Abstract: A method for collecting facial recognition data includes: locating a first face area from an Nth image frame; extracting a first facial feature defined with S factors; acquiring a second facial feature extracted from a second face area shown in an (N?1)th image frame at a corresponding position; determining whether the first face area is relevant to the second face area, and assigning to the first face area a tracing code; determining whether to store the first facial feature according to a similarity level of the first facial feature to existent data; storing and inputting the first facial feature into a neural network to generate an adjusted feature defined with T factors if the similarity level of the first facial feature to the existent data is not lower than a preset level, wherein T is not smaller than S; acquiring adjusted data generated by inputting the existent data into the neural network; determining whether the person is a registered one according to a similarity level of the adjusted feature to a

Abstract: A method for collecting facial recognition data includes: locating a first face area from an Nth image frame; extracting a first facial feature defined with S factors; acquiring a second facial feature extracted from a second face area shown in an (N?1)th image frame at a corresponding position; determining whether the first face area is relevant to the second face area, and assigning to the first face area a tracing code; determining whether to store the first facial feature according to a similarity level of the first facial feature to existent data; storing and inputting the first facial feature into a neural network to generate an adjusted feature defined with T factors if the similarity level of the first facial feature to the existent data is not lower than a preset level, wherein T is not smaller than S; acquiring adjusted data generated by inputting the existent data into the neural network; determining whether the person is a registered one according to a similarity level of the adjusted feature to a

Abstract: A method and an electronic apparatus for wave detection are provided. The method is adapted to the electronic apparatus having an image capturing device and a processor, and includes following steps: successively capturing a plurality of images; calculating a difference image between each two adjacent images among the images, and determining whether a variation degree of the difference images is over a predetermined degree according to pixel values of a plurality of pixels in the difference images; if the variation degree is over the predetermined degree, detecting a variation range formed by the pixels having the pixels values to which a predetermined variation is occurred in each of the difference images and determining whether a variation frequency of the pixel values within the detected variation range is over a predetermined frequency; and if the variation frequency is over the predetermined frequency, determining that a wave movement appears in the images.

Abstract: A video searching method and a video searching system are applied to an auxiliary searching of an original video. The video searching method includes setting a region-of-interest in a screen of the original video, setting a capturing condition that includes an interactive relation between the region-of-interest and a moving object of the original video, capturing a background screen of the original video and object snapshots of the moving object that comply with the capturing condition, selecting at least one of the object snapshots captured from the same moving object as a representative object snapshot, or integrating some of the object snapshots as a single representative object snapshot; and pasting the representative object snapshot at a coordinate corresponding to the background screen according to a corresponding timestamp, to generate a graphical event timeline that displays all the object snapshots.

Abstract: A method and an electronic apparatus for wave detection are provided. The method is adapted to the electronic apparatus having an image capturing device and a processor, and includes following steps: successively capturing a plurality of images; calculating a difference image between each two adjacent images among the images, and determining whether a variation degree of the difference images is over a predetermined degree according to pixel values of a plurality of pixels in the difference images; if the variation degree is over the predetermined degree, detecting a variation range formed by the pixels having the pixels values to which a predetermined variation is occurred in each of the difference images and determining whether a variation frequency of the pixel values within the detected variation range is over a predetermined frequency; and if the variation frequency is over the predetermined frequency, determining that a wave movement appears in the images.

Abstract: A method and an electronic apparatus for image background learning are provided. In the method, a memory space for recording multiple historical background values of each pixel in an input image is disposed in a memory device, in which the memory space is divided into a lock area and an open area. Whenever receiving the input image, a processor determines whether each pixel in the input image is a background pixel according to the historical background values recorded in the memory space. If the pixel is determined as the background pixel, the processor updates one of the historic background values recorded in the open area by using the pixel value of the pixel while keeping the historical background values in the lock area unchanged. The processor also periodically switches a location of the lock area in the memory space, so as to forget old historical background values.

Abstract: A method and an electronic apparatus for image background learning are provided. In the method, a memory space for recording multiple historical background values of each pixel in an input image is disposed in a memory device, in which the memory space is divided into a lock area and an open area. Whenever receiving the input image, a processor determines whether each pixel in the input image is a background pixel according to the historical background values recorded in the memory space. If the pixel is determined as the background pixel, the processor updates one of the historic background values recorded in the open area by using the pixel value of the pixel while keeping the historical background values in the lock area unchanged. The processor also periodically switches a location of the lock area in the memory space, so as to forget old historical background values.

Abstract: A video searching method and a video searching system are applied to an auxiliary searching of an original video. The video searching method includes setting a region-of-interest in a screen of the original video, setting a capturing condition that includes an interactive relation between the region-of-interest and a moving object of the original video, capturing a background screen of the original video and object snapshots of the moving object that comply with the capturing condition, selecting at least one of the object snapshots captured from the same moving object as a representative object snapshot, or integrating some of the object snapshots as a single representative object snapshot; and pasting the representative object snapshot at a coordinate corresponding to the background screen according to a corresponding timestamp, to generate a graphical event timeline that displays all the object snapshots.

Abstract: A video object detection system based on region transition includes a video acquiring unit, a user interface unit and a control module. The video acquiring unit is utilized for acquiring a video frame. The user interface unit is configured to provide a user to define at least one detection region with a set of image pixels on the acquired video frame and to define at least one region transition rule for identifying video objects of interest. Each detection region is represented with a set of image pixels. The control module is utilized for detecting position of a target video object and determining whether a moving trajectory of the target video object matches the at least one region transition rule.