Abstract: In an image comparison method, an original reference image and an original test image are obtained. The original reference image and the original test image are binarized to obtain a reference binary image and a test binary image. The reference binary image and the test binary image are detected edges to obtain a reference edge image and a test edge image. A morphological expansion is performed on the reference edge image to obtain an expanded reference edge image. An OR operation is performed on the extended reference edge image and the test edge image to obtain an extended test edge image. An XOR operation is performed on the expanded reference edge image and the expanded test edge image. The method improves the accuracy of image comparison.

Abstract: A method of optimizing the detection of abnormalities in images of products generates a first image similar to training images and a second image similar to testing images with normal images and the images showing abnormalities inputted into a generative adversarial network (GAN). The GAN determines a first similarity ratio between the first image and the training image and generates a parameter based on the first similarity ratio for adjusting the GAN. A second similarity ratio between the second image and the testing image is determined. The testing image is deemed a normal image when the second similarity ratio is larger than the specified threshold value, and deemed to be an image revealing abnormalities when the second similarity ratio is less than or equal to the specified threshold value. A terminal device and a computer readable storage medium applying the method are also provided.

Abstract: In a method of distinguishing objects in images, a first image segmentation model is applied to segment a first segmented image including a first object from a test image. A second image segmentation model is applied to segment a second segmented image including a second object from the test image. A third segmented image marking the first object and the second object is obtained according to first coordinates of the first object in the first segmented image and/or second coordinates of the second object in the second segmented image. The method can segment different objects from an image quickly and accurately.

Abstract: A method for detecting a product for defects implemented in an electronic device, the method obtains an image of a product to be detected, obtains a reconstructed image by inputting the image to be detected into a pre-trained autoencoder, generates a difference image from the image and the reconstructed image, obtains a number of feature absolute values by performing clustering processing on the difference image; generates a target image according to the number of feature absolute values, the difference image, and a preset value; and determines a defect detection result by detecting the target image for defects.

Abstract: An inductive module with a miniaturized metamaterial structure includes an insulating substrate, two coil units, and a magnetic unit. The insulating substrate has opposing first and second surfaces and a through hole extending between the first and second surfaces. The coil units are respectively disposed on the first surface and the second surface of the insulating substrate, and are electrically connected to each other through the through hole. Each of the coil units includes a closed loop coil. The magnetic unit corresponds in position to a portion of the coil unit, surrounds said portion of the coil unit, and has an opening.

Abstract: An inductive module with a miniaturized metamaterial structure includes an insulating substrate, two coil units, and a magnetic unit. The insulating substrate has opposing first and second surfaces and a through hole extending between the first and second surfaces. The coil units are respectively disposed on the first surface and the second surface of the insulating substrate, and are electrically connected to each other through the through hole. Each of the coil units includes a closed loop coil. The magnetic unit corresponds in position to a portion of the coil unit, surrounds said portion of the coil unit, and has an opening.

Abstract: A method of optimizing the detection of abnormalities in images of products generates a first image similar to training images and a second image similar to testing images with normal images and the images showing abnormalities inputted into a generative adversarial network (GAN). The GAN determines a first similarity ratio between the first image and the training image and generates a parameter based on the first similarity ratio for adjusting the GAN. A second similarity ratio between the second image and the testing image is determined. The testing image is deemed a normal image when the second similarity ratio is larger than the specified threshold value, and deemed to be an image revealing abnormalities when the second similarity ratio is less than or equal to the specified threshold value. A terminal device and a computer readable storage medium applying the method are also provided.

Abstract: A method, apparatus, and non-transitory computer readable medium for optimizing generative adversarial network includes determining a first weight of a generator and an equal second weight of a discriminator the first weight is configured to indicate a learning ability of the generator, the second weight is configured to indicate a learning ability of the discriminator; and alternative iteratively training the generator and the discriminator until the generator and the discriminator are convergent.

Abstract: A method for assisting a driver to drive a vehicle in a safer manner includes capturing images of road in front of the vehicle, and identifying a traffic sign in the images. A first image frame is captured at a first time and a second image frame is captured at a later second time when the images do comprise the traffic sign. A change in size or other apparent change of the traffic sign from the first image frame to the second image frame is determined, and conformity or non-conformity with a predetermined rule is then determined. The traffic sign can be analyzed and recognized to trigger the vehicle to perform an action accordingly when conformity is found. A device providing assistance with driving is also provided.

Abstract: A flexible thin film metal oxide electrode fabrication methods and devices are provided and illustrated with thin film polyimide electrode formation and IrOx chemical bath deposition. Growth factors of the deposited film such as film thickness, deposition rate and quality of crystallites can be controlled by varying the solution pH, temperature and component concentrations of the bath. The methods allow for selective deposition of IrOx on a flexible substrate (e.g. polyimide electrode) where the IrOx will only coat onto an exposed metal area but not the entire device surface. This feature enables the bath process to coat the IrOx onto every individual electrode in one batch, and to ensure electrical isolation between channels. The ability to perform selective deposition, pads for external connections will not have IrOx coverage that would otherwise interfere with a soldering/bumping process.

Abstract: In an image comparison method, an original reference image and an original test image are obtained. The original reference image and the original test image are binarized to obtain a reference binary image and a test binary image. The reference binary image and the test binary image are detected edges to obtain a reference edge image and a test edge image. A morphological expansion is performed on the reference edge image to obtain an expanded reference edge image. An OR operation is performed on the extended reference edge image and the test edge image to obtain an extended test edge image. An XOR operation is performed on the expanded reference edge image and the expanded test edge image. The method improves the accuracy of image comparison.

