Nearest neighbour classifier

In order to improve the recognition rate and accuracy of the Tifinagh OCR, this document proposes an approach to build a powerful automatic recognition system of isolated handwritten Tifinagh characters by using a combination and fusion of some features extraction methods. The Krawtchouk, Chebyshev and Gaussian Hermite moments are used as descriptors in the features extraction phase due to their invariance to translation, rotation and scaling changes. In the classification phase, the discriminative power of the neural networks, the multiclass SVM (Support Vector Machine), the nearest neighbour classifiers, and the generative nature of the Bayesian networks, are combined together in order to benefit from their complementarity. The experimental results of each single features extraction method and each single classification method are compared with our approach to show its robustness. To approve the claimed hypothesis and results, the experiments are conducted using databases of Handwritten Tifinagh Characters.

Hybrid image segmentation is proposed in this paper. The input image is firstly preprocessed in order to extract the features using Discrete Wavelet Transform (DWT) .The features are then fed to Fuzzy C-means algorithm which is unsupervised. The membership function created by Fuzzy C-means (FCM) is used as a target to be fed in neural network. Then the Back Propagation Neural network (BPN) has been trained based on targets which is obtained by (FCM) and features as input data. Combining the FCM information and neural network in unsupervised manner lead us to achieve better segmentation .The proposed algorithm is tested on various Berkeley database gray level images.

Handwritten character recognition (HCR) is an important subset within the pattern recognition area. Very little work is happening on Marathi Barakhadi characters which are formed by the combination of one of the 12 vowels and 36 consonants resulting in 432 characters. As the number of characters to be uniquely identified is very large, the proposed method aims at recognizing Marathi language Barakhadi characters by recognizing a vowel and a consonant separately. Based on the Devanagiri characters shape analysis and data set, the whole image is split into top region image with information above the header line and middle region image with information below the header line. The middle region is further processed to detect and separate the side modifiers if any, for vowel recognition. Invariant moment features are extracted from the top region and from the side modifiers and classified using quadratic classifier for recognition of vowel matra. If no vowel matra found, the image is cut by 20-30% from the bottom for detecting the presence of lower modifiers. Invariant moment features are extracted from the cut image and classified using quadratic classifier. Core consonant is divided into various zones and invariant moment features are extracted from each zone. These features are compressed using principle component analysis and classified using quadratic classifier for consonant recognition. These features will be trained and tested for both vowel and consonant recognition using quadratic classifier.

Today all kind of information is getting digitized and along with all this digitization, the huge archive of various kinds of documents is being digitized too. We know that, Optical Character Recognition is the method through which, newspapers and other paper documents convert into digital resources. But, it is a fact that this method works on texts only. As a result, if we try to process any document which contains non-textual zones, then we will get garbage texts as output. That is why; in order to digitize documents properly they should be prepossessed carefully. And while preprocessing, segmenting document in different regions according to the category properly is most important. But, the Optical Character Recognition processes available for Bangla language have no such algorithm that can categorize a newspaper/book page fully. So we worked to decompose a document into its several parts like headlines, sub headlines, columns, images etc. And if the input is skewed and rotated, t...

Classification is very important in the process of Machine Learning and Data Mining. Traditional Neural Network classifier work with many kinds of data such as items, text documents, signals, networks, but there is lack of study on Trajectory Classification based on Neural Network. In this paper, proposing a system for classification of Trajectories on Road Network using classifier Neural Network. In this paper explored classification technique used for Trajectory Classification. The best feature candidate for classifying trajectory on road network is Sequential Pattern, as it preserves order of visiting sequence of Trajectories on road network. In this paper, here proposing a model using sequential pattern and neural network for acquiring high accuracy and efficiency for Trajectory Classification.

This paper provides an approach to automatically recognize the Tifinagh characters. The proposed recognition system is based on Texture, Walsh transformation and GIST descriptors as feature extraction methods while the Bayesian Networks are used as a classifier. A comparative study between the Texture descriptor, Walsh transformation and GIST descriptor is given. The experimental results are obtained using a character database of isolated Amazigh characters. A recognition rate of 98.18 % is achieved using GIST descriptors.

Writing is one of the most essential medium to communicate with people. This is why we created character recognition systems to facilitate man-machine interaction. Most methods of character recognition existing require lot of pre-processing. Based on the idea that any form is apprehended by the human perception, we present a structural approach to recognition of Tifinagh characters (alphabet used by the Amazighe, mainly Tuareg). After using pre-processing techniques, we uses graphs representation as a model for offline recognition of printed Tifinagh characters. This representation allows extracting the basic form of an independent letter and recognizes it. The proposed approach shows its effectiveness against problems such as size and orientation resulting performance gain, also in term of its speed.

This paper proposes a structural description scheme using second order primitives, in particular circular arcs. In this framework, a distance measure between pairs of circular arcs and relations among them is introduced, and its main properties are discussed. This measure accomplishes some perceptive criteria for increasing its efficiency: it proved applicable in a wide class of application domains characterised by high variability in the shape of the visual patterns, where a structural approach is particularly useful. The description method together with the distance have been experimentally validated in the context of the recognition of handwritten digits