Matsushita Electric Industrial Co., Ltd.

Panasonic Corporation

Yue Ma

Jinhong K Guo

Daniel P Lopresti

Junichi Kanai

Jian Zhou

Andrew Stephen Tomkins

Dennis Bushmitch

Mu Li

Yu-kun Tong

Anhui Wang

Tian-shun Yao

Wenliang Chen

Jing-bo Zhu

Tianshun Yao

Chi Zhang

Jingbo Zhu

Min Yi

An EPG contents collection and recommendation system includes an EPG database of identifications of available programs. A program information acquisition module applies text classification to detailed descriptions of the available programs. An EPG recommendation module recommends an available program to a user based on the text classification. Preferably, EPG contents are collected from publicly available TV websites and parsed into a uniform format. For example, contents are vectorized, and a Maximum Entropy technique is applied. Also, user interaction with the EPG database is used to form a user profile database. Further, classifiers are trained based on contents of the user profile database, and these classifiers are used to recommend EPG contents to the user.

Programming guide content collection and recommendation system for viewing on a portable device

An event moderating architecture is provided for exporting event notification messages from an event publishing environment. The event moderating architecture includes: a mobile network device residing outside of the event publishing environment and operable to formulate a subscription request for receiving event notification messages; and an event moderation module adapted to receive the subscription request from the mobile network device and translate the subscription request into a subscription with the event publishing environment. The event moderation module receives a subset of event notification messages from the event publishing environment and forwards select event notification messages in accordance with the subscription request to the mobile network device.

Event moderation for event publishing environments

A method of post-processing character data from an optical character recognition (OCR) engine and apparatus to perform the method. This exemplary method includes segmenting the character data into a set of initial words. The set of initial words is word level processed to determine at least one candidate word corresponding to each initial word. The set of initial words is segmented into a set of sentences. Each sentence in the set of sentences includes a plurality of initial words and candidate words corresponding to the initial words. A sentence is selected from the set of sentences. The selected sentence is word disambiguity processed to determine a plurality of final words. A final word is selected from the at least one candidate word corresponding to a matching initial word. The plurality of final words is then assembled as post-processed OCR data.

Post-processing system and method for correcting machine recognized text

An advertising content redelivery system for use with real-time broadcasting and time shift recording includes a confirmation component detecting skipping of advertising content by a user. An input is receptive of user preferences relating to redelivery of skipped advertising content, and a redelivery module redelivers skipped advertising content to the user in accordance with the user preferences. In another aspect, skipped advertising content is redelivered to the user in a non-intrusive manner that does not interfere with user enjoyment of primary media content.

System and method for re-assuring delivery of television advertisements non-intrusively in real-time broadcast and time shift recording

A system and method for identifying and separating handwritten text from machine printed text in a document having a combination of handwritten text and machine printed text. In one embodiment, the present invention is installed as an intelligent printing control interface in a conventional computer and allows any document generated by any application to be selectively processed to remove any handwritten text prior to printing of the document, under the control of the user. In an alternative embodiment, the present invention is installed as an intelligent printing control interface in a conventional digital copy machine, which allows any document being copied to be selectively processed to remove any handwritten text prior to printing of the document, under the control of the user. The present invention employs a handwriting separation method which uses Hidden Markov Models to identify regions as either handwritten text or machine printed text.

Printing control interface system and method with handwriting discrimination capability

A scanned document image, including add-on information such as handwritten annotations in addition to printed text lines, is processed by a handwriting detection method. First, at least one projection histogram is generated from the scanned document image. A regular pattern that correlates to the printed text lines is determined from the projection histogram. Second, connected component analysis is applied to the scanned document image to generate at least one merged text line. Each merged text line relates to at least one of the handwritten annotation and the printed text line. By comparing the merged text lines to the regular pattern of the projection histograms, the printed text lines are discriminated from the handwritten annotations.

Detecting and utilizing add-on information from a scanned document image

Cursive Chinese characters are analyzed using a semantic matching process whereby radicals within the character are first extracted and used to reduce the search space of the full lexicon to only those characters containing the matching radical. In performing the radical extraction, the input character is normalized and segmented into strokes that are in turn organized based on stroke up/down information and local maxima and minima information. Obscure breakpoints and connecting strokes are removed in the process. Dynamic program matching is then performed on a stroke basis in which stroke substitution costs are assessed on a point-by-point basis through a variety of techniques, including tangent vector analysis, center relationship assessment and starting point/ending point assessment. Dynamic programming costs are normalized based on the length of the reference radical and location dissimilarities are removed.

