Using Hierarchical Shape Models to Spot Keywords in Cursive Handwriting Data
نویسندگان
چکیده
Diierent instances of a handwritten word consist of the same basic features (humps, cusps, crossings, etc.) arranged in a deformable spatial pattern. Thus, keywords in cursive text can be detected by looking for the appropriate features in the \correct" spatial conng-uration. A keyword can be modeled hierarchically as a set of word fragments, each of which consists of lower-level features. To allow exibility, the spatial conng-uration of keypoints within a fragment is modeled using a Dryden-Mardia (DM) probability density over the shape of the connguration. In a writer-dependent test on a transcription of the Declaration of Independence (1300 words, 7500 characters), the method detected all eleven instances of the keyword \govern-ment" with only four false positives.
منابع مشابه
A Learning-based Approach to Cursive Handwriting Synthesis ?
This paper proposes a learning-based approach to synthesize cursive handwriting of the user’s personal handwriting style, by combining shape models and physical models together. In the training process, some sample paragraphs written by the user are collected and these cursive handwriting samples are segmented into individual characters by using a two-level writer-independent segmentation algor...
متن کاملAn Effective Character Separation Method for Online Cursive Uyghur Handwriting
There are many connected characters in cursive Uyghur handwriting, which makes the segmentation and recognition of Uyghur words very difficult. To enable large vocabulary Uyghur word recognition using character models, we propose a character separation method for over-segmentation in online cursive Uyghur handwriting. After removing delayed strokes from the handwritten words, potential breakpoi...
متن کاملThe Hierarchical Hidden Markov Model : Analysis and
We introduce, analyze and demonstrate a recursive hierarchical generalization of the widely used hidden Markov models, which we name Hierarchical Hidden Markov Models (HHMM). Our model is motivated by the complex multiscale structure which appears in many natural sequences, particularly in language, handwriting and speech. We seek for a systematic, unsupervised approach to the modeling of such ...
متن کاملUsing Shape models for Error Correction of On-line Handwriting
A writer-dependent technique is proposed for automatically correcting written spelling errors in on-line cursive handwriting. In a training process, handwriting samples of the user are collected and segmented into characters by using a writer-independent segmentation algorithm. Shape models are built on these samples to capture the user’s writing style for each character. In the application pro...
متن کاملOn-line cursive handwriting characterization using TF-IDF scores of graphemes
In this paper, we present an approach for characterizing the on-line cursive handwriting of different writers, which may consist in identifying the writer or his handwriting style. This method is inspired from information retrieval methods and is designed to be embedded in an adaptive word recognizer. We perform experiments assessing the effectiveness of the proposed method for writer identific...
متن کامل