Abstract: Some embodiments provide a method for selecting a portion of an image. The method identifies edges in the image. The method defines a border about the portion of the image by using the identified edges. The method represents the border as a deformable curve. In some embodiments, defining the border includes detecting a cursor moving over the image and defining the border along identified edges in the vicinity of the cursor. In some embodiments, the method searches for edges in the vicinity of the cursor and snaps the border to the edges. Identifying the edges of the image includes performing an edge detection algorithm in some embodiments. Identifying the edges further includes performing a de-noise algorithm in some embodiments. In some embodiments, the parametrizable curve is a bezier spline.

Abstract: Script-agnostic text reflow technique embodiments are presented that generally reflow text found in an image of a document in a manner that functions across multiple scripts, multiple fonts of a script and multiple languages using the same script. This generally involves segmenting regions of text in a document image into individual words and doing this without relying on any script-specific characteristics or requiring any form of character recognition. While segmenting text, the possible presence of accents, diacritics and punctuation marks is considered.

Abstract: Disclosed is a method of classifying segmented contents of a scanned image of a document. The method comprise partitioning the scanned image into color segmented tiles at pixel level. The method then generates superpositioned segmented contents, each segmented content representing related color segments in at least one color segmented tile. Statistics are then calculated for each segmented content using pixel level statistics from each of the tile color segments included in segmented content, and then determines a classification for each segmented content based on the calculated statistics. The segmented content may be macroregions. The macroregions may form part of a multi-layered document representation of the document.

Abstract: A device that includes at least one memory unit adapted to store image data; the device is characterized by including a configurable filter adapted to apply de-ringing filtering and de-blocking filtering such as to filter image data retrieved from the at least one memory unit, whereas the device is adapted to repetitively determine a configuration of the configurable filter in response to received image data and to at least one mode selection rule and to configure the configurable filter in response to the determination.

Abstract: A method for detecting an object on an image representable by picture elements includes: “determining first and second adaptive thresholds for picture elements of the image, depending on an average intensity in a region around the respective picture element”, “determining partial objects of picture elements of a first type that are obtained based on a comparison with the first adaptive threshold”, “determining picture elements of a second type that are obtained based on a comparison with the second adaptive threshold” and “combining a first and a second one of the partial objects to an extended partial object by picture elements of the second type, when a minimum distance exists between the first and the second of the partial objects, wherein the object to be detected can be described by a sum of the partial objects of picture elements of the first type and/or the obtained extended partial objects”.

Abstract: A system for identifying individuals in digital images and for providing matching digital images is provided. A set of images that include faces of known individuals is received. Faces are detected in the images and facial components are identified in each face. Visual words corresponding to the facial components are generated, stored, and associated with identifiers of the individuals. At a later time, a user may provide an image that includes the face of one of the known individuals. Visual words are determined from the face of the individual in the provided image and matched against the stored visual words. Images associated with matching visual words are ranked and presented to the user.

Abstract: Disclosed is a high resolution image obtaining apparatus and method. The high resolution image obtaining apparatus may divide an input image frame into a background region and foreground region and apply an optimized resolution enhancement algorithm to each region, thereby effectively obtaining a high resolution image frame with respect to the input image frame.

Abstract: There is provided an image processing apparatus including a dynamic body detecting unit for detecting a dynamic body contained in a moving image, a dynamic body region setting unit for, during a predetermined time from a time point the dynamic body is detected by the dynamic body detecting unit, setting a region containing the dynamic body at the detection time point as a dynamic body region, and a fluctuation removable processing unit for performing a fluctuation removal process on a region other than the dynamic body region set by the dynamic body region setting unit.

Abstract: An approach that dynamically learns a set of attributes of an operator of a point of sale (POS) is provided. In one embodiment, there is an attribute tool, including an extraction component configured to receive sensor data of a set of moving objects, and extract a set of attributes from each of the set of moving objects captured within the scan area at the POS; an identification component configured to update an appearance model with the set of attributes from each of the set of moving objects; and an analysis component configured to analyze the appearance model to identify at least one of the set of moving objects as an operator of the POS.

Abstract: A vehicle apparatus control system and method thereof are disclosed. The vehicle apparatus control system comprises a data storage module, an image capturing module, a face recognition module and a control module. The data storage module stores multiple registered users' facial feature parameters and vehicle apparatus setting parameters, and integration setting data. The face recognition module detects several facial images contained in the captured image and recognizes the users corresponding to the face images according to the facial feature parameters stored in data storage module. The control module set a vehicle apparatus according to the integration setting data, and the corresponding users' vehicle apparatus setting parameters.

Abstract: Systems and methods for estimating the centers of moving objects in a video sequence are disclose. One embodiment is a method of defining one or more motion centers in a video sequence, the method comprising receiving a video sequence comprising a plurality of frames, receiving a motion history image for each of a subset of the plurality of frames based on the video sequence, identifying, through use of the motion history image, one or more data segments having a first orientation, wherein each data segment having the first orientation has a start location and a length, identifying, one or more data segments having a second orientation, wherein each element of a data segment having the second orientation is associated with a data segment having the first orientation, and defining a corresponding motion center for one or more of the indentified data segments having the second orientation.

