from image processing performed on the MRI image; b) for one of the brain image regions, calculating a characteristic parameter based on the respective portion of the diffusion index values; and c) calculating a severity score that represents the clinical severity of the neurological disorder of the brain based on the characteristic parameter of the one of the brain image regions via a prediction model associated with the neurological disorder.

Abstract: A method for laser processing a packaging box is provided, which includes feeding a paper material printed with a pattern on the front side thereof to a cutting machine by back feeding using an automatic paper feeder; performing edge finding on the rear side of the paper material, and forming indentations on the rear side of the paper material corresponding to where the pattern is on the front side; conveying the paper material to a laser cutting machine to perform registration marking on the rear side of the paper material before laser cutting; and finally performing laser cutting based on the registration markings to obtain a packaging box with the pattern printed on the front side and the indentations formed on the rear side.

Abstract: A method for laser processing a packaging box is provided, which includes feeding a paper material printed with a pattern on the front side thereof to a cutting machine by back feeding using an automatic paper feeder; performing edge finding on the rear side of the paper material, and forming indentations on the rear side of the paper material corresponding to where the pattern is on the front side; conveying the paper material to a laser cutting machine to perform registration marking on the rear side of the paper material before laser cutting; and finally performing laser cutting based on the registration markings to obtain a packaging box with the pattern printed on the front side and the indentations formed on the rear side.

Abstract: A laser integrated switching device for mounting on a laser cutting machine is disclosed, wherein it comprises a laser tube, a X/Y deflection laser outputting module, a triaxial deflection laser outputting module, a first optical path, a second optical path, and an optical path switcher; wherein the first optical path is disposed with both ends thereof connecting to the laser tube and the X/Y deflection laser outputting module, the second optical path is disposed with both ends thereof connecting to the laser tube and the triaxial deflection laser outputting module, and the optical path switcher is disposed between the first and second optical paths, thereby before the optical path switcher switches the laser beams to the first optical path or the second optical path, the laser tube alternately outputs laser beams to the X/Y deflection laser outputting module or the triaxial deflection laser outputting module.

Abstract: An optical inspection method for an optical inspection device comprising an optical lens is provided according to an embodiment of the disclosure. The optical inspection method includes: obtaining a first image of an object by the optical lens; performing an edge detection on the first image to obtain a second image comprising an edge pattern; and performing a defect inspection operation on the second image based on a neural network architecture to inspect a defect pattern in the second image. In addition, an optical inspection device and an optical inspection system are provided according to embodiments of the disclosure.

Abstract: A defect inspection system, connected to an automatic visual inspection device, is provided, including the followings. A re-inspection server (VRS) receives a defect image and a defect location. A training terminal stores trained modules. A classification terminal receives the defect image and the defect location, reads a target trained module corresponding to the defect image, classifies the defect image according to the target trained module to obtain a labeled defect image, and sends the labeled defect image to the VRS. A re-inspection terminal receives the labeled defect image from the VRS, and sends a verified operation corresponding to the labeled defect image to the VRS. A labeling re-inspection terminal receives the verified operation and the labeled defect image, and a labeling result corresponding to the labeled defect image. The VRS sends the labeling result and the labeled defect image to the training terminal to train a corresponding training module.

Abstract: The present invention is an automated optical inspection method using deep learning, comprising the steps of: providing a plurality of paired image combinations, wherein each said paired image combination includes at least one defect-free image and at least one defect-containing image corresponding to the defect-free image; providing a convolutional neural network to start a training mode of the convolutional neural network; inputting the plurality of paired image combinations into the convolutional neural network, and adjusting a weight of at least one fully connected layer of the convolutional neural network through backpropagation to complete the training mode of the convolutional neural network; and performing an optical inspection process using the trained convolutional neural network.

Abstract: The present disclosure provides an image-based classification system, comprising an image capturing device, and a processing device connected to the image capturing device. The image capturing device is used for capturing an image of an object. The object has a surface layer and an inner layer. The processing device is configured to use a deep learning model, perform image segmentation on the image of the object, define a surface-layer region and an inner-layer region of the image, and generate classification information. The surface-layer region and the inner-layer region correspond respectively to the surface layer and the inner layer of the object.

Abstract: A defect inspection system, connected to an automatic visual inspection device, is provided, including the followings. A re-inspection server (VRS) receives a defect image and a defect location. A training terminal stores trained modules. A classification terminal receives the defect image and the defect location, reads a target trained module corresponding to the defect image, classifies the defect image according to the target trained module to obtain a labeled defect image, and sends the labeled defect image to the VRS. A re-inspection terminal receives the labeled defect image from the VRS, and sends a verified operation corresponding to the labeled defect image to the VRS. A labeling re-inspection terminal receives the verified operation and the labeled defect image, and a labeling result corresponding to the labeled defect image. The VRS sends the labeling result and the labeled defect image to the training terminal to train a corresponding training module.

