Abstract: Methods and a processing device are provided for reducing purple fringing artifacts appearing in a digital image. A linear filter may be applied to a digital image to identify purplish candidate regions of pixels. Ones of pixels that are in any of the purplish candidate regions and are within a predefined distance of a high gradient/high contrast region may be identified as damaged pixels. A map of the damaged pixels may then be created, or formed. The damaged pixels may be reconstructed based on interpolation of values from undamaged pixels on a fringe boundary with guidance from a green channel. In various embodiments, the damaged pixels may be reconstructed based on a Poisson blending approach, an approximated Poisson blending approach, or a variety of approaches based on interpolation of values from undamaged pixels on a fringe boundary, with guidance from a green channel.

Abstract: A computerized method of recognizing an input hand-drawn table formed by freeform line objects comprises transforming each freeform line object of the table into one of a vertical line segment and a horizontal line segment, generating a grid system based on the vertical and horizontal line segments and converting the generated grid system into a table object.

Abstract: Image data processing is facilitated. According to an example embodiment, image data is processed using photometric similarity and, where appropriate, a classification of sample pixels for the image data. In some applications, a trained bilateral filter function is used with a filter coefficient selected for a particular classification of image data to filter artifacts in the image data.

Abstract: An image processing apparatus includes a data supply node to receive line data scanned in a main scan direction of an image, an image enlargement unit coupled to the data supply node to apply to the line data an enlargement process for enlarging the image by an enlargement factor equal to an integer so as to produce enlarged data at an output node, and an image reduction unit coupled to the output node of the image enlargement unit to apply to the enlarged data a reduction process for reducing the enlarged image by a desired reduction factor so as to produce reduced data at an output node.

Abstract: An image display device capable of supporting brightness enhancement and power control and a method thereof, in which the brightness and contrast are enhanced and the power of a light source is controlled in accordance with the image characteristic. In the image display method, a parameter representative of an input image is calculated from a histogram of the input image, a model corresponding to the input image is selected from a plurality of representative models by analyzing the parameter, and then a brightness controlling function matched with the selected model is selected. The size of each component of a pixel constituting the input image is controlled using the brightness controlling function, and the output image of the pixel whose component size has been controlled is displayed.

Abstract: The feature selection device includes a feature extraction unit that extracts M types of features from each of a plurality of original images and each of a plurality of altered images obtained by applying an alteration process to the plurality of original images; and a feature selection unit that handles an original image and an altered image of the original image as identical images and handles altered images of the same original image as identical images, while handles other images as different images, and with use of discrimination capability which is a degree of discriminating different images and robustness which is a degree that a value of a feature does not vary due to the alteration process applied to an image as evaluation criteria, evaluates the M types of features extracted from the respective images, and selects a collection of N types of features, the N types being smaller in number than that of the M types, from the M types of features as features for discriminating images.

Abstract: A co-registration system provides a means for spatially warping an optical image of an object with another images of a similar object. The optical image may be a scatter image, and the second image may be the same type of image modality, or may be different. The co-registration may use landmarks selected by a user, or may make use of contour information derived from the images. The system may also include processing of three-dimensional volume data in the form of sets of two-dimensional slices for co-registration.

Abstract: In order to perform vehicle control, a warning process, and the like which do not give a driver an uncomfortable feeling in speed adjustment, a warning process, and the like corresponding to a road shape such as a curve, it is necessary to recognize not only a near road shape but also a far road shape with high accuracy.

Abstract: An image data processing apparatus includes a processing unit that detects an attribute of image data input. The image data processing apparatus also includes a network interface that receives content data from an external section. When the processing unit detects that the image data is contained in a predetermined location of the content data, the processing unit processes, based on the attribute detected and in accordance with an aspect ratio of a display section where the image data is to be displayed, the image data such that a horizontal to vertical ratio of the image data is kept when the image data is displayed on the display section.

Abstract: The image pickup apparatus 100 comprises the image pickup unit 1 to pick up an image of the subject which a user desires, a detecting of the face image area which includes the face of the subject person in the picked-up image based on the image information of the picked-up image, a recognizing of the expression of the face in the detected face image area, a ranking of the face image areas in the order of good smile of the recognized expressions and a displaying of the face image areas F arranged in the order of ranking and the entire picked-up image G on the same screen.

