Abstract: A method for selecting a deep learning network which is optimal for solving an image processing task obtaining a type of the image processing task, selecting a data set according to the type of problem, and dividing selected data set into training data and test data. Similarities between different training data are calculated, and a batch size of the training data is adjusted according to the similarities of the training data. A plurality of deep learning networks is selected according to the type of problem, and the plurality of deep learning networks is trained through the training data to obtain network models. Each of the network models is tested through the test data, and the optimal deep learning network with the best test result is selected from the plurality of deep learning networks appropriate for image processing.

Abstract: The present invention discloses a power converter, a switch control circuit, and a short circuit detection method for current sensing resistor of the power converter. The power converter includes: a transformer, a power switch, a current sensing resistor and a switch control unit. The current sensing resistor has one end coupled to the power switch and another end coupled to ground. The switch control unit generates the operation signal to control the power switch. The switch control unit generates a first sample-and-hold voltage at a first time point and a second sample-and-hold voltage at a second time point according to a voltage across the current sensing resistor. When a voltage difference between the first sample-and-hold voltage and the second sample-and-hold voltage is smaller than a reference voltage, it is determined that a short circuit occurs in the current sensing resistor.

Abstract: A spike suppression circuit includes a wide bandgap transistor, a first transistor, a clamping circuit, and a capacitor. The wide bandgap transistor is depletion-type. The first transistor is coupled in series with the wide bandgap transistor. The clamping circuit provides a voltage difference, and is coupled to a common node between the wide bandgap transistor and the first transistor. The capacitor provides a supply voltage for the clamping circuit. When the first transistor is turned off, the capacitor can recycle spike energy at the common node.

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 spike suppression circuit includes a wide bandgap transistor, a first transistor, a clamping circuit, and a capacitor. The wide bandgap transistor is depletion-type. The first transistor is coupled in series with the wide bandgap transistor. The clamping circuit provides a voltage difference, and is coupled to a common node between the wide bandgap transistor and the first transistor. The capacitor provides a supply voltage for the clamping circuit. When the first transistor is turned off, the capacitor can recycle spike energy at the common node.

Abstract: A switching regulator includes a first switch, a second switch, an inductor coupled to the first and second switches, and a control circuit. The control circuit controls the first switch to be ON for an ON time period. Next, the control circuit controls the first and second switches to be OFF for a first dead time period. Next, the control circuit controls the second switch to be ON for a synchronous rectification time period. Next, the control circuit controls the first and second switches to be OFF for a second dead time period. Next, the control circuit controls the second switch to be ON for a zero-voltage-switching pulse time period. Next, the control circuit controls the first and second switches to be OFF for a third dead time period. By the above operations, the first switch achieves soft switching.

Abstract: A flyback power converter circuit includes: a power transformer, a primary side switch and a conversion control circuit. In a DCM, during a dead time, the conversion control circuit calculates an upper limit frequency corresponding to output current according to a frequency upper limit function, and obtains a frequency upper limit masking period according to a reciprocal of the upper limit frequency, wherein the frequency upper limit masking period is a period starting from when the primary side switch is turned ON. During an upper limit selection period, the conversion control circuit selects a valley among one or more valleys in a ringing signal related to a voltage across the primary side switch as an upper limit locked valley, so that the conversion control circuit once again turns ON the primary side switch at a beginning time point of the upper limit locked valley.

Abstract: A method for discovering defects in products by detecting abnormalities in images, an electronic device, and a storage medium are provided. The method includes training an autoencoder model using images of flawless products, inputting such an image into the autoencoder model, and determining whether a reconstructed image can be generated based on the image. The image is determined to be showing abnormality in respond that no reconstructed image is generated. In respond that the reconstructed image is generated, the reconstructed image corresponding to the image to be detected is obtained, and the presence of abnormality in the reconstructed image is determined according to a defect judgment criterion. This method running in the electronic device improves efficiency and accuracy of abnormality detection.

Abstract: A method for detecting product for defects implemented in an electronic device includes classifying a plurality of product images to be detected into linear images or non-linear images; performing dimension reduction processing on the product images after image classification according to a plurality of dimension reduction algorithms to obtain a plurality of dimension reduction data; determining an optimal dimension reduction data of the plurality of dimension reduction data; obtaining score data of the product image by inputting the optimal dimension reduction data into a Gaussian mixture model; comparing the score data with a threshold; determining whether the score data is less than the threshold; and determining that there is at least one defect in the product image in response that the score data is determined to be less than the threshold.

Abstract: An image defect detection method is used in an electronic device. The electronic device determines a training image feature set, and trains a Gaussian mixture model by using the feature set to obtain an image defect detection model and a reference error value. An image for analysis is input into the autoencoder to obtain a second implicit vector and a second reconstructed image, and to calculate a second reconstruction error. The electronic device obtains a test image feature of the image for analysis according to the second reconstruction error and the second implicit vector, and inputs the test image feature into the image defect detection model to obtain a prediction score. The image for analysis is determined to reveal a defect when the prediction score is less than or equal to the reference error value.

