Abstract: Methods and apparatus for detecting the presence of combs, determining their shape and removing the combs from a scanned form in an automated manner are described. Horizontal and vertical line feature analysis is combined with knowledge of the usual size, shape, and spacing characteristics of lines which form a comb. Vertical and horizontal lines failing to meet certain characteristics, e.g., size or shape characteristics, are eliminated from consideration. Vertical lines which do not intersect a horizontal line are also eliminated from consideration. Confidence measures for different possible comb shapes are generated and the most probable comb shapes as indicated by the confidence measures are included in a comb list. The comb list may be output for use in further processing, e.g., comb removal and/or data extraction processing.

Abstract: Upon searching for a digital document of a document image, if information indicating a security level “vector conversion of objects is NG” is embedded in the document of interest, information of objects to be used in the search is deficient, thus disturbing satisfactory search processing. To solve this problem, a document image is read, and the read image is divided in accordance with the attributes of image regions. Designation of an image region whose image is to be vector-converted of the divided image regions is accepted, and additional information included in the designated image region is extracted. Search processing of a data file corresponding to the document image is controlled in accordance with the presence/absence of the additional information or the interpretation result of the additional information.

Abstract: A segmentation operation is applied to an input image to identify foreground objects of interest, and then a shadow removal operation is applied to remove any detected shadows from the foreground segmentation. The shadow removal algorithms can leave holes and bisections in the segmentation map, however, which will then subsequently impact on an object detection step performed using connected component analysis. To get around this problem, a conditional morphological dilation operation is applied to the segmentation map to ‘grow’ the segmented blobs to fill in any holes and bisections, without re-growing shadow pixels in the segmentation. The result is an object detection method and system which is robust to illumination changes causing shadows and/or highlights.

Abstract: A system for automatically recognizing a handwriting image and converting such image to text data including a sequence of validated words, has an image input device, a number of handwriting recognition engines, and control unit. A first handwriting recognition engine is responsive to the image input device, for analyzing the data file and providing one or more possible text words for each successive word in the data file. The first handwriting recognition engine further provides a resemblance indication for each possible text word indicating a level of resemblance between its appearance and the appearance of the handwritten word in the data file. In the event that there is not a high level of confidence in the selection of the first handwriting recognition engine, a selection of a validated word is based on the selections of one or more of the other handwriting recognition engines.

Abstract: A method for reducing an artifact within an image of a substance is described. The method includes generating the image of the substance, and constraining a measured linear attenuation coefficient of a pixel of the image based on at least one of a measured diffraction profile, a measured effective atomic number, and a measured packing fraction of the substance.

Abstract: A decoding apparatus includes: a decoding section for decoding input encoded data; an output section for outputting data decoded by the decoding section, in accordance with an output control signal; a plurality of copyright information detection sections for detecting different types of copyright information from the data decoded by the decoding section and each outputting the detected copyright information; an output control section for outputting the output control signal in accordance with the copyright information detected by at least one of the plurality of copyright information detection sections; and a detection control section for controlling the plurality of copyright information detection sections so that at least one of the plurality of copyright information detection sections has a period of time in which the at least one copyright information detection section does not perform process.

Abstract: A method and a device for discriminating an obscene video using a time-based feature value are provided. The method includes: forming a first time-based flow of predetermined feature values varying with the lapse of time from one or more types of videos which are normalized with a first time interval; extracting a feature value varying with time from an input video of which obsceneness is to be determined and which is normalized with a second time interval, and forming a second time-based flow of the extracted feature value; and determining the obsceneness of the input video by calculating a loss value between the first time-based flow and the second time-based flow. The videos such as movies and dramas in which many persons appear have different obscenity characteristics from that of pornography, so it is possible to enhance reliability in determination of obsceneness.

Abstract: An image encoding and decoding scheme operable according two different modes depending on properties of the processed image is disclosed. In the encoding, an image is decomposed into image blocks (600) comprising image elements (610). The blocks (600) are compressed into block representations (700A, 700B) according to one of two compression modes. A block representation (700A; 700B) comprises two codewords (720A, 730A; 720B, 730B) representing properties of the image elements (610) in the block (600) and a sequence (740A; 740B) of image element associated indices indicative of one of the codewords (720B, 730B) or a property representation generated based on a codeword (730A). The block representation (700A; 700B) also includes a mode index representing the mode, according to which the block representation (700A; 700B) was compressed. This mode index can be provided before, during or after generation of the codewords (720A, 730A; 720B, 730B) and index sequence (740A; 740B).

Abstract: In a method to determine a selection vector that indicates a displacement of an image area from a first position in a first image to a second position in a second image, a set of prediction vectors and a set of test vectors are provided. Using selected test vectors, an image comparison is performed to supply an image comparison result for each selected test vector. The selected test vectors and at least one prediction vector are compared to provide at least one test vector comparison result for each selected test vector. The image comparison result and the at least one test vector comparison result are linked to provide at least one quality characteristic for each selected test vector. A ranking order is determined for these quality characteristics, where at least one test vector is selected as the displacement vector based on the ranking order determined.

