Techniques for cropping images containing an occlusion are presented. A method for image editing is presented comprising, when an occlusion is detected in an original digital image, determining an area occupied by the occlusion, assigning importance scores to different content elements of the original digital image, defining a cropping window around an area of the original digital image that does not include the area occupied by the occlusion and that is based on the importance scores, and cropping the original digital image to the cropping window.

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.

An information processing apparatus capable of displaying an image on a predetermined display unit, includes: a reception unit that receives a written input on an image according to an operation of a user in a state where the image is displayed on the display unit; a generation unit that generates a written object according to the written input received by the reception unit; a reference detection unit that detects a reference direction of the image displayed on the display unit; a correction unit that corrects the written object on the basis of the reference direction detected by the reference detection unit; and a display control unit that displays the written object generated by the generation unit.

A system and process for extracting information from filled form images is described. In one example, the claimed invention first extracts textual information and the hierarchy in a blank form. This information is then used to extract and understand the content of filled forms. In this way, the system does not have to analyze from the beginning each filled form. The system is designed so that it remains as generic as possible. The number of hard-coded rules in the whole pipeline was minimized to offer an adaptive solution able to address the largest number of forms, with various structures and typography. The system is also created to be integrated as a built-in function in a larger pipeline. The form understanding pipeline could be the starting point of any advanced Natural Language Processing application.

A method of generating a semi transparent QR code in which a QR code image and an ordinary color background image are synthesized, and a QR code detection method of separating a QR code and a normal color image from an image obtained by capturing a semi transparent QR code are disclosed.

A display apparatus is provided. The display apparatus includes a storage unit configured to, in response to a subject being captured, store a captured first image, an output unit configured to, in response to the first image being stored, output a guide message for guiding a subject so as to move out of a subject area of the first image, and a controller configured to, in response to the subject being moved and re-capturing being performed, acquire a re-captured second image, detect a local image area corresponding to the subject area of the first image from the second image, synthesize the detected local image area with the first image, generate a background image from which the subject is removed, and store the background image in the storage unit.

A vehicle capable of autonomous driving includes a lane detection system. The lane detection system is trained to predict lane lines using training images. The training images are automatically processed by a training module of the lane detection system in order to create ground truth data. The ground truth data is used to train the lane detection system to predict lane lines that are occluded in real-time images of roadways. The lane detection system predicts lane lines of a roadway in a real-time image even though the lane lines maybe indiscernible due to objects on the roadway or due to the position of the lane lines being in the horizon.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing satellite images. In one aspect, a system comprises: a reservoir computing neural network for processing satellite images, wherein the reservoir computing neural network is configured to receive a satellite image and to generate a prediction characterizing the satellite image, wherein the reservoir computing neural network comprises: (i) a brain emulation sub-network, and (ii) an output sub-network, wherein: the brain emulation sub-network has a neural network architecture that is specified by a brain emulation graph, wherein the brain emulation graph is generated based on a synaptic connectivity graph representing synaptic connectivity between neurons in a brain of a biological organism, and the values of at least some of the brain emulation sub-network parameters are determined before the reservoir computing neural network is trained and are not adjusted during training of the reservoir computing neural network.

Images in bitonal formats often include watermarks, stamps, or other patterns and artifacts. These patterned artifacts may be represented as a series of geometric points, dots, and/or dashes in the general shape of the original pattern. These patterned artifacts make other processes such as optical character recognition (OCR) difficult or impossible when items or pixels of interest are also found within the pattern of such artifact(s). Current patterned artifact removal solutions use methods of erosion to minimize the unwanted patterned artifact. However, such methods also erode the pixels/items of interest which, in turn, cause failures in other processes, such as OCR, that are desired to be carried out on or with the image.

A method for image processing includes the following. Edge pixel points in the image to be processed are determined by performing edge detection on the image to be processed. The number of the edge pixel points in the image to be processed is determined as a first pixel number. Determine that a moire pattern exists in the image to be processed when the first pixel number is larger than a first number threshold.