Current Arabic (Hindi) Hand Written Numbers Segmentaion and Recognition Advance ImageProcessing and Neural Network (original) (raw)
Related papers
Handwritten Hindi Numerals Recognition
2013
The proposed method is efficient where it is new, simple, fast, accurate so it is used in this research for recognizing Hindi numerals (0,1,2,3,4,5,6,7,8,9), that are usually used by Arabic population. The method is effective with handwritten numerals. This method is simply depends on determining number of terminal points and its positions for each digit in its different shapes, that represent the main feature for recognition. Only five features are added when there are similarity between digits (have the same number of terminals and position), the additional features was: less pixels number to recognize digit zero, intersection point position to recognize digit (2,3,6,7) that have three terminal points, image width to recognize digit one, curve number to recognize digit (2,4) that have two terminal points finally closed shape feature is added to recognize special cases of digit five and nine that have irregular shapes. Hence the proposed method is based on structural primitives such as curve, line, point type and etc. in a manner similar to that in which human beings describe characters geometrically. This work deals with noisy object by removed them from the original image to ensure that the noise pixels not merge with the original digit pixels. Encouraged recognition results are obtained for handwritten numerals samples written by different persons, different ages, different pens type, also different size, digits with rotation state are tested that gave an excellent recognition results. Some of problems with digit 9,5 are solved.
RECOGNITION OF HINDI (ARABIC) HANDWRITTEN NUMERALS
Recognition of handwritten numerals has been one of the most challenging topics in image processing. This is due to its contributions in the automation process in several applications. The aim of this study was to build a classifier that can easily recognize offline handwritten Arabic numerals to support those applications that are deal with Hindi (Arabic) numerals. A new algorithm for Hindi (Arabic) Numeral Recognition is proposed. The proposed algorithm was developed using MATLAB and tested with a large sample of handwritten numeral datasets for different writers in different ages. Pattern recognition techniques are used to identify Hindi (Arabic) handwritten numerals. After testing, high recognition rates were achieved, their ranges from 95% for some numerals and up to 99% for others. The proposed algorithm used a powerful set of features which proved to be effective in the recognition of Hindi (Arabic) numerals.
Segmentation of Arabic Handwritten Numeral Strings Based on Watershed Approach
2019
Arabic offline handwriting recognition systems are considered as one of the most challenging topics. Arabic Handwritten Numeral Strings are used to automate systems that deal with numbers such as postal code, banking account numbers and numbers on car plates. Segmentation of connected numerals is the main bottleneck in the handwritten numeral recognition system. This is in turn can increase the speed and efficiency of the recognition system. In this paper, we proposed algorithms for automatic segmentation and feature extraction of Arabic handwritten numeral strings based on Watershed approach. The algorithms have been designed and implemented to achieve the main goal of segmenting and extracting the string of numeral digits written by hand especially in a courtesy amount of bank checks. The segmentation algorithm partitions the string into multiple regions that can be associated with the properties of one or more criteria. The numeral extraction algorithm extracts the numeral string...
Off-Line Arabic (Indian) Numbers Recognition Using Expert System
—This paper proposes an effective approach to automatic recognition of printed Arabic numerals which are extracted from digital images. First, the input image is normalized and pre-processed to an acceptable form. From the preprocessed image, components of the words are segmented into individual objects representing different numbers. Second, the numerical recognition is performed using an expert system based on a set of if-else rules, where each set of rules represents the categorization of each number. Finally, rigorous experiments are carried out on 226 random Arabic numerals selected from 40 images of Iraqi car plate numbers. The proposed method attained an accuracy of 97%.
Recognition of Assamese Handwritten Numerals Using Mathematical Morphology
The aim of this paper is to describe an algorithm to recognize Assamese handwritten numerals using mathematical morphology. The digits are classified into two groups. One group contains digits which contains one or more blobs or/and stems in its structure. The other group does not contain any blobs. The number of blobs is determined with the help of morphological boundary finding method considering the property as hole. We also use the concept called `connected component' of morphology to recognize digits without blobs. Digits without blobs are extended to blobs by using connected component approach of morphology. Digits with blobs and stems need to recognize the number of stems. The present study shows that stems need not to be exactly vertical or horizontal to detect it. The proposed algorithm has been applied and tested for various handwritten digits from ISI Kolkata database. We also compare this algorithm for various printed Assamese digits. Experiment result shows that the average recognition rate that can be achieved by this algorithm is 80% for handwritten numerals and almost 100% for printed numerals. The result is obtained by using 50 handwritten samples for each digit and different printed Assamese digits.
