Showing papers by "Umapada Pal published in 2006"

Recognition of off-line handwritten devnagari characters using quadratic classifier

Abstract: Recognition of handwritten characters is a challenging task because of the variability involved in the writing styles of different individuals. In this paper we propose a quadratic classifier based scheme for the recognition of off-line Devnagari handwritten characters. The features used in the classifier are obtained from the directional chain code information of the contour points of the characters. The bounding box of a character is segmented into blocks and the chain code histogram is computed in each of the blocks. Based on the chain code histogram, here we have used 64 dimensional features for recognition. These chain code features are fed to the quadratic classifier for recognition. From the proposed scheme we obtained 98.86% and 80.36% recognition accuracy on Devnagari numerals and characters, respectively. We used five-fold cross-validation technique for result computation.

Handwriting segmentation of unconstrained Oriya text

Abstract: Segmentation of handwritten text into lines, words and characters is one of the important steps in the handwritten text recognition process. In this paper we propose a water reservoir concept-based scheme for segmentation of unconstrained Oriya handwritten text into individual characters. Here, at first, the text image is segmented into lines, and the lines are then segmented into individual words. For line segmentation, the document is divided into vertical stripes. Analysing the heights of the water reservoirs obtained from different components of the document, the width of a stripe is calculated. Stripe-wise horizontal histograms are then computed and the relationship of the peak-valley points of the histograms is used for line segmentation. Based on vertical projection profiles and structural features of Oriya characters, text lines are segmented into words. For character segmentation, at first, the isolated and connected (touching) characters in a word are detected. Using structural, topological and water reservoir concept-based features, characters of the word that touch are then segmented. From experiments we have observed that the proposed “touching character” segmentation module has 96.7% accuracy for two-character touching strings.

Recognition of Handwritten Kannada Numerals

Abstract: This paper deals with a quadratic classifier based scheme for the recognition of off-line handwritten numerals of Kannada, an important Indian script. The features used in the classifier are obtained from the directional chain code information of the contour points of the characters. The bounding box of a character is segmented into blocks and the chain code histogram is computed in each of the blocks. Here we have used 64 dimensional and 100 dimensional features for a comparative study on the recognition accuracy of our proposed system. This chain code features are fed to the quadratic classifier for recognition. We tested our scheme on 2300 data samples and obtained 97.87% and 98.45% recognition accuracy using 64 dimensional and 100 dimensional features respectively, from the proposed scheme using five-fold cross-validation technique.

A Complete System for Bangla Handwritten Numeral Recognition

Abstract: This paper deals with a complete recognition system for unconstrained off-line Bangla (Bengali) handwritten numerals. To take care of variability involved in the writing style of different individuals, a robust scheme is presented here. The scheme is mainly based on new features obtained from the concept of water overflow from reservoir as well as topological and structural features of the numerals. The proposed scheme is tested on data collected from different individuals of various background and we obtained an overall recognition accuracy of about 92.8% from 12000 data.

Word-wise Hand-written Script Separation for Indian Postal automation

Abstract: In a multi-lingual multi-script country like India, a postal document may contain words of two or more scripts. For recognition of this document it is necessary to separate different scripts from the document. In this paper, an automatic scheme for word-wise identification of hand-written Roman and Oriya scripts is proposed for Indian postal automation. In the proposed scheme, at first, document skew is corrected. Next, using a piecewise projection method the document is segmented into lines and then lines into words. Finally, using different features like, water reservoir concept based features, fractal dimension based features, topological features, scripts characteristics based features etc., a Neural Network (NN) classifier is used for word-wise script identification. For experiment we consider 2500 words and overall accuracy of 97.69% is obtained from the proposed identification scheme.

Handwritten character recognition of popular south Indian scripts

Abstract: India is a multi-lingual, multi-script country. Considerably less work has been done towards handwritten character recognition of Indian languages than for other languages. In this paper we propose a quadratic classifier based scheme for the recognition of off-line handwritten characters of three popular south Indian scripts: Kannada, Telugu, and Tamil. The features used here are mainly obtained from the directional information. For feature computation, the bounding box of a character is segmented into blocks, and the directional features are computed in each block. These blocks are then down-sampled by a Gaussian filter, and the features obtained from the down-sampled blocks are fed to a modified quadratic classifier for recognition. Here, we used two sets of features. We used 64-dimensional features for high speed recognition and 400-dimensional features for high accuracy recognition. A five-fold cross validation technique was used for result computation, and we obtained 90.34%, 90.90%, and 96.73% accuracy rates from Kannada, Telugu, and Tamil characters, respectively, from 400 dimensional features.

Online Bangla Handwriting Recognition System

Abstract: Handwriting recognition is a difficult task because of the variability involved in the writing styles of different individuals. This paper presents a scheme for the online handwriting recognition of Bangla script. Online handwriting recognition refers to the problem of interpretation of handwriting input captured as a stream of pen positions using a digitizer or other pen position sensor. The sequential and dynamical information obtained from the pen movements on the writing pads are used as features in our proposed scheme. These features are then fed to the quadratic classifier for recognition. We tested our system on 2500 Bangla numeral data and 12500 Bangla character data and obtained 98.42% accuracy on numeral data and 91.13% accuracy on character data from the proposed system.

Recognition of off-line handwritten devnagari characters using quadratic classifier

Abstract: Recognition of handwritten characters is a challenging task because of the variability involved in the writing styles of different individuals. In this paper we propose a quadratic classifier based scheme for the recognition of offline Devnagari handwritten characters. The features used in the classifier are obtained from the directional chain code information of the contour points of the characters. The bounding box of a character is segmented into blocks and the chain code histogram is computed in each of the blocks. Based on the chain code histogram, here we have used 64 dimensional features for recognition. These chain code features are fed to the quadratic classifier for recognition. From the proposed scheme we obtained 98.86% and 80.36% recognition accuracy on Devnagari numerals and characters, respectively. We used fivefold cross-validation technique for result computation.

Recognition of English Multi-oriented Characters

Abstract: There are some printed artistic documents where text lines may be curved in shape. As a result, characters of a single line may be multi-oriented. To handle such artistic documents, in this paper, we present a scheme towards the recognition of multi-oriented and multi-sized English characters. The features used here are invariant to character orientation and computed based on the angular information of the border points of the characters. We used modified quadratic discriminant function (MQDF) for recognition. We tested our proposed scheme on a dataset of 18232 characters and obtained 98.34% accuracy from the system.