Retrieval of cursive Chinese handwritten annotations based on radical model

A method of calculating a skew angle for a two-dimensional barcode, in which the horizontal or vertical edges within the barcode are located, preferably using a finite state recognizer, and an edge array identifying the horizontal or vertical edges is generated. Next, the edge lines within the edge array are identified and traced, and any segments of edge lines within the edge array which are perpendicularly connected are separated. The slope for each edge line within the edge array is calculated, preferably using linear regression techniques. In the preferred embodiment, a discrete histogram of the slopes is generated and the skew angle is then set as the highest value within the discrete histogram. In a preferred embodiment, edge lines within the edge array which are located within a first predetermined threshold of each other are merged with each other and edge lines within the edge array having a length less than a second predetermined threshold are eliminated from the edge array to speed processing. Other techniques for analyzing the edge line slopes are also presented.

Method for determining the skew angle of a two-dimensional barcode

A method of delineating titles within a grayscale image, in which a grayscale image is received, e.g., by scanning a document, and then is subjected to multi-level thresholding to obtain a plurality of binary images representing the original grayscale image. Each of the binary images is preferably pre-processed to filter any noise components from each of the binary images, and then all connected components within each of said binary images are identified, optionally filtered, and then clustered to identify possible title regions within each of the binary images. Next, each binary image is preferably post-processed to merge possible title regions comprising strokes and to remove non-title regions from the previously identified possible title regions in each of the images by comparing characteristics of the previously identified possible title regions to pre-determined criteria. Further, certain of the previously identified possible title regions within each of the binary images which satisfy pre-determined criteria are merged together. Still further, title regions within each of the binary images are combined after the post-processing step and the merging step. Finally, certain of the previously identified possible title regions for different layers are preferably merged to identify all possible title regions. Once the title region are located, various processing can be performed to extract the text from the title region.

Method for extracting titles from digital images

Two-dimensional barcodes surrounded by a quiet zone of white space which may or may not include a border, each barcode having encoded digital information in a bitmap representing preferably randomized encoded data bits, are printed onto a printed medium. To extract the encoded digital information from the printed medium, the printed medium is scanned, then the bitmap is located within the printed medium by moving a window, in stepwise fashion in a predetermined pattern across the printed medium. At each step the portion of the printed medium which is encompassed by the window is tested to determine whether it conforms to one or more characteristics of the bitmap. The skew of the bitmap, if any, is determined, by using a finite-state recognizer in combination with a Hough Transform calculation. In one embodiment, the candidate region is divided into a plurality of horizontal regions, preliminary skew angles are calculated for each region, and the actual skew angle is selected using a voting scheme. Once the skew angle is calculated, the bitmap is deskewed if necessary, cropped, and the randomized digital information is read from the bitmap. Finally, the digital information is derandomized and any error correction codes are removed, in the process correcting and/or recording any errors discovered, thereby reproducing the original encoded digital information.

Method for locating and reading a two-dimensional barcode

Two embodiments of a method of decoding information stored in a two-dimensional barcode printed on a printed medium are introduced. Both embodiments provide an improved method of analyzing horizontal and vertical edge count arrays to identify the column and row centerlines therein to enable the subsequent reading of the binary data located at the intersection of each row centerline and column centerline. In the first embodiment, the centerlines are located by first locating each successive pair of peaks in the respective edge count array, where each peak must have a magnitude greater than a first predetermined value, and then locating a centerline in a valley region between each successive pair of peaks, each of the centerlines having a magnitude less than a second predetermined value. Preferably, each successive pair of peaks in the respective edge count array is separated by a third predetermined value. In addition, the first predetermined value is preferably reduced by a predetermined amount if a second peak within a pair of peaks in the respective edge count array is separated from a first peak by more than a fourth predetermined value, and the second peak is then re-identified using the reduced first predetermined value. The second embodiment alternately employs the method of the first embodiment or a prior art method to reduce the number of errors produced, using the prior art method first to locate the column centerlines and the method of the first embodiment first to locate the row centerlines.

Method for reading a two-dimensional barcode

The user communicates through a digitizing writing surface with the audio/video control apparatus. An on-screen display is generated, providing the user with a user environment in which a wide range of different tasks and functions can be performed. The digitizing writing surface can be incorporated into a hand-held remote control unit and the audio/video control apparatus may likewise be incorporated into existing home entertainment or computer equipment. By tapping on the writing surface a command bar is presented on the screen, allowing the user to select among various functions. Included in these functions is an on-screen programming feature, allowing the user to select programs for viewing or recording by entry of user-drawn annotations or commands via the writing surface.

Video user's environment

The document browser for electronic filing systems supports pen-based markup and annotation. The user may electronically write notes anywhere on a page and then later search for those notes using the approximate ink matching (AIM) technique. The technique segments the user-drawn strokes, extracts and vector quantizes features contained in those strokes. An edit distance comparison technique is used to query the database, rendering the system capable of performing approximate or partial matches to achieve fuzzy search capability.

Growing community of inventors

West Windsor, NJ, United States of America

Yue Ma