Canon Kabushiki Kaisha

Hamadi Jamali

Ivan Bojer

A computer implemented method, system, and computer-readable medium for modifying and creating networked documents (). To create a document (), the method includes the acts of reading a control sheet (), reading a content sheet (), and generating the document () using the control sheet () and the content sheet (). To modify a document (), the method includes the acts of reading a control sheet () having commands, reading a content sheet () having content (), retrieving the document () using a command from the command sheet (); and modifying the document using the control sheet () and the content sheet (). The content sheet includes content of the document () and the control sheet () specifies the location of the content on the Web page. Either or both of the control sheet () and content sheet () may include print content.

Automatically uploading and organizing documents in a document server

Communication channel characteristics are determined without the use of a training mode using a single-valued solution. A received signal x is sent to an equalizer ( ) which compensates for noise added to the received signal x during transmission. To accurately determine the weights of the equalizer ( ), the output of the equalizer ( ) is transmitted to an amplitude square extractor ( ) to generate a value representative of the amplitude of the received signal x . Then, a forward-mapping module ( ) maps the amplitude value from the n-dimensional space of the amplitude value to an augmented space having, in a preferred embodiment n dimensions. In the augmented space, an augmented space blind adaptation mechanism ( ) is applied to generate a single-valued channel characteristic value in terms of an augmented space variable. Then, a backward-mapping module ( ) is applied to generale the optimal weights for the equalizer ( ) allowing an accurate recovery of the original signal s . The principles of the present invention can be applied to generate all of the filters required in high-speed data communications, and can be used for any other system in which channel characteristics are desired.

Digital signal processing for high-speed communications

The present invention is a computer-implemented method for calculating word accuracy. Word grouping accuracy values (,) are calculated (,) by using the character accuracy values (,) calculated by an OCR program present in a computer system. The present invention preferably uses these character accuracy values (,) to create a word grouping accuracy value (,). Various methods are employed to calculate the word accuracy (,), including binarizing the character accuracy values (,), modified averaging of the character accuracy values (,), and creating fuzzy visual displays of word grouping accuracy values (,). The calculated word grouping accuracy values (,) are then adjusted based upon known OCR strengths and weaknesses, and based upon comparisons to stored word lists and the application of language rules. In a system with multiple character recognition techniques, the system can compare the accuracy values (,) of different versions of the word groupings to find the most accurate version. Then, the most accurate version of the word groupings is kept.

Word grouping accuracy value generation

An attribute extracting module (,) extracts attributes from a document (,) input into the system. An attribute comparison module (,) compares extracted attributes with multiple classes (,) of documents. Upon determining that attributes of the document (,) match attributes of one of the classes (,), the document (,) is classified as belonging to the class (,) and is processed in accordance with the system actions associated with the matched class (,). In one embodiment, attributes of the input document (,) are compared to the documents (,) belonging to the matched class (,) which are already on the system. If the system determines that the input document (,) matches one of the existing images (,), the user (,) is alerted that the input document (,) already exists in the system. In a further embodiment, a match is determined in response to a comparison quality measure determined by a quality assessment module (,). The comparison quality measure measures the accuracy of the comparison. If the comparison quality measure exceeds a threshold, a match is determined to have been made. The comparison quality measure examines, among other factors, sizes, locations, and word accuracy values of matching regions within the input document (,) and the matching class (,).

Adaptive recognition of documents using layout attributes

Method and apparatus for separating touching characters within an optical character recognition (OCR) computer (1). An input document (20) is scanned by scanner (2), forming a set of scan line's (3). A segmentation process (4) is performed on the scan lines (3) to create a set of segmented image boxes (5). Candidate characters within the image boxes (5) are classified by a classification module (6), based upon a library of stored models (7). When the candidate characters have high degree of confidence, they are classified and coded into a binary form (8), such as ASCII. Those candidate characters that are not classified are processed by a touching character decision module (9) to determine whether a series of separation modules (10-14) is to be invoked. The execution of modules (10-13), followed by the reexecution of modules (4) and (6), may or may not cause all of the touching characters to be separated. Any touching characters that remain are subjected to one or more reprocessing cycles. The reprocessing can entail examination (14) of adjacent scan lines (3), shifting of separation threshold T by separation threshold determination module (10), or re-execution of deconvolution step (12) with changed parameters or structure.

Growing community of inventors

Redwood City, CA, United States of America

Hamadi Jamali