Abstract: A web-based application provides more accurate and clearer methods of searching, sorting, and displaying a set of images stored in a database. A first aspect of the present invention is the method by which image data is stored. Typical content-based systems use color information, whereas the present invention uses an image-location tagging method. A second aspect of the present invention is the method by which the set of images are sorted in relevancy. Tag data of the images allows for a new and fast method of searching through an entire set. A third aspect of the present invention is the method by which the sorted images are displayed to the user. Instead of the common method of just displaying the images in a rectangular array, where each image is the same size, the web-based application positions and sizes each image based on how relevant it is.

Abstract: A method and system generates and compares fingerprints for videos in a video library. The video fingerprints provide a compact representation of the spatial and sequential characteristics of the video that can be used to quickly and efficiently identify video content. Because the fingerprints are based on spatial and sequential characteristics rather than exact bit sequences, visual content of videos can be effectively compared even when there are small differences between the videos in compression factors, source resolutions, start and stop times, frame rates, and so on. Comparison of video fingerprints can be used, for example, to search for and remove copyright protected videos from a video library. Further, duplicate videos can be detected and discarded in order to preserve storage space.

Abstract: A processor and method make use of multiple weak classifiers to construct a single strong classifier to identify regions that contain text within an input image document. The weak classifiers are grouped by their computing cost from low to median to high, and each weak classifier is assigned a weight value based on its ability to accurately identify text regions. A level 1 classifier is constructed by selecting weak classifiers from the low group, a level 2 classifier is constructed by selecting weak classifiers from the low and median groups, and a level 3 classifier is constructed by selecting weak classifiers from the low, median and high groups. Regions that the level 1 classifier identifies as containing text are submitted to the level 2 classifier, and regions that the level 2 classifier identifies as containing text are submitted to the level 3 classifier.

Abstract: A method and system for registering two images is described. The method comprises synthesizing projections from two volumetric images to be registered, estimating a plurality of two dimensional (2D) deformable fields from the projections and generating a three dimensional (3D) deformable fields using a plurality of backprojections of the 2D deformable fields.

Abstract: A computerized method of recognizing an input hand-drawn table formed by freeform line objects comprises transforming each freeform line object of the table into one of a vertical line segment and a horizontal line segment, generating a grid system based on the vertical and horizontal line segments and converting the generated grid system into a table object.

Abstract: Methods, devices and systems are described for transcribing text from artifacts to electronic files. A computer system is provided, wherein the computer system comprises a computer-readable storage device. An image of the artifact is received wherein text is present on the artifact. A first portion of the text is analyzed. Characters representing the first portion of the text are identified at a first confidence level equal to or greater than a threshold confidence level. The characters representing the first portion of the text are stored. A second portion of the text appearing on the artifact is analyzed. A plurality of candidates to represent the second portion of the text are identified at a second confidence level below the threshold confidence level. Finally, the plurality of candidates to a user for selection are presented.

Abstract: Embodiments of the invention provide devices and methods for capturing text found in a variety of sources and transforming it into a different user-accessible formats or medium. For example, the device can capture text from a magazine and provide it to the user as spoken words through headphones or speakers. Such devices are useful for individuals such as those having reading difficulties (such as dyslexia), blindness, and other visual impairments arising from diabetic retinopathy, cataracts, age-related macular degeneration (AMD), and glaucoma.

Abstract: Finger-based identification systems and methods are described. In one aspect, a two-dimensional fingerprint image of a person's finger contacting an input surface is captured. Finger trace data is captured from movement of the person's finger over the input surface. Based on the captured two-dimensional fingerprint image and the captured finger trace data, a determination is made whether the person corresponds to an enrolled person.

Abstract: A de-skew method of an image forming apparatus is provided which includes reading an image on a print medium fed through an automatic document feeder (ADF); detecting a leading edge of the print medium and calculating a skew angle of the read image; comparing the calculated skew angle to a first threshold and determining whether to perform a de-skew operation; and setting skew compensation levels based on the calculated skew angle and performing different de-skew operations according to the set skew compensation levels to output a de-skewed image when the absolute value of the calculated skew angle is equal to or greater than the first threshold.

Abstract: A system is provided for generating an online biometrically accurate electronic signature. The system includes a computer interface module which records movement of a cursor on a computer screen and outputs the recorded data. A signature generation module which receives the recorded data and generates a graphical image based upon the recorded data.