In this paper, an off-line recognition system based on multifeature and multilevel classification is presented for handwritten Chinese characters. Ten classes of multifeatures, such as peripheral shape features, stroke density features, and stroke direction features, are used in this system. The multilevel classification scheme consists of a group classifier and a five-level character classifier, where two new technologies, overlap clustering and Gaussian distribution selector are developed. Experiments have been conducted to recognize 5,401 daily-used Chinese characters. The recognition rate is about 90 percent for a unique candidate, and 98 percent for multichoice with 10 candidates.

Offline Recognition of Chinese Handwriting by Multifeature and Mulitilevel Classification

https://hal.archives-ouvertes.fr/hal-00933509/document

HBF49 feature set: A first unified baseline for online symbol recognition

A collection of different scripts is employed in writing languages throughout the world. Character and numeral recognition of a particular script is a key area in the field of pattern recognition. In this paper, we have presented a comprehensive survey on character and numeral recognition of non-Indic and Indic scripts. Many researchers have done work on character and numeral recognition from the most recent couple of years. In perspective of this, few strategies for character/numeral have been developed so far. There are an immense number of frameworks available for printed and handwritten character recognition for non-Indic scripts. But, only a limited number of systems are offered for character/numeral recognition of Indic scripts. However, few endeavors have been made on the recognition of Bangla, Devanagari, Gurmukhi, Kannada, Oriya and Tamil scripts. In this paper, we have additionally examined major challenges/issues for character/numeral recognition. The efforts in two directions (non-Indic and Indic scripts) are reflected in this paper. When compared with non-Indic scripts, the research on character recognition of Indic scripts has not achieved that perfection yet. The techniques used for recognition of non-Indic scripts may be used for recognition of Indic scripts (printed/handwritten text) and vice versa to improve the recognition rates. It is also noticed that the research in this field is quietly thin and still more research is to be done, particularly in the case of handwritten Indic scripts documents.

Character and numeral recognition for non-Indic and Indic scripts: a survey

This paper presents a system to recognize online handwritten Gurmukhi words. We have proposed a new step as rearrangement of recognized strokes in online handwriting recognition procedure. The rearrangement of recognized strokes includes: strokes identification as dependent and major dependent strokes; the rearrangement of strokes with respect to their positions; the combination of strokes to recognize character. We have achieved an overall recognition rate as 81.02% in online handwritten cursive handwriting for a set of 2576 Gurmukhi dictionary words.

http://www.cvc.uab.es/icdar2009/papers/3725b241.pdf

Rearrangement of Recognized Strokes in Online Handwritten Gurmukhi Words Recognition

The peculiar nature in which one or more consonants combine with vowels to produce a compound character in Kannada language results in a huge number of character combinations, running to tens of thousands or more. The aim of the work is therefore, to reduce the number of character combinations by employing a divide and conquer technique. In the first level of the technique, the structural and the dynamic features of online handwritten Kannada characters are exploited to segment the compound Kannada characters into 282 distinct symbols. This reduction in the number of classes overcomes the huge data collection problem and also reduces the computational complexity. In the second level, these 282 symbols are further divided into three distinct sets of stroke groups, thus further reducing the search space for the recognition engine. One or more of these stroke groups can combine to form any of the thousands of Kannada compound characters. Since the focus of this paper is the above strategy, a simple classifier has been used to validate the effectiveness of the proposed scheme in handling the difficult task of recognizing all possible character combinations of Kannada. The features extracted from the segmented stroke groups are mapped to lower dimensional space using PCA. The subspace features of distinct stroke groups are fed to the respective classifiers in an order and the output of these classifiers are combined to output the Unicode of the recognized akshara. The proposed work is an attempt made for the first time in Kannada language which considers all possible combinations of symbols, including Kannada numerals.

Divide and conquer technique in online handwritten Kannada character recognition

This paper describes character based elastic matching using local features for recognizing online handwritten data. Dynamic time warping (DTW) has been used with four different feature sets: x-y features, shape context (SC) and tangent angle (TA) features, generalized shape context feature (GSC) and the fourth set containing x-y, normalized first and second derivatives and curvature features. Nearest neighborhood classifier with DTW distance was used as the classifier. In comparison, the SC and TA feature set was found to be the slowest and the fourth set was best among all in the recognition rate. The results have been compiled for the online handwritten Tamil and Telugu data. On Telugu data we obtained an accuracy of 90.6% with a speed of 0.166 symbols/sec. To increase the speed we have proposed a 2-stage recognition scheme using which we obtained accuracy of 89.77% but with a speed of 3.977 symbols/sec.

http://www.hpl.hp.com/techreports/2007/HPL-2007-104.pdf

Elastic Matching of Online Handwritten Tamil and Telugu Scripts Using Local Features

Feature extraction is a very important step in the process of character recognition. The features extracted from the character should encode the local, global and the structural characteristics of the character shape. In this paper we propose a new feature for recognition of online handwritten characters called the star feature. The star feature encodes the local, global and structural characteristics of a character. The star feature describes every point of the character, in terms of its relative position with respect to the other points in the character. We have evaluated the performance of the star feature on IRONOFF data set and IWFHR-06 Tamil competition data set. The experimental results show that the star feature achieves high accuracy on both the data sets.

http://www.hpl.hp.com/techreports/2007/HPL-2007-109.pdf

M. Dinesh

Papers

Elastic Matching of Online Handwritten Tamil and Telugu Scripts Using Local Features

A Feature based on Encoding the Relative Position of a Point in the Character for Online Handwritten Character Recognition