Abstract:
A method of preventing fraud and theft during automated teller machine (ATM) transactions includes recording a video stream using a camera mounted on or near the ATM, the camera being positioned to record the face of a user of the ATM and a background behind the user, providing a facial model database containing images of a large number of people taken from different angles, the facial model database containing images of unobscured faces as well as obscured faces, and receiving insertion of a bank card into the ATM. The method further includes comparing images captured from the recorded video stream with images contained in the facial model database, and producing a corresponding first face comparison result, and issuing a notice for the user to uncover the user's face when the first face comparison result indicates that the user's face is obscured.
Abstract:
The present invention is to provide an image processing equipment and method, for enabling an electronic device having a plurality of image capturing elements installed thereon to capture calibration sample images of a parameter calibration module and verification sample images of a parameter verification module, wherein the parameter calibration module is formed by four calibration identification boards each having a chess board pattern printed thereon and arranged parallelly in a predetermined angle with each other, the parameter verification module is formed by four verification identification boards each having a chess board pattern printed thereon and arranged in parallel with each other, so as for the electronic device to promptly calibrate the intrinsic and extrinsic parameters of the mage capturing elements according to the calibration sample images and then to promptly verify the correctness of the calibrated intrinsic and extrinsic parameters according to the verification sample images.
Abstract:
To control an electronic device, a combination of a gesture command and a voice command are used. A motion sensor is used to detect the gesture command and a sound sensor is used to detect the voice command. When the combination of the gesture command and the voice command is detected, at least one function corresponding to the combination of the gesture command and the voice command is determined and the electronic device is controlled to perform the at least one function.
Abstract:
The present invention is to provide a method for enabling an electronic device to read at least two images taken from different positions by a digital camera mounted with a fisheye lens; acquire internal and external parameters of the fisheye lens corresponding to the different positions as well as the vignetting coefficient for eliminating the vignetting on the images; perform exposure compensation and color calibration on the images for letting them have consistent brightness and hues; project the images onto a spherical surface and spread out the spherical surface to form a two-dimensional spread-out picture based on the parameters; register the overlapped images projected on the two-dimensional spread-out picture and adjust the offset of corresponding pixels thereof, register and adjust the brightness and hues of the overlapped images into consistency; and fuse overlapped images together to produce a 360-degree spherical panorama without having any noticeable stitching seam between the images.
Abstract:
A smart refrigerator has a body having a shelf and a drawer, a door coupled to the body and has a plurality of trays. The shelf has a corresponding camera configured to capture an image of items on the shelf. The drawer has a corresponding camera configured to capture an image of items in the drawer. The trays have a corresponding camera configured to capture an image of items in the trays. The images captured by the cameras are processed to identify the type of the item and the location of the item within the smart refrigerator.
Abstract:
A method to provide privacy protection on a video includes performing people recognition on the video, when a registered person is recognized, determining if a privacy setting is turned on, and, when the privacy setting is turned on, performing privacy protection on the video. Performing privacy protection on the video includes pausing a recording of a live video, obscuring the registered person in the live video or a recorded video, or skipping ahead or deleting part of the recorded video.
Abstract:
To generate a preferred image, at least two images may be captured. From the at least two images, a base image is selected to be edited and another image is selected as a source of image data used for editing the base image. A user selects an object of the base image to be replaced. The object on the base image is compared to the object on the another image to generate a region on the base image and the another image. The region on the base image is replaced with the region on the another image.
Abstract:
To generate a preferred image, at least two images may be captured. From the at least two images, a base image is selected to be edited and another image is selected as a source of image data used for editing the base image. A user selects an object of the base image to be replaced. The object on the base image is compared to the object on the another image to generate a region on the base image and the another image. The region on the base image is replaced with the region on the another image.
Abstract:
The present invention is to provide a method for achieving a clear and precise optical zooming mechanism, which is applied to an electronic device equipped with a wide-angle image capturing element and a long-focus image capturing element. The wide-angle image capturing element and the long-focus image capturing element are controlled by the electronic device for capturing a wide-angle image and a long-focus image of a same spot simultaneously and respectively. The method enables the electronic device to sequentially perform an exposure and white balance adjustment process, a robust image matching algorithm and an image morphing fusion process to the wide-angle image and the long-focus image, respectively, so as to generate a clear and precise optical zooming image of the spot without having a significant skipping phenomenon occurred in an object within two zooming images.
Abstract:
The present invention is to provide a method for ensuring perfect stitching of a subject's images in a real-site image stitching operation, which enables an electronic device to read two real-site images which are taken respectively of different parts of the same site and each of which has an overlap area of a common subject; to determine and choose an optimal stitching path bypassing the subject; to construct a mask diagram such that, within a difference diagram of the overlap areas, the farther a pixel on one side of the optimal stitching path is from the optimal stitching path, the greater the pixel's value, and the farther a pixel on the other side of the optimal stitching path is from the optimal stitching path, the smaller the pixel's value; and to stitch and fuse the overlap areas together through a fusion algorithm, with the mask diagram serving as a weight.