Abstract: The invention is a power supply management device for intelligent motorcycle, comprising a power device and a power supply management system. The power supply management system is electrically connected to the power device. The power supply management system includes a processor, an input module connected to the processor, a link module connected to the processor, a voltage modulation module connected to the processor, a protection module connected to the processor, and an output module connected to the processor. Thereby, the power supply management system can be electrically connected to the rechargeable battery of the power device, serving for power supply and power management in various demands, and in turn, for effective control and management of the power to meet the operation requirement of the intelligent motorcycle.

Abstract: Systems and methods of instant-messaging bot for robotic process automation (RPA) and robotic textual-content extraction from digital images include a chatbot application, a software RPA manager, and an instant-messaging (IM) platform, all built for an enterprise. The enterprise IM platform is connected to one or more public IM platforms over the Internet. The RPA manager contains multiple modules of enterprise workflows and receives instructions from the enterprise chatbot for executing individual workflows. The system allows enterprise users connected to the enterprise IM platform, and external users connected to the public IM platforms, to use instant messaging to initiate enterprise workflows that are automated with the help of the enterprise chatbot and delivered via instant messaging. Furthermore, textual-content extraction from digital images is incorporated in the RPA manager as an enterprise workflow, and provides improved convolutional neural network (CNN) methods for textual-content extraction.

Abstract: The present invention is an AI motorcycle comprising a motorcycle, an AI device, a first plate image acquisition device, a second plate image acquisition device, a display device, and an alert device. Thereby, there are a smart movable investigation and crime prevention system, a multi-lane plate number and smart street lamp recognition system, a portable face recognition system, a portable drunk driving detection system, a mobile recognition integrated radar speedometer system, a mobile image recognition integrated RFID receiver, and equipped with multiple application functions, including a 360° panoramic camera for road condition recording and image analysis, a cloud database police network system implementation, a roadside parking billing plate recognition function, and a multi-lane plate number recognition functions are accomplished when riding the motorcycle on patrol.

Abstract: Systems and methods of instant-messaging bot for robotic process automation (RPA) and robotic textual-content extraction from digital images include a chatbot application, a software RPA manager, and an instant-messaging (IM) platform, all built for an enterprise. The enterprise IM platform is connected to one or more public IM platforms over the Internet. The RPA manager contains multiple modules of enterprise workflows and receives instructions from the enterprise chatbot for executing individual workflows. The system allows enterprise users connected to the enterprise IM platform, and external users connected to the public IM platforms, to use instant messaging to initiate enterprise workflows that are automated with the help of the enterprise chatbot and delivered via instant messaging. Furthermore, textual-content extraction from digital images is incorporated in the RPA manager as an enterprise workflow, and provides improved convolutional neural network (CNN) methods for textual-content extraction.

Abstract: A device and a method for obtaining a clear image, the method is executed by a digital signal processor (DSP) chip or a microprocessor. Through merging clear parts of two images with different focal lengths, a single clear image is obtained. The image is divided into a plurality of blocks, and then edge detection is processed to obtain an edge image. Blocks having more complete edge information are selected as clear blocks. Then, the clear blocks are further merged into a single clear image. Once the images are processed with the method, a depth of field of the image can be adjusted, without adding hardware elements of a digital camera such as a variable diaphragm.

Abstract: An image brightness adjusting method is provided. The brightness values of all pixels of the image are firstly increased in various increasing degrees. Next, the increased brightness values are decreased in various decreasing degrees according to the original brightness values, thereby avoiding over-increasing the brightness values of the image. Moreover, the use of the color saturation values to adjust the brightness values can avoid the unnatural image appearance.

Abstract: A method of generating a high dynamic range image corresponding to a specific scene. The method includes shooting a specific scene to generate a base image; selecting a bright area and a dark area from the base image; determining base luminance according to the base image; shooting the specific scene to generate at least a first image, wherein average luminance of a part of the first image corresponding to the bright area of the base image is less than or equal to the base luminance; shooting the specific scene to generate at least a second image, wherein average luminance of a part of the second image corresponding to the dark area of the base image is greater than or equal to the base luminance; and combining at least the first image and the second image into a high dynamic range image corresponding to the specific scene.

Abstract: An image processing apparatus and method is disclosed that is applied for image stabilization. The method comprises the following steps of: At least two images are captured by the image capture module. A sharpest image and a sharper image are selected from the at least two images. At least a motion vector is generated between the sharpest image and the sharper image. The sharpest image is combined with the sharper image based on the motion vector and a combination ratio so as to generate a combined image.

