Abstract: Disclosed are a method and a system for video stitching. After it is determined that initial mounting of cameras in a M×N video stitching scene is completed, a reference image is selected from M×N images corresponding to M×N cameras; where both M and N are positive integers, at least one of M and N is larger than 1, and a rotating mirror is set in front of a camera lens of each camera; an image whose position does not meet a requirement among respective images except for the selected reference image is adjusted by controlling a rotating mirror corresponding to the image to rotate according to the selected reference image; and video stitching is performed according to an adjustment result.

Abstract: A method of automatically separating a stack of pages into documents includes receiving a plurality of page images from a scanner; extracting content from each of the plurality of page images; for each of the plurality of page images, determining, based upon the extracted content, whether the page image is an initial page image of a document; and appending each of the plurality of page images located between a first determined initial page image and a second determined initial page image to the first determined initial page image.

Abstract: Described is a system for detecting objects of interest in imagery. The system is configured to receive an input video and generate an attention map. The attention map represents features found in the input video that represent potential objects-of-interest (OI). An eye-fixation map is generated based on a subject's eye fixations. The eye-fixation map also represents features found in the input video that are potential OI. A brain-enhanced synergistic attention map is generated by fusing the attention map with the eye-fixation map. The potential OI in the brain-enhanced synergistic attention map are scored, with scores that cross a predetermined threshold being used to designate potential OI as actual or final OI.

Abstract: Methods and apparatus are provided for compressing and decompressing image data by producing two sets of reduced size image data, generating a modulation value for each elementary of the area from the image data, the modulation value encoding information about how to combine the sets of reduced size image data to generate an approximation to the image. In one arrangement, a set of index values is generated corresponding to a set of modulation values for each of the respective elementary areas of a group of elementary areas and these are assigned to each respective group and a second set of index values corresponding to one of the set of first index values for each elementary areas is assigned to each first group of elementary areas. These index values are stored for use in deriving modulation data more accurately when decompressing the image data.

Abstract: A method and a system for generating adaptive fast forward of egocentric videos are provided here. The method may include the following steps: obtaining a video footage containing a sequence of image frames captured by a non-stationary capturing device; estimating a moving direction of the non-stationary capturing device for a plurality of frames in the sequence of image frames; and generating a shortened video footage having fewer frames than said video footage, by sampling the sequence of image frames, wherein the sampling is carried out by selecting specific image frames and that minimize an overall cost associated with a deviation from a specific direction related to the moving direction, calculated for each of said plurality of image frames.

Abstract: Embodiments relate generally to new and useful systems and methods for processing digital images of items to facilitate item transport and/or handling. In some embodiments, a method is provided for operating an image processing and item transport system having a computing system that includes a digital image processing component. In some embodiments, the method can involve the digital image processing component acquiring a digital image and processing the digital image to obtain a digital representation of an item represented in the digital image, to estimate a dimensional size and/or weight of the item represented in the digital image, and to convert the digital image to a format suitable for outputting.

Abstract: Provided herein are systems, methods and computer readable media for classification of documents using a location hierarchy.

Abstract: A key identification system is provided. The key identification system comprises a sensing device configured to extract bitting information from a master key, and a logic configured to analyze the image. The sensing device may be configured to capture information about the bittings of the master key, such as an image of the bittings. The logic analyzes information about the bittings of the master key and compares it with bitting characteristics of known key blanks to determine the likelihood of a match between the master key and a known key blank.

Abstract: Methods and apparatus are provided for compressing and decompressing image data by producing two sets of reduced size image data, generating a modulation value for each elementary of the area from the image data, the modulation value encoding information about how to combine the sets of reduced size image data to generate an approximation to the image. In one arrangement, a set of index values is generated corresponding to a set of modulation values for each of the respective elementary areas of a group of elementary areas and these are assigned to each respective group and a second set of index values corresponding to one of the set of first index values for each elementary areas is assigned to each first group of elementary areas. These index values are stored for use in deriving modulation data more accurately when decompressing the image data.

Abstract: Described is a system for object tracking with integrated motion-based object detection and enhanced Kalman-type filtering. The system detects a location of a moving object in an image frame using an object detection MogS module, thereby generating an object detection. For each image frame in a sequence of image frames, the system predicts the location of the moving object in the next image frame using a Kalman filter prediction module to generate a predicted object location. The predicted object location is refined using a Kalman filter updating module, and the Kalman filter updating module is controlled by a controller module that monitors a similarity between the predicted object location and the moving object's location in a previous image frame. Finally, a set of detected moving object locations in the sequence of image frames is output.