Abstract: An optical inspection method for an optical inspection device comprising an optical lens is provided according to an embodiment of the disclosure. The optical inspection method includes: obtaining a first image of an object by the optical lens; performing an edge detection on the first image to obtain a second image comprising an edge pattern; and performing a defect inspection operation on the second image based on a neural network architecture to inspect a defect pattern in the second image. In addition, an optical inspection device and an optical inspection system are provided according to embodiments of the disclosure.

Abstract: The present invention provides a dynamic automatic focus tracking system, comprising an image capturing device for capturing an image of a workpiece in a target picture-taking region; a driving device for adjusting a spacing between the image capturing device and the workpiece; and a focal length adjustment module coupled to the image capturing device and the driving device to generate a control signal according to a figure feature and a predefined figure feature in the image of the workpiece and send the control signal to the driving device, thereby adjusting a position of the image capturing device with the driving device.

Abstract: The present invention is an automated optical inspection method using deep learning, comprising the steps of: providing a plurality of paired image combinations, wherein each said paired image combination includes at least one defect-free image and at least one defect-containing image corresponding to the defect-free image; providing a convolutional neural network to start a training mode of the convolutional neural network; inputting the plurality of paired image combinations into the convolutional neural network, and adjusting a weight of at least one fully connected layer of the convolutional neural network through backpropagation to complete the training mode of the convolutional neural network; and performing an optical inspection process using the trained convolutional neural network.

Abstract: An automatic sensing and warning device for placing an intravenous drip includes a transmitter unit, a blocking unit, a receiver unit, and a fixing device. The transmitter unit is attachable to an injection site on a patient's hand and is operable to transmit an identification signal. The receiver unit is arranged on the blocking unit and includes a drive circuit and a warning device. The fixing device supports the blocking unit and the receiver unit on the intravenous drip pole. The RF receiver is set at a predetermined vertical distance from a drip chamber and areas above and below the RF receiver are respectively defined as dangerous and safe areas. When the injection site is spaced from the drip chamber by a distance shorter than the predetermined distance, the RF receiver receives the identification signal from the RF transmitter and the drive circuit activates the warning device to issue warnings.

Abstract: An automatic sensing and warning device for placing an intravenous drip includes a transmitter unit, a blocking unit, a receiver unit, and a fixing device. The transmitter unit is attachable to an injection site on a patient's hand and is operable to transmit an identification signal. The receiver unit is arranged on the blocking unit and includes a drive circuit and a warning device. The fixing device supports the blocking unit and the receiver unit on the intravenous drip pole. The RF receiver is set at a predetermined vertical distance from a drip chamber and areas above and below the RF receiver are respectively defined as dangerous and safe areas. When the injection site is spaced from the drip chamber by a distance shorter than the predetermined distance, the RF receiver receives the identification signal from the RF transmitter and the drive circuit activates the warning device to issue warnings.

Abstract: The present invention provides a dynamic automatic focus tracking system, comprising an image capturing device for capturing an image of a workpiece in a target picture-taking region; a driving device for adjusting a spacing between the image capturing device and the workpiece; and a focal length adjustment module coupled to the image capturing device and the driving device to generate a control signal according to a figure feature and a predefined figure feature in the image of the workpiece and send the control signal to the driving device, thereby adjusting a position of the image capturing device with the driving device.

Abstract: A printer inkjet head cleaning system for waste ink collection and inkjet head cleaning and protection comprises a frame, a pushing device and a cleaning device. An accommodating space is disposed inside the frame. A horizontal rail and an elevating rail are correspondingly disposed on two lateral sides of the frame respectively. A cover used for protecting an inkjet head is disposed on the pushing device. Two sides of the pushing device are movably coupled on the horizontal rails so that the pushing device can displace on the horizontal rails horizontally. A scraper is disposed on the cleaning device. Two sides of the cleaning device are movably coupled on the elevating rails. An end of the cleaning device is connected with the pushing device so that the cleaning device can displace on the elevating rails when the pushing device moves forward and backward.

Abstract: A fastener comprises a fixing frame, a sliding base as well as a sliding frame and a swinging arm disposed inside the sliding base. A beveled guide surface of a fastening hook of a fastening rod of the fixing frame is pressed against a front side wall of the sliding base for inserting the fastening hook into a fastening groove in order that the sliding frame is fixed by the fastening rod at a fastening position. When the sliding base moves along a detaching direction from the fastening position, a turning portion of the swinging arm can be turned by pressing against an actuating rod, and a pressing portion of the swinging arm is driven by the turning portion to push the fastening rod upward for unfastening the sliding frame.