This paper presents rotation and size invariant English numerals recognition system with, competitive recognition rate. The novelty of this paper is the introduction of two unique methods of feature extraction namely Pixel Moment of Inertia (PMI) and Delta Distance Coding (DDC). The proposed Multiple Hidden Markov Model (MHMM) is a two tier model to neutralize the effect of two very frequent writing styles of numerals ‘4’ and ‘7’ on their recognition rates. The novelty of PMI is that it finds moment of all the pixels of a specified zone about the central pixel and not about geometrical centroid of image area. In this paper, PMI has been observed to have an upper hand over centroidal MI. DDC is a new technique of curvature coding, based on distance from a reference level and is similar to the logic behind Delta modulation scheme in Digital Communications. Thus, the current paper correlates two digital domains namely, Digital Image Processing and Digital Communications. Support Vector Machine differentiates two close output classes obtained from classification with MHMM. The overall recognition accuracy rate of 99.17% has been achieved based on MNIST database.

No abstract

This paper aims at presenting a rotation invariant feature extraction scheme to support well known result oriented recognizer HMM. Hybrid feature extraction method consists of features due to moment of inertia (FMI) and projection features. Projection features have been applied in case of digits (2 and 3) and for other numerals FMI is introduced. Any recognition system consists of two major components viz. Feature extraction method and recognizer. This paper uses Hidden Markov Model (HMM) as recognizer to recognize Off-line handwritten English numerals due to its inherent specialities and promising results in automatic speech recognition. Our data-base consists of own collected data from people of different ages and CENPARMI data. The percent recognition accuracy of self collected samples and CENPARMI samples have been found to be 91.7% and 91.2% respectively.Index Terms-Numeral recognition, HMM, features due to moment of inertia (FMI), projection features, Viter-bi algorithm, Baum-welch algorithm.

An Optical Character Recognition (OCR) consists of three bold steps namely Preprocessing, Feature extraction, Classification. Methods of Feature extraction yield feature vectors based on which the classification of a testing pattern is executed. The paper aims at proposing some  methods of feature extraction that may go a long way to recognize a Bengali numeral or character. Pixel Ex-OR Method presents a digital gating (Ex-OR) technique to extract the information in an image. Two successive elements of a row in image matrix have been Ex-ORed and the output is again Ex-ORed with the next element.  Alphabetical coding codes a binary character image by means of letters of English alphabet. Directional features find gradient information using Sobel Masks to make position of stroke clear in an image. The features have been derived in eight standard directions and then these eight feature vectors are merged into four sets of features to reduce the system complexity and hence processing time is saved considerably. These features will help develop a Bengali numeral recognition system.

Purpose of the study: This paper aims to recognition of handwritten English characters in offline mode. It develops an efficient character recognition model avoiding large variations in handwriting by using better feature extraction techniques.      Methodology: The samples of characters are preprocessed by applying a sequence of operations in succession like Thickening, Thresholding, Filtering, and Thinning. Efficient features like Gradient features and Zonal features have been extracted. Gradient features are helpful to find out stroke information in the character whereas Zonal features detail out local information in a more précised way. Hidden Markov Model is the classifier.   Main Findings: Classification has been started with only a 5-state HMM model but it is observed that as the number of states of HMM model is increased, the corresponding recognition rate is also improved. Finally, with the 36 states HMM model we have got the expected result. This produces an overall average recognition rate of 92.6%. For the letters ‘A’ and ‘W’, the recognition rate is found to be very low, because of a lot of variations in writing style of these letters. Applications of this study: HMM is a flexible tool which is capable of absorbing variations in character images. The future works will be concentrated on improvement of recognition rate of such letters by finding some demarcating features and post processing. The proposed method can be well used in Natural Language Processing, Signature verification, Face recognition like other Pattern Recognition applications.  Novelty/Originality of this study: Preprocessing uses Median filter which removes all stray marks in samples and hence avoids any possibility of false pixels. The combination of Gradient features and Zonal features leads to a recognition accuracy of 92.6% which may be used by researchers in any other domains for the purpose of classification. The application of HMM will motivate the readers to use it for better results of classification.