Abstract: A method is provided for displaying physical objects. The method comprises capturing an input image of physical objects, and matching a three-dimensional model to the physical objects. The method further comprises producing a modified partial image by at least one of modifying a portion of the matched three-dimensional model, or modifying a partial image extracted from the input image using the matched three-dimensional model. The method also comprises displaying an output image including the modified partial image superimposed over the input image.

Abstract: Various embodiments of the present invention relate to a method, system and computer program product for detecting and recognizing text in the images captured by cameras and scanners. First, a series of image-processing techniques is applied to detect text regions in the image. Subsequently, the detected text regions pass through different processing stages that reduce blurring and the negative effects of variable lighting. This results in the creation of multiple images that are versions of the same text region. Some of these multiple versions are sent to a character-recognition system. The resulting texts from each of the versions of the image sent to the character-recognition system are then combined to a single result, wherein the single result is detected text.

Abstract: A method, a device and a system for restoring a resized depth frame into an original depth frame are disclosed. The method for restoring a resized depth frame into an original depth frame includes the steps of: obtaining a first sub-pixel value from one pixel of the resized depth frame; storing the first sub-pixel value in all sub-pixels of a first pixel of the original depth frame; obtaining a second sub-pixel value of the pixel of the resized depth frame; and storing the second sub-pixel value to all sub-pixels of a second pixel of the original depth frame.

Abstract: Embodiments are disclosed for randomly and pseudo-randomly presenting images to a user. An exemplary method includes receiving a first set of images from a user, receiving a second set of conditions that an image must satisfy, creating a subset of the first set of images that satisfies the second set of conditions, selecting a random element of said subset, and displaying said random element to a user. The conditions define the breadth or narrowness of the subset of images from which a random element is chosen. The conditions may be system set, user configured, or any combination, and a user may repeat the process, or may choose to view a new image that has one or more affinities to the last randomly chosen image presented. Affinities function in similar manner to the conditions of a pseudo-random selection, but generally serve to narrow the available set of photos to a greater extent.

Abstract: Systems and techniques are disclosed for applying an effect to a digital image using a cursor. An effect can be applied to an image at a region under a cursor. The cursor has an outer periphery and an effect indicating periphery within the outer periphery. The outer periphery defines a maximum extent to which the effect is applied. The effect indicating periphery indicates how the effect will be applied to the image, such as providing a visual indication of a softness setting.

Abstract: A method, a device and a system for resizing an original depth frame into a resized depth frame. The method for resizing an original depth frame into a resized depth frame includes the steps of: obtaining two sub-pixel values from at least two pixels of the original depth frame, respectively; and storing the two sub-pixel values into corresponding two sub-pixels of one pixel of the resized depth frame, respectively.

Abstract: Methods, apparatus, and systems for information identification are provided. A card image of a pre-set collection area is photographed and obtained, when a request event for information identification is detected. Edge-size information of the card image obtained by photographing is determined. A target area of the card image is marked according to the edge-size information. An image of the target area is extracted. Character shapes to be identified in the image of the target area is determined based on a pre-set character pattern library. A character corresponding to each character shape to be identified is identified according to each character shape to be identified that is determined and according to the character pattern library.

Abstract: A key identification system is provided. The key identification system comprises an imaging system to capture an image of a master key, and a logic to analyze the captured image. The imaging system may be capture an image of a groove in the master key from an angle between perpendicular and parallel to the blade of said master key. The logic analyzes the captured image to compare characteristics of the groove with groove characteristics of known key blanks to determine the likelihood of a match between the master key and a known key blank. The key identification system may further compensate for displacement or orientation of the master key with respect to the imaging system when analyzing characteristics of the groove.

Abstract: A system and method for a procedure that can be performed on any appropriate subject. Procedures can include assembling any appropriate work piece or installing members into a work piece, such as an airframe, autoframe, etc. Regardless of the subject, generally the procedure can have a selected result that is efficacious. The efficacious result may be the desired or best result for the procedure. The system and method can be used in confirming a selected result that can be efficacious.

Abstract: A method and apparatus for detecting and recognizing a traffic sign using a modified census transform (MCT) feature are disclosed. The traffic sign recognizing method according to an exemplary embodiment of the present invention includes detecting a traffic sign candidate region from an input image using a modified census transform (MCT) feature; verifying whether the candidate region corresponds to a traffic sign using the MCT feature histogram for the candidate region; and lassifying a region of interest into the corresponding traffic sign step by step using the MCT feature histogram for the verified candidate region.