Abstract: An image processing apparatus processes input pixel data and outputs the processed pixel data as output pixel data. The image processing apparatus includes an input reliability calculation section for calculating an input reliability indicating the reliability of the input pixel data, an output reliability calculation section for calculating an output reliability indicating the reliability of the output pixel data, a motion-amount detecting section for detecting the amount of the motion of the input pixel data, a compensation section for compensating the output reliability according to the amount of the motion, and a processing section for processing the input pixel data according to the input reliability and the compensated output reliability and for outputting the output pixel data.

Abstract: An image processing apparatus including a receiving unit, an extraction means, and a conversion means is disclosed. The receiving unit receives a first document data and a second document data obtained by reading respectively a first document and a second document each having at least one drawing. The extraction means extracts a first caption group for identifying the drawing contained in the first document and a second caption group for identifying the drawing contained in the second document. The conversion means converts the first caption group and the second caption group into a third caption group so that a character string in the first caption group does not overlap a character string in the second caption group.

Abstract: An image processing device is structured such that an appropriate judgement of an image, at which blurring or disappearance or the like will occur, is possible. When pixels, which form a line image at which there is the possibility that blurring or disappearance will occur at the time of printing by using a printing plate, are extracted, a line image warning function gives notice by displaying a warning message on a monitor of a client terminal. Thereafter, image converting and print setting are carried out such that an extracted line image is clarified. In this way, when a proof is prepared, an image, at which there is the possibility that blurring or disappearance will occur on a printed matter obtained by using a printing plate, is clarified, and appropriate proofing is possible.

Abstract: A method and image data acquisition service arrangement are disclosed that facilitate standardizing the process of adding metadata to acquired image information downloaded from a connected image capture device to a computer system. An image acquisition service analyzes image information downloaded from the image capture device and renders new metadata values based upon applied analytical algorithms/filters. Thereafter, the image information and new metadata are rendered available to other processes that use the image information and new metadata.

Abstract: Described herein is a technology for semantically classifying areas of an image (and/or the images themselves) as one of a number of multiple discriminating categories. More particularly, the technology employs one or more hierarchical, probabilistic techniques for performing such classification. Such technology is particularly useful in fields of image classification and image retrieval. The architecture of such technology employs multiple hierarchical layers. The architecture is based on modeling class likelihoods at each of such layers separately and then combining these to form an overall estimate of the posterior, conditioned on the data. The task of combining the estimated class likelihoods at each layer is made more efficient by assuming statistical independence between layers. This abstract itself is not intended to limit the scope of this patent. The scope of the present invention is pointed out in the appending claims.

Abstract: An overlay vernier pattern for measuring multi-layer overlay alignment accuracy and a method for measuring the same is provided. A distance between a first alignment mark in a first material layer and a second alignment mark in an underlying second material layer is measured, so as to provide an alignment offset between the first material layer and the second material layer. In addition, a distance between the second alignment mark in the second material layer and a third alignment mark in a third material layer underlying the second material layer is measured, so as to provide an alignment offset between the second material layer and the third material layer. Because the second alignment marks can be repeatedly used, scribe line areas for forming these alignment marks and measuring time are saved to increase the production throughput.

Abstract: An overlay vernier pattern for measuring multi-layer overlay alignment accuracy and a method for measuring the same is provided. A distance between a first alignment mark in a first material layer and a second alignment mark in an underlying second material layer is measured, so as to provide an alignment offset between the first material layer and the second material layer in addition, a distance between the second alignment mark in the second material layer and a third alignment mark in a third material layer underlying the second material layer is measured, so as to provide an alignment offset between the second material layer and the third material layer. The second alignment marks can be repeatedly used when measuring the alignment accuracy between the first and the second material layers measuring the alignment accuracy between the second and the third material layers.

Abstract: A fingerprint authenticating system includes a fingerprint registering unit and a fingerprint collating unit. The fingerprint registering unit takes a first fingerprint data indicating a first portion of a first fingerprint from a first fingerprint sensor, registers said first fingerprint data to a memory unit, and takes a second fingerprint data indicating a second portion of a second fingerprint from a second fingerprint sensor. The fingerprint collating unit collates said second fingerprint data with said first fingerprint data to confirm whether or not said first fingerprint is equal to said second fingerprint. Here, an area of the first portion is equal to or larger than an area of the second portion.

Abstract: A device and method for embedding plural kinds of additional information or multiple bits of additional information into one picture is provided. A region information generating step generates region information to specify at least two regions in the real picture spatial or frequency space corresponding to the picture data, a coefficient sequence generating step sets at least two coefficient sequences, which are different from each other, a watermark pattern generating step allocates the coefficient sequences to each divided region to generate watermark patterns, and an embedding step embeds digital watermark information by changing the picture data using the watermark patterns.

Abstract: Pattern matching apparatus for comparing signal samples with a pattern to find signal samples substantially matching said pattern, the apparatus comprising: a projector for projecting said signal samples over a tree of projection vectors of successively increasing frequency at nodes of said tree to successively provide projection values, a distance measurer, associated with an output of said projector for determining a distance between a projection value and a corresponding projection value of said pattern, said distance being an expression of a minimum bound of a true distance between said sample and said pattern, and a thresholder, associated with an output of said distance measurer for applying a threshold to said minimum bound to successively reject samples at respective nodes.