Abstract: An image processing apparatus and method is disclosed that is applied for image stabilization. The method comprises the following steps of: At least two images are captured by the image capture module. A sharpest image and a sharper image are selected from the at least two images. At least a motion vector is generated between the sharpest image and the sharper image. The sharpest image is combined with the sharper image based on the motion vector and a combination ratio so as to generate a combined image.

Abstract: A white balance adjustment method for a digital image capturing device is disclosed. The white balance adjustment method comprises the steps of: setting a color temperature estimation area; capturing an image with the digital image capturing device; choosing one or more analysis blocks from the image; determining whether values of Cb and Cr of each analysis block are located in either a color temperature zone or a white zone of the color temperature estimation area; collecting and calculating each point value of each color temperature that is located in the color temperature estimation area to obtaining a final color temperature; and performing a white balance adjustment procedure according to the final color temperature.

Abstract: An image brightness adjusting method is provided. The brightness values of all pixels of the image are firstly increased in various increasing degrees. Next, the increased brightness values are decreased in various decreasing degrees according to the original brightness values, thereby avoiding over-increasing the brightness values of the image. Moreover, the use of the color saturation values to adjust the brightness values can avoid the unnatural image appearance.

Abstract: The invention is to provide a method that reconstructs enhanced-resolution images with improved super-resolution algorithms, which is based on an iterative method and employs our suggested initial interpolation, robust image registration, automatic image selection, and further image enhancement post-processing. According to the method of the invention, the reconstruction of enhanced-resolution image can be quickly achieved not only by low-resolution image sequences associated with a moving object but also by low-resolution image sequences associated with a stationary scene.

Abstract: This invention provides a metering method of automatic exposure for determining an exposure value of a picture having a subject, including a subject detecting step that uses focus values of the picture to detect the subject, and an exposure value calculating step that uses an auto exposure metering function to calculate an exposure value of the picture. The present invention can provide a simpler and smaller metering method.

Abstract: A device and a method for obtaining a clear image, the method is executed by a digital signal processor (DSP) chip or a microprocessor. Through merging clear parts of two images with different focal lengths, a single clear image is obtained. The image is divided into a plurality of blocks, and then edge detection is processed to obtain an edge image. Blocks having more complete edge information are selected as clear blocks. Then, the clear blocks are further merged into a single clear image. Once the images are processed with the method, a depth of field of the image can be adjusted, without adding hardware elements of a digital camera such as a variable diaphragm.

Abstract: A zoom tracking method for digital camera is disclosed. The method comprises storing a position table comprising data of several zoom position curves respect to positions of a focus lens and move the focus lens position by looking up said position table while moving a zoom lens position. The curves are divided into a first linear region, a second linear region and a nonlinear region to reduce the table size while still achieving good image quality.

Abstract: A white balance method for an image formed by a digital still camera is provided. The white balance method comprises steps of: removing a color cast over a white object of the image; detecting a reference white point from the image by extracting an a pixel information of the white object; and adjusting a white balance of the white object by determining a scale factor based on the color cast and the pixel information.

Abstract: An auto focus method of a digital camera for moving a lens of the digital camera to the maximum focus value position is provided. According to certain criteria, the lens movement states are categorized into four states, i.e. an initial state, a coarse state, a mid state and a fine state. The numbers of search steps for the lens in different states are different.

Abstract: A white balance adjustment method for a digital image capturing device is disclosed. The white balance adjustment method comprises the steps of: setting a color temperature estimation area; capturing an image with the digital image capturing device; choosing one or more analysis blocks from the image; determining whether values of Cb and Cr of each analysis block are located in either a color temperature zone or a white zone of the color temperature estimation area; collecting and calculating each point value of each color temperature that is located in the color temperature estimation area to obtaining a final color temperature; and performing a white balance adjustment procedure according to the final color temperature.

Abstract: A method of generating a high dynamic range image corresponding to a specific scene. The method includes shooting a specific scene to generate a base image; selecting a bright area and a dark area from the base image; determining base luminance according to the base image; shooting the specific scene to generate at least a first image, wherein average luminance of a part of the first image corresponding to the bright area of the base image is less than or equal to the base luminance; shooting the specific scene to generate at least a second image, wherein average luminance of a part of the second image corresponding to the dark area of the base image is greater than or equal to the base luminance; and combining at least the first image and the second image into a high dynamic range image corresponding to the specific scene.

Abstract: A zoom tracking method for digital camera is disclosed. The method comprises storing a position table comprising data of several zoom position curves respect to positions of a focus lens and move the focus lens position by looking up said position table while moving a zoom lens position. The curves are divided into a first linear region, a second linear region and a nonlinear region to reduce the table size while still achieving good image quality.