Topic
Intelligent word recognition
About: Intelligent word recognition is a research topic. Over the lifetime, 2480 publications have been published within this topic receiving 45813 citations.
Papers published on a yearly basis
Papers
More filters
Patent•
23 Jul 2003
TL;DR: In this article, a voice recognition method for recommending use of misrecognized synonymous words to a user as replaced words of recognition object words when recognition vocabularies are misrecognised.
Abstract: PROBLEM TO BE SOLVED: To provide a voice recognition method for recommending use of misrecognized synonymous words to a user as replaced words of recognition object words when recognition vocabularies are misrecognized, even if the recognition vocabularies to be used are wholly registered from first, and to provide a voice recognition device. SOLUTION: A prescribed input voice, pronounced by the user from a voice input part 101, is acquired to recognize the input voice with a voice recognition part 106 so as to be presented to the user by outputting a recognition from GUI 102 or a voice output part 110. Determination as to whether the recognition result is correct is received from the user, and when the recognition result is misrecognized, correct recognition object words for the input voice are designated. The synonymous words of the correctly recognized object words are retrieved, and recommended to the user to be used as the replaced words of the correctly recognized object words. In addition, an operation command, corresponding to the correct recognition object words, is further made to correspond with the synonym words. COPYRIGHT: (C)2005,JPO&NCIPI
15 citations
TL;DR: A one- dimensional feature set is introduced, which embeds two-dimensional information into an observation sequence of one-dimensional string, selected from a code-book, which provides a consistent normalization among distinct classes of shapes, which is very convenient for Hidden Markov Model (HMM) based shape recognition schemes.
15 citations
07 Mar 1996
TL;DR: Based on the capabilities of morphological operators in extracting shape features, a new method for character recognition in Persian machine printed documents is introduced in which the hit-or-miss operator is used to determine which patterns exist or do not exist in the input images of the recognition system.
Abstract: Based on the capabilities of morphological operators in extracting shape features, a new method for character recognition in Persian machine printed documents is introduced. Given the image of a printed character is available with high enough SNR such that its regular shape is preserved, some common primitive patterns can always be found after thinning different images of a single character. This property has inspired the development of our morphological processing in which the hit-or-miss operator is used to determine which patterns exist or do not exist in the input images of the recognition system. All the required processing before feature extraction including image enhancement, segmentation, and thinning are also performed using the hit-or-miss operator. Having the input words described in terms of some pre-defined patterns, the system knowledge base, holding descriptions for all characters, is searched for possible matches. Finding a match ends in the recognition of a character. This approach is proved to be fast and reliable in practice.© (1996) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.
15 citations
30 Aug 1992
TL;DR: It is shown that the clustering algorithm can correctly locate groups of short function words with better than a 95 percent correct rate.
Abstract: A technique is presented that determines equivalences between word images in a passage of text. A clustering procedure is applied to group visually similar words. Initial hypotheses for the identities of words are then generated by matching the word groups to language statistics that predict the frequency at which certain words will occur. This is followed by a recognition step that assigns identifications to the images in the clusters. This paper concentrates on the clustering algorithm. A clustering technique is presented and its performance on a running text of 1062 word images is determined. It is shown that the clustering algorithm can correctly locate groups of short function words with better than a 95 percent correct rate. >
15 citations
20 Oct 1993
TL;DR: By adopting several techniques of offline handwritten Chinese character recognition (HCCR), a new approach is proposed for online HCCR that solves the problems of stroke order variation, stroke number variation, and some kinds of connective strokes.
Abstract: By adopting several techniques of offline handwritten Chinese character recognition (HCCR), a new approach is proposed for online HCCR. First, an online handwritten Chinese character (HCC) sample library is built. Then, a five layer representation model of HCC based on attributed structural relationships among line segments is proposed. A kind of recognition device called a detector is designed to detect and identify line segments and their relationships. Finally, a recognition network composed of detectors is introduced. This approach solves the problems of stroke order variation, stroke number variation, and some kinds of connective strokes. An online HCCR system based on this approach has perfectly solved the above-mentioned problem with an average recognition rate more than 93% for unlearned handwriting and with real-time response. >
15 citations