Abstract: In a method of distinguishing objects in images, a first image segmentation model is applied to segment a first segmented image including a first object from a test image. A second image segmentation model is applied to segment a second segmented image including a second object from the test image. A third segmented image marking the first object and the second object is obtained according to first coordinates of the first object in the first segmented image and/or second coordinates of the second object in the second segmented image. The method can segment different objects from an image quickly and accurately.

Abstract: A method for selecting a light source for illuminating defects, an electronic device, and a non-transitory storage medium are provided. The method includes acquire grayscale images of an object with a known defect and generates a pseudo-hyperspectral image cube based on the grayscale images, so that algorithms related to hyperspectral images can analyze the grayscale images collected under different light sources. A most effective or target light source can be automatically and quickly determined from the plurality of light sources, improving an efficiency of light source selection.

Abstract: A method for optimizing the conversion of a deep learning model to process other data, applied in a device, includes converting a first deep learning model to obtain a second deep learning model, obtaining a weighting arrangement of the two models according to their deep learning frameworks and performing a quantization on the two models. A similarity in weighting between the two models is analyzed to produce a weighting analysis based on the first and second weighting arrangement and the first and second model quantization result weighting. The two models are tested to establish a model performance analysis. One or more suggestions for optimization are obtained based on the weighting analysis and the model performance analysis, and are applied to optimize the second deep learning model, an optimized second deep learning model being employed to process the other data.

Abstract: A wireless power system receives an input voltage signal from a first node of a secondary side coil, comprises an active rectifier, a buck converter, and a linear charger comprising a first resistor, a second resistor, a third resistor, a mode switching circuit, a current mirror circuit. The active rectifier rectifies the input voltage signal to generate a rectified voltage signal. The first resistor couples between a first node point and second node point. The second resistor couples between the second node point and ground terminal. The third resistor couples between a third node point and ground terminal. The current mirror circuit outputs a reference current and charge current according to the rectified voltage signal and mode switching signal generated by the mode switching circuit. The buck converter outputs a first output voltage signal or second output voltage signal according to a first node point voltage.

Abstract: A wireless charging device includes a wireless charging transmitter transmitting a charging signal to a signal gain module to generate at least one gain signal. The signal gain module includes an insulation substrate with an upper surface thereof provided with a first conductive wire. The first conductive wire makes at least one turns arranged along the inner edge of the insulation substrate. The lower surface of the insulation substrate is provided with a second conductive wire whose position corresponds to the position of the first conductive wire. A connecting element is arranged between the first conductive wire and the second conductive wire, such that the first conductive wire is electrically connected to the second conductive wire through the connecting element. The present invention provides a charging signal with high intensity to avoid the low charging efficiency caused by deflection and too long a distance.

Abstract: A method of chemical deposition of Iridium oxide film on rigid substrate is provided. The method comprises providing a rigid substrate in a container, adding an iridium precursor and mixing the iridium precursor with water to form an iridium precursor liquid in the container, adding and mixing an oxidant with the iridium precursor liquid in the container; and depositing an iridium oxide film on the rigid substrate in the container. A chelating agent and pH adjustor can be either selectively used for stabilizing the chemical bath deposition and for adjusting pH value of the liquid. For a variety of rigid substrates to be applied, the pH adjustor can adjust the pH value within a range of 4˜13. By employing the proposed fabrication method, it is extraordinarily advantageous of chemical alkaline as well as chemical acid deposition formula with configuration of depositing sodium-doped IrOx iridium oxide film.

Abstract: A method for assisting a driver to drive a vehicle in a safer manner includes capturing images of road in front of the vehicle, and identifying a traffic sign in the images. A first image frame is captured at a first time and a second image frame is captured at a later second time when the images do comprise the traffic sign. A change in size or other apparent change of the traffic sign from the first image frame to the second image frame is determined, and conformity or non-conformity with a predetermined rule is then determined. The traffic sign can be analyzed and recognized to trigger the vehicle to perform an action accordingly when conformity is found. A device providing assistance with driving is also provided.

Abstract: A wireless charging device includes a wireless charging transmitter transmitting a charging signal to a signal gain module to generate at least one gain signal. The signal gain module includes an insulation substrate with an upper surface thereof provided with a first conductive wire. The first conductive wire makes at least one turns arranged along the inner edge of the insulation substrate. The lower surface of the insulation substrate is provided with a second conductive wire whose position corresponds to the position of the first conductive wire. A connecting element is arranged between the first conductive wire and the second conductive wire, such that the first conductive wire is electrically connected to the second conductive wire through the connecting element. The present invention provides a charging signal with high intensity to avoid the low charging efficiency caused by deflection and too long a distance.

Abstract: A cochlear implant device comprises a receiver, a processing device, a first electrode and a second electrode. The receiver is configured to receive outside voice signal. The processing device is coupled to the receiver, configured to receive and transfer the voice signal to an electrical stimulation signal. The first electrode connects to the processing device, disposed on stapes footplate ligament or oval window. The second electrode connects to the processing device, disposed on round window. Wherein the electrical stimulation signal is applied to stapes footplate ligament, oval window or round window to stimulate acoustic nerve through the first electrode or the second electrode.