Abstract: A search method is disclosed for finding bar code symbols and various two-dimensional symbols, regardless of orientation, that is efficient, robust, and easy to use. The method works well on cluttered backgrounds, on skewed symbols, when symbols are almost touching, and when symbols are adjacent to text. The method includes choosing a candidate start region in the image, and then determining whether the candidate start region includes at least a portion of a candidate oriented encoded signal. Next, an approximate orientation of the candidate oriented encoded signal is determined. Then, the candidate start region is grown, using the approximate orientation, so as to form a candidate symbol region that encloses an entire candidate code symbol, including at least a portion of the candidate start region. The method is finely responsive to orientation.

Abstract: A color image sensor sequentially acquires a plurality of fingerprint images when a finger is pressed against the detector surface. A color information extraction unit detects the finger color in synchronization with the input of the plurality of fingerprint images. An areal information extraction unit detects a physical quantity representing the pressure applied by the finger to the color image sensor when the plurality of fingerprint images are acquired, particularly, the quantity related with the area of the finger in contact with the detector surface. A living body identification unit determines whether the finger is a live or dead one by the analysis of correlation between the physical quantity and the finger color. According to this configuration, even if the finger color does not change much, it is possible to distinguish living bodies from dead ones if there is a sufficient correlation with information such as the area of the fingerprint that reflects the finger pressure.

Abstract: An adapter suitable for use with digital cameras (and other digital imaging devices) converts the digital camera to a biometric scanner. One exemplary adapter includes a receptacle for receiving a body part, a coupler for attachment to the digital camera, and one or more optical components for acquiring an image of a biometric characteristic of the body part. Optional features might include: (a) automatically detecting of the body part and transmitting a command to an input interface of the camera; (b) using auxiliary lighting to illuminate the biometric image; (b) digitally post-processing the image after acquisition but prior to authentication; and/or (d) acquiring a biometric utterance of the user providing the biometric image for dual-factor biometric authentication; and/or still other features described herein.

Abstract: The digital camera being capable of recording stereoscopic first and second still images includes an imaging device that captures the first and second still images in this order, a display unit that displays a moving image captured by the imaging device to allow framing an image to be taken. The display unit superimpose a framing assisting pattern on the moving image to facilitate the framing of the image to be taken. A grid pattern may be utilized as the framing assisting pattern. After the first still image is captured, the display unit displays the first still image, with the framing assisting pattern superimposed thereon, besides the moving image after said first still image is captured.

Abstract: Images having been subjected to image processing optimal for each user or each output device are obtained. Correction function calculation means calculates correction functions for correcting image data sets for each user ID or for each device ID, and correction function storing means stores the calculated correction functions. When the image processing is carried out on the image data sets, the correction functions corresponding to the user ID or the device ID added to the image data sets are searched for and correction parameter calculation means calculates correction parameters based on the correction functions. The image processing is then carried out on the image data sets according to the correction parameters to generate corrected image data sets.

Abstract: In computerized recognition having multiple experts, a method and system is described that obtains an optimum value for an expert tuning parameter in a single pass over sample tuning data. Each tuning sample is applied to two experts, resulting in scores from which ranges of parameters that correct incorrect recognition errors without changing correct results for that sample are determined. To determine the range data for a given sample, the experts return scores for each prototype in a database, the scores separated into matching and non-matching scores. The matching and non-matching scores from each expert are compared, providing upper and lower bounds defining ranges. Maxima and minima histograms track upper and lower bound range data, respectively. An analysis of the histograms based on the full set of tuning samples provides the optimum value. For tuning multiple parameters, each parameter may be optimized by this method in isolation, and then iterated.

Abstract: A method and apparatus is disclosed for reading and decoding information extracted from a form. In the system of the present invention, packages are randomly placed on a conveyor belt, with their labels facing a two-camera subassembly. As the conveyor belt moves, the two-camera subassembly continuously takes images of the belt underneath the overhead camera. The design of the camera permits it to take a high resolution image of a non-singulated, unjustified package flow. A digital image of the packages within the field of view of the camera is then transferred to the processing system for analysis. The processing system identifies individual packages in the image, extracts them and then analyzes the information written on the package labels. The analysis process utilizes conventional Optical Character Recognition (OCR) and Intelligent Character Recognition (ICR) techniques to evaluate the information written on the package label.

Abstract: A data analyzer/classifier comprises using a preprocessing step, and energy minimization step, and a postprocessing step to analyze/classify data.

Abstract: Methods and apparatus of the invention enable users to request access to one or more electronic images of pages in a physical text. When the user is identified and user ownership of the physical text is confirmed, the user is given access to the requested electronic images in accordance with the one or more access rules. Electronic images of pages may be automatically added to a user-personalized library of electronic content for later access. A flag associated with the user and the pages images may be set to indicate confirmed user ownership of the physical text. A user may purchase a physical text itself or purchase an item that the physical text normally accompanies. Electronic page images may be acquired by scanning printed pages of the text or from a user upload. Access to the electronic images of a physical text is based on user ownership of the physical text.

Abstract: A user can enter handwritten electronic ink into a writing guide on an electronic page of an electronic tablet. An ink processing module can display the handwritten electronic ink as it is rendered on the electronic page by the user. Upon the occurrence of a predefined event, the writing guide module can automatically recognize and convert the electronic ink to text without the user's manual intervention. The writing guide module can replace the electronic ink in the writing guide with the converted text.