Applying the zoning information to whole word recognition
نویسنده
چکیده
The whole word recognition process described in this report aims at limiting the recognition domain, i.e. the size of the lexicon used for a particular word. The process consists of the following stages: • calculating the word zoning information and the position of ascenders/descenders within the word; • building word shape information using the obtained zoning information; • locating words of similar shape within the lexicon; • assessing the similarity of shapes of the located words. Zoning information is described using the combined histogram and local extrema analysis method described in [5]. Other aspects are newly developed by the author and described in the following sections.
منابع مشابه
Holistic Farsi handwritten word recognition using gradient features
In this paper we address the issue of recognizing Farsi handwritten words. Two types of gradient features are extracted from a sliding vertical stripe which sweeps across a word image. These are directional and intensity gradient features. The feature vector extracted from each stripe is then coded using the Self Organizing Map (SOM). In this method each word is modeled using the discrete Hidde...
متن کاملFeature Extraction: on the Importance of Zoning Information in Cursive Script Recognition
Cursive script has many ambiguities. Feature extraction, by locating some specific characteristics of a writing sample in isolation or in combination with other features, can minimise the effect of these ambiguities. There are many features that can be extracted from any given sample. Information about the expected vertical letter position within the word, the zoning information, is envisaged t...
متن کاملZoning invariant holistic recognizer for hybrid recognition of handwriting
As human handwriting is immensely variable, no single recognition approach appears capable of uniformly good performance. Combining results of multiple recognition approaches gives improved recognition rates. Recognizers used in such a hybrid approach need to be different, so that their results are complementary. Segmentation-based and wholistic recognition approaches are methods which are diff...
متن کاملWord shape analysis for a hybrid recognition system
~ This paper describes two wholistic recognizers developed for use in a hybrid recognition system. The recognizers use information about the word shape. This information is strongly related to word zoning. One of the recognizers is explicitly limited by the accuracy of the zoning information extraction. The other recognizer is designed so as to avoid this limitation. The recognizers use very si...
متن کاملبه کارگیری سامانه تبدیل گفتار به متن در حوزه مراقبت سلامت: مزایا، محدودیتها، راهکارها
Background and Aim: The applicability of any technology to enter a certain field is determined by defining the advantages and disadvantages of the system in that field. The aim of this study is to show the advantages and limitations of using speech recognition systems in health care and providing practical solutions to improve the acceptability of the system in that field. Materials and M...
متن کامل