Numeral Handwritten Hindi/Arabic Numeric Recognition Method
International Journal of Scientific and Engineering Research
Handwritten numerals recognition plays a vital role in postal automation services. The major problem in handwritten recognition is the huge variability and distortions of patterns. The aim of the current research work is to develop a heuristic based method has good recognition efficiency for recognizing numeral free handwritten objects. In this research, the introduced method for extracting features from patterns is based on (i) the percentage of strokes in both horizontal and vertical directions and (ii) some morphological operations. The proposed method gives good recognition result, the attained recognition rate is 98.15%, the number of tested samples was 4500 samples.
Handwritten Hindi Numerals Recognition System
2012
In this project, we consider the problem of recognizing handwritten numerals using Machine Learning techniques. The first step is building the database using various image processing techniques like noise removal, elastic distortion, etc. We created a dataset of more than 200,000 Hindi numerals which is used to train and test our classifiers. Two neural network algorithms were used backpropagation using gradient descent method and deep auto-encoders using the idea of Restricted Boltzmann machine. For each of the classifiers, after training the networks, their accuracy of classification was calculated and compared on the test set.
Classification of Kannada Numerals Using Multi-layer Neural Network
Abstract. A simple multilayer feed forward neural network based classification of handwritten as well as printed Kannada numerals is presented in this paper. A feed forward neural network is an artificial neural network where connections between the units do not form a directed cycle. Here four sets of Kannada numerals from 0 to 9 are used for training the network and one set is tested using the proposed algorithm. The input scanned document image containing Kannada numerals is binarized and a negative transformation is applied followed by noise elimination. Edge detection is carried out and then dilation is applied using 3 × 3 structuring element. The holes present in this image are filled. Every image is then segmented out forming 50 segmented images each containing one numeral, which is then resized. A multilayer feed forward neural network is created and this network is trained with 40 neural images. Then testing has been performed over ten numeral images. The proposed algorithm could perfectly able to classify and recognize the printed numerals with different fonts and hand written numerals.
Recognition of Marathi Handwritten Numerals Using Multi-Layer Feed-Forward Neural Network
2014 World Congress on Computing and Communication Technologies, 2014
Marathi is one of the ancient Indian languages majorly spoken in the state of Maharashtra. Marathi is one of the Devanagari script and the literals and numerals are almost similar to Hindi. Recognition of handwritten Marathi numerals is quite challenging task because people have the practice of writing these numerals in variant ways. In this work we have presented a method to recognize the handwritten Marathi numerals using multilayer feed-forward neural network. The scanned document image is preprocessed to eliminate the noise and care is taken to link the broken characters. Each numeral is segmented from the document and it is resized to 7 × 5 pixels using cubic interpolation. While resizing a technique is used to provide better representation for every pixel in segmented numeral. This resized numeral is converted into a vector with 35 values before inputting it to the neural network. We have used 100 sets containing 1000 numerals for this experimentation, of which 50 sets are used for training the network and 50 sets for the testing purpose. The overall recognition rate of the proposed method is 97%.
International Workshop on Frontiers in Handwriting Recognition, 2002
In integrated segmentation and recognition (ISR) of handwritten character strings, the underlying classifier is desired to be accurate in character classification and resistant to non-character patterns (also called garbage or outliers). This paper compares the performance of a number of statistical and neural classifiers in ISR. Each classifier has some variations depending on learning method: maximum likelihood estimation (MLE), discriminative learning (DL) under the minimum square error (MSE) or minimum classification error (MCE) criterion, or enhanced DL (EDL) with outlier samples. A heuristic pre-segmentation method is proposed to generate candidate cuts and character patterns. The methods were tested on the 5-digit Zip code images in CEDAR CDROM-1. The results show that training with outliers is crucial for neural classifiers in ISR. The best result was given by the learning quadratic discriminant function (LQDF) classifier.