Abstract: A method for processing images, an electronic device, and a storage medium are provided. A head portrait of a subject is obtained from a camera device. A hair region and a scalp region are identified from the head portrait. A proportion of the scalp region is calculated. The proportion of the scalp region is compared with a preset value, and baldness of the subject is determined accordingly. If found to be bald, complementary color processing is performed by processing the scalp region using a hair color of the hair region, and an updated head portrait is obtained after finishing the complementary color processing. The method automatically detects baldness and supplements the hair color in the scalp region.

Abstract: A method for recognizing different object-categories within images based on texture classification of the different categories, which is implemented in an electronic device, includes extracting texture features from block images segmented from original images according to at least one Gabor filter; determining a grayscale level co-occurrence matrix of each block image according to the texture features; calculating texture feature statistics of each block image according to the grayscale level co-occurrence matrix; training and generating an object recognition model using the texture features and the texture feature statistics; and recognizing and classifying at least one object in original image according to the object recognition model.

Abstract: A method for determining a growth height of a plant, an electronic device, and storage medium are provided. The method includes controlling a camera device to capture a plant to be detected, and obtaining a color image and a depth image of the plant to be detected. The color image and the depth image are aligned and an alignment image is obtained. The color image is detected using a pre-trained mobilenet-ssd network, and a detection box including the plant to be detected is obtained. A depth value of each of pixel points in the detection box is determined, and target depth values are obtained. A mean value and a standard deviation of the target depth values are determined, and a height of the plant to be detected is determined. According to the method, accuracy of the height of the plant can be improved.

Abstract: A method for detecting image abnormities, applied in an electronic device, and stored in a storage medium are provided, obtains images for analysis. The images are divided into a plurality of first divided images and a plurality of second divided images by reference to image size. A first abnormity score is obtained by inputting the image into a first pre-trained abnormity detection model. A plurality of second abnormity scores are obtained by inputting the first divided images into a second pre-trained abnormity detection model. A plurality of third abnormity scores are obtained by inputting the second divided images into a third pre-trained abnormity detection model. An abnormal type of the image is determined according to a preset abnormity database in response to an abnormity detected in the image, the method improves accuracy of defect detection.

Abstract: A method for determining a plant growth curve includes obtaining color images and depth images of a plant to be detected at different time points, performing alignment processing on each color image and each depth image to obtain an alignment image, detecting the color image through a pre-trained target detection model to obtain a target bounding box, calculating an area ratio of the target bounding box in the color image, determining a depth value of all pixel points in the target boundary frame according to the aligned image, performing denoising processing on each depth value to obtain a target depth value, generating a first growth curve of the plant to be detected according to the target depth values and corresponding time points, and generating a second growth curve of the plant to be detected according to the area ratios and the corresponding time points.

Abstract: A method for measuring a growth height of a plant, an electronic device, and a storage medium are provided. The method controls a camera device to obtain a color image and a depth image of a plant to be detected. The color image is detected by a detection model which is pre-trained, and a plurality of detection boxes which includes a plurality of plants to be detected is obtained. The color image and the depth image are aligned to create an alignment image. A plurality of target boxes is acquired from the alignment image, and depth values of the plurality of target boxes are determined. The quantity of the target boxes and a height of one or more plants to be detected are determined, no manual operations are required.

Abstract: A method for determining a height of a plant, an electronic device, and a storage medium are disclosed. In the method, a target image is obtained by mapping an obtained color image with an obtained depth image. The electronic device processes the color image by using a pre-trained mobilenet-ssd network, obtains a detection box appearance of the plant, and extracts target contours of the plant to be detected from the detection box. The electronic device determines a depth value of each of pixel points in the target contour according to the target image. Target depth values are obtained by performing a de-noising on depth values of the pixel points, and a height of the plant to be detected is determined according to the target depth value. The method improves accuracy of height determination of a plant.

Abstract: A method of detecting defects revealed in images of finished products includes importing flawless images into an autoencoder for model training and obtaining reconstructed images from them. The reconstructed images are compared with the flawless images to obtain groups of test errors. An error threshold is selected from the groups of the test errors according to preset rules. In practice, obtaining an image to be tested, and a reconstructed image to be tested, and an error to be tested; determining detection of the image to be tested according to the error and the error threshold; and importing the image into a classifier for defect classification if the image is found to reveal a defect. An electronic device and a non-volatile storage medium for performing the above-described method, are also disclosed.

Abstract: A method for evaluating environment and surroundings of a pedestrian passageway, used in an electronic device, obtains a position information of a target area, and obtains a streetscape image corresponding to the position information of the area. The method further inputs the streetscape image into a trained convolutional neural network, makes the trained convolutional neural network carry out a convolution calculation of the streetscape image to generate a feature vector for classifying a number of target objects in the streetscape image, and outputs the feature vector. The feature vector is input into a full convolution neural network to apply a certain color to a number of pixels belonging to a same target object, and outputs the streetscape image with colored target objects.

Abstract: In a product defect detection method, a detection image of a product is obtained. A first preset number of detection blocks are cut out from the detection image. The detection blocks are input into an auto-encoder to obtain reconstructed blocks and a mean square error between each detection block and the corresponding reconstructed block is calculated, an association between the mean square error and the detection block being established. Whether the product carries defective is determined according to the mean square error of each detection block. The method improves accuracy of detecting defects of the product.