Abstract: Systems and methods for perceptual image preview are described. In one aspect, a naïve preview image is generated by downsampling a larger image. Perceptual features of the larger image are then detected. Information associated with the detected perceptual features is then incorporated into the naïve preview image to create a perceptual preview image. Since the perceptual preview image incorporates information associated with the detected perceptual features, a viewer of the perceptual preview image will be more likely to detect the presence or absence of such perceptual features in the larger image.

Abstract: An image compilation production system and method, for use in a setting attended by multiple visitors. The system comprises multiple identification devices, multiple digital image capturing devices, and a reader device associated with each of the image capturing devices. Each identification device includes an electronic data storage device having identification data stored therein. One of the identification devices is carried by at least one of the visitors to the setting. The reader device activates the digital image capturing device to capture the image of the visitor when the identification data stored in the electronic data storage device of the identification device is carried within the detection range of the associated reader device by the visitor.

Abstract: An alpha image encoding and decoding scheme operable according two different modes is disclosed. In the encoding, an alpha image is decomposed into alpha image blocks (600) comprising image elements (610). The blocks (600) are compressed into block representations (700) according to one of the two compression modes. A block representation (700) comprises a color codeword (720), an intensity codeword (730), an alpha codeword (740) and a sequence (750) of image element associated indices indicative of one of the codewords (730, 740). The compression and decompression mode to use for a block (600) is determined based on the alpha codeword (740). In a high alpha-resolution mode, the index sequence (750) comprises alpha indices selecting one of the quantized alpha values (740A, 740B) of the alpha codeword (740) and intensity indices selecting an intensity modifier from a modifier set represented by the intensity codeword (730).

Abstract: A deblocking method, for removing blocking artifacts comprises selecting a plurality of first pixels according to a bandwidth of a memory device, wherein the first pixels are uniformly distributed at two sides of a block boundary; calculating a first value according to the first pixels stored in the memory device; determining a computing mode according to the first value and a first predetermined value; generating a plurality of second pixels according to the first pixels and the computing mode; and replacing the first pixels stored in the memory device with the second pixels.

Abstract: A pixel boundary difference detector detects a pixel boundary difference across a pixel boundary on the basis of a difference value between pixel values of adjacent pixels across the pixel boundary on a picture plane of an input image frame, and a predicted pixel value on the pixel boundary predicted from at least a plurality of pixels on one side of the pixel boundary, an accumulator accumulates the pixel boundary differences for one image frame, and a block noise detector detects a block noise on the basis of a result of the accumulation. The accuracy of block noise detection is improved, the effect of block noise reduction is improved, and the picture quality is improved.

Abstract: An improved method of watermarking picture identification documents (IDs) such as passports, driver's licenses, identification cards and the like which combines biometric information with digital watermarking to provide an improved secure picture ID document and authentication of same. A facial image—that is part of the identification document—is processed such that particular facial features are extracted from the overall facial image. The extracted features are used to generate a watermark key that is subsequently used to embed a unique watermark into the facial image or other location on the identification document.

Abstract: A method of detecting a corner, and an apparatus to perform the method, the method including acquiring a visible light image and an infrared image of a spatial area of interest; and extracting corner information of the spatial area of interest using the acquired visible light image and the acquired infrared image.

Abstract: An article confirmation method has reading irreproducible fine characteristics from a genuine article, reading irreproducible fine characteristics from an article to be confirmed, comparing the irreproducible fine characteristics between the genuine article and the article to be confirmed, and determining authenticity of the article to be confirmed based on a comparison result.

Abstract: Various technologies and techniques are disclosed that improve cursive handwriting recognition. Cursive handwriting input is received from a user. The system performs a hierarchical prototype search as part of a recognition operation. A same space search is performed against a mixed database that has both print and cursive samples. A same space search is also performed against a cursive database that has only cursive samples. The results of these two same space searches are merged into a combined alternate list. The combined alternate list is then used as a constraint for the dynamic time warp searches that are performed against the mixed and cursive databases, respectively. The results of the dynamic time warp searches are also merged into a final combined alternate list, and the combined alternate list is used to make a recognition decision regarding the user's handwritten input.

Abstract: A method is provided for tracking a non-rigid object in a sequence of frames of a video. Features of an object are extracted from the video. The features include locations of pixels and properties of the pixels. The features are used to construct a covariance matrix. The covariance matrix is used as a descriptor of the object for tracking purposes. Object deformations and appearance changes are managed with an update mechanism that is based on Lie algebra averaging.

Abstract: A computer method and system for deblurring an image is provided. The invention method and system of deblurring employs statistics on distribution of intensity gradients of a known model. The known model is based on a natural image which may be unrelated to the subject image to be deblurred by the system. Given a subject image having blur, the invention method/system estimates a blur kernel and a solution image portion corresponding to a sample area of the subject image, by applying the statistics to intensity gradients of the sample area and solving for most probable solution image. The estimation process is carried out at multiple scales and results in a blur kernel. In a last step, the subject image is deconvolved image using the resulting blur kernel. The deconvolution generates a deblurred image corresponding to the subject image.