Abstract: A method of controlling a digital image processing apparatus that performs a moving picture photographing mode and a reproduction mode. The method includes the operations of detecting face frames where faces of different persons exist in an operations of storing images of a series of frames in a moving picture file in the moving picture photographing mode, storing representative image frames including face frames selected from the detected face frames in the moving picture photographing mode, and displaying images of the stored representative image frames to indicate the moving picture file in the reproduction mode. The method can be performed by a controller of the digital image processing apparatus.

Abstract: A method detects noise in a document image. The image includes pixels representing at least text and image data forming the document. The noise includes at least one of halftone, bleeding and texture noise. The method partitions the image into tiles, formed of pixels, determines a set of dominant colors for each tile, associates each pixel with one of the determined dominant colors, and then determines for each dominant color a fragmentation statistic, and applies a threshold to each statistic to detect the noise in the corresponding dominant color in the tile. Detected noise in the image is reduced by (a) merging colors with noise to one color without noise if the noise is halftone noise or texture noise; and (b) removing the colors with noise if the noise is bleeding noise. The pixels of the tile are then quantized to those remaining dominant colors of the set.

Abstract: A method and apparatus for detecting an object using a perspective plane are disclosed. The method includes determining a perspective plane for a background scene, and determining a moving object within the background scene based upon the determined perspective plane. By using a visual surveillance device and an apparatus for detecting objects, the method and apparatus for detecting an object using a perspective plane is capable of efficiently detecting objects and tracking the movements of the corresponding objects.

Abstract: Some embodiments provide a method of selecting a section of interest in an image that includes numerous pixels. the method draws a curvilinear boundary about the section of interest. From the curvilinear boundary, the method generates a two-dimensional transition tunnel region about the section of interest. The method analyzes image data based on the tunnel region to identify a subset of pixels in the region that should be associated with the section of interest. In some embodiments, the tunnel region includes a pair of curves bounding the tunnel region. In some embodiments, the curvilinear boundary has a particular shape, and generating the tunnel region includes determining whether the tunnel can be generated at a specified width with both curves of the tunnel having the same particular shape as the defined border. In some embodiments, analyzing image data includes comparing pixels inside the transition tunnel region to pixels outside the transition tunnel region.

Abstract: There is provided an information processing apparatus, comprising: an obtaining unit which obtains video data captured by an image capturing apparatus disposed in a monitored space, location information regarding a location of a moving object in the monitored space, and existence information regarding a capturing period of the moving object in the video data; and a display processing unit which processes a display of a trajectory of the moving object in the monitored space based on the location information, the display processing unit processing a display of the trajectory so that the portion of the trajectory that corresponds to the capturing period is distinguishable from the other portions of the trajectory, based on the existence information.

Abstract: The invention relates to a method for detecting the proper motion of an real-world object, comprising the steps of acquiring, by an image capturing device (ICD), a first image (I1) of the object at a first point in time (t1) and a second image (I2) at a second point in time (t2); obtaining a third (hypothetical) image (I3), based on an estimated effect of the motion of the image capturing device (ICD) itself (EMF) between the first and the second point in time (t1, t2), wherein the effect of the motion of the image capturing device (ICD) itself is estimated based on the forward kinematics of the image capturing device; determining an optical flow (OF) between the second image (I2) and the third image (I3); and evaluating the optical flow (OF) by incorporating uncertainties of the optical flow (OF) and the ego-motion-flow (EMF) in order to determine the proper motion of the object.

Abstract: A method for creating an appearance model of an object includes receiving an image of the object and creating a hierarchical appearance model of the object from the image of the object. The hierarchical appearance model has a plurality of layers, each layer including one or more nodes. Nodes in each layer contain information of the object with a corresponding level of detail. Nodes in different layers of the hierarchical appearance model correspond to different levels of detail.

Abstract: A method and apparatus for placing a time stamp in a remotely applied watermark is disclosed. The method permits a time stamp of high resolution to be added remotely while minimizing the number of bits necessary in the time stamp.

Abstract: Techniques are disclosed for acceleration techniques for improved image remoting. A rolling 2D hash of a first image sent to a client is computed. When the server has a second image to send to the client, it calculates a rolling 2D hash of the new image. It also calculates “pivot points” for the images based on the rolling 2D hashes. Based on the pivot points, it determines possible matching hash windows between the two images that correspond to window moves or scrolls. Where a match is confirmed, it determines whether a “larger” a larger matching rectangle exists between the two images. It then instructs the client to display the matching rectangle that exists in the first image that the client has in the appropriate location in the second image, thereby saving the bandwidth requirements to re-transmit it to the client.