An Efficient Radical-Based Algorithm for Stroke-Order Free and Stroke-Number Free Online Kanji Character Recognition
نویسندگان
چکیده
This paper investigates improvements of an online handwriting stroke-order analysis algorithm ― radical-based cube search (RBCS), which based on free stroke-order generation model called cube graph and dynamic programming (DP). We propose a novel model to resolve both of the stroke-order free and the stroke-number free problems, with lower time complexity of stroke-order search DP. By dividing character into radicals, the model is decomposed into intra-radical graphs and an inter-radical graph. This decomposition considerably reduces the time and spatial complexity. Within the intra-radical graphs, we resolve the stroke-number free problem by using a model called multilayer cube graph. Experimental results showed a higher recognition accuracy of 91.65%, and a practical average recognition time of 0.45s per character.
منابع مشابه
A Comparative Study of Stroke Correspondence Search Algorithms for Online Kanji Character Recognition
The stroke to stroke correspondence search between an input character and a reference character plays an important role in stroke-order-free online Kanji character recognition. It has a vital influence on the recognition performance. Various stroke correspondence algorithms have been proposed, and official comparative studies for clarifying the relative superiority of those algorithms are hoped...
متن کاملGeneration of Hierarchical Dictionary for Stroke-order Free Kanji Handwriting Recognition Based on Substroke HMM
This paper describes a method of generating a Kanji hierarchical structured dictionary for stroke-number and stroke-order free handwriting recognition based on substroke HMM. In stroke-based methods, a large number of stroke-order variations can be easily expressed by just adding different stroke sequences to the dictionary and it is not necessary to train new reference patterns. The hierarchic...
متن کاملبازشناسی برخط حروف مجزای دستنویس فارسی بر اساس تشخیص گروه بدنه اصلی با استفاده از ماشین بردار پشتیبان
In this paper a new method for the online recognition of handwritten Persian characters has been proposed which uses a set of simple features and Support Vector Machine (SVM) as a classifier. The task of preprocessing allows us to equalize feature vectors from different characters. This algorithm is implemented in two steps. In the first step, input character is classified into one of eighteen ...
متن کاملJKanji: Wavelet-Based Interactive Kanji Completion
JKanji is an interactive character completion system that provides stroke-order-independent recognition of complex hand-written glyphs such as Japanese kanji or Chinese hanzi. As the user enters each stroke, JKanji offers a menu of likely completions, generated from a robust multiscale matching algorithm augmented with a statistical language model. Drawbacks of traditional wavelet-based approac...
متن کاملSubstroke Approach to HMM-Based On-line Kanji Handwriting Recognition
A new method is proposed for on-line handwriting recognition of Kanji characters. The method employs substroke HMMs as minimum units to constitute Japanese Kanji characters and utilizes the direction of pen motion. The main motivation is to fully utilize the continuous speech recognition algorithm by relating sentence speech to Kanji character , phonemes to substrokes, and grammar to Kanji stru...
متن کامل