Abstract: A method for acquiring shadow-free images of a document for scanning or other purposes is applied in a device. The method includes training a shadow prediction model based on sample documents of a sample library and inputting a background color and a shadow mask of each of the sample documents extracted by the shadow prediction model into a predetermined shadow removing network for training, to obtain a shadow removing model. The method further includes obtaining a background color and a shadow mask of the document through the shadow prediction model and removing the shadows of the document based on the shadow removing model. The device utilizing the method is also disclosed.

Abstract: A method for recognition of characters by optical means in an unclear or non-optimal image of an object document, the image carrying shadows or other impediments inputs the document into a shadow prediction model to obtain a shadow mask. A determination is made as to whether the shadow mask of the document affect an optical character recognition (OCR) performance. The method further inputs the document into a shadow removing model for removal of shadows to obtain an intermediate document if the shadow mask are deemed to affect the OCR performance, then OCR can then be performed on the final object document.

Abstract: A driving warning method applied to a vehicle-mounted device is provided. The method includes detecting a moving object and a moving direction of the moving object by using at least one external sensor when a vehicle is moving. A driving behavior of a driver of the vehicle is monitored by using at least one internal sensor when the moving object and the moving direction of the moving object are detected. Once the moving direction of the moving object is not parallel to a moving direction of the vehicle and a sight direction of the driver does not cross the moving direction of the moving object, a first warning is transmitted.

Abstract: A method for generating images with high dynamic range (HDR) based on multiple images captured at different aperture values, under different conditions, or at different shutter speeds is applied in a device. The method inputs the original multiple images into a predetermined model and aligns the multiple images. The method further confirms object images that need to be attended among multiple aligned images and obtains a merge weighting for each of the object images, and merges the images for a generated HDR according to the merge weighting of each image. The device utilizing the method is also disclosed.

Abstract: A method for recognition of characters by optical means in an unclear or non-optimal image of an object document, the image carrying shadows or other impediments inputs the document into a shadow prediction model to obtain a shadow mask. A determination is made as to whether the shadow mask of the document affect an optical character recognition (OCR) performance. The method further inputs the document into a shadow removing model for removal of shadows to obtain an intermediate document if the shadow mask are deemed to affect the OCR performance, then OCR can then be performed on the final object document.

Abstract: A method for acquiring shadow-free images of a document for scanning or other purposes is applied in a device. The method includes training a shadow prediction model based on sample documents of a sample library and inputting a background color and a shadow mask of each of the sample documents extracted by the shadow prediction model into a predetermined shadow removing network for training, to obtain a shadow removing model. The method further includes obtaining a background color and a shadow mask of the document through the shadow prediction model and removing the shadows of the document based on the shadow removing model. The device utilizing the method is also disclosed.

Abstract: A method of training an object recognition model includes obtaining a sample set. The sample set is divided into a training set and a verification set. The object recognition model is obtained by training a neural network using the training set, and the object recognition model is verified using the verification set.

Abstract: A human-computer interaction method applied to a vehicle-mounted device is provided. The method includes obtaining video data of a scene inside a vehicle which is captured by a camera in real time. An action of a passenger in each of a plurality of seating positions in the vehicle is detected from the video data. Once a specified action is detected, a corresponding control operation is executed based on the specified action and the seating position of the passenger who performs the specified action.

Abstract: A driving warning method applied to a vehicle-mounted device is provided. The method includes detecting a moving object and a moving direction of the moving object by using at least one external sensor when a vehicle is moving. A driving behavior of a driver of the vehicle is monitored by using at least one internal sensor when the moving object and the moving direction of the moving object are detected. Once the moving direction of the moving object is not parallel to a moving direction of the vehicle and a sight direction of the driver does not cross the moving direction of the moving object, a first warning is transmitted.

Abstract: A method for generating dynamic images applied to a computer device includes obtaining a depth image of a static image. A preset region of the depth image is converted into a histogram and an average depth value D is calculated therefrom. A first depth value d1 and a second depth value d2 are determined from the histogram according to the average depth value D. M numbers of third depth values d3 are calculated according to the first depth value d1 and the second depth value d2. Once M number of blurred images are generated according to each M number of third depth values d3, the M number of blurred images are played back according to a magnitude of the third depth value d3 corresponding to each of the M number of blurred images.

Abstract: A method for dividing an image obtains the image by captured and a depth map of the image. The method creates a histogram of the depth map including horizontal and vertical axes. A clustering algorithm is applied to the data in the histogram to determine upon two data clusters and the cluster centers of the two clusters. The method determines that the abscissa value of the smallest ordinate value between two cluster centers in the histogram is a segmentation threshold. If the obtained segmentation threshold meets a preset condition, the image is segmented into a foreground region and a background region. An electronic device for applying the method is also provided.

Abstract: A method for dividing an image obtains the image by captured and a depth map of the image. The method creates a histogram of the depth map including horizontal and vertical axes. A clustering algorithm is applied to the data in the histogram to determine upon two data clusters and the cluster centers of the two clusters. The method determines that the abscissa value of the smallest ordinate value between two cluster centers in the histogram is a segmentation threshold. If the obtained segmentation threshold meets a preset condition, the image is segmented into a foreground region and a background region. An electronic device for applying the method is also provided.

Abstract: A method for generating dynamic images applied to a computer device includes obtaining a depth image of a static image. A preset region of the depth image is converted into a histogram and an average depth value D is calculated therefrom. A first depth value d1 and a second depth value d2 are determined from the histogram according to the average depth value D. M numbers of third depth values d3 are calculated according to the first depth value d1 and the second depth value d2. Once M number of blurred images are generated according to each M number of third depth values d3, the M number of blurred images are played back according to a magnitude of the third depth value d3 corresponding to each of the M number of blurred images.

Abstract: A method for recycling a used sputtering target is provided, including the steps of: (1) cleaning, (2) pulverization, (3) dissolution, (4) filtering, (5) peptization, (6) neutralization and precipitation, (7) rinsing and filtering, (8) drying, and (9) calcination; through the steps above, which can then be recycling used sputtering target to recover the constituent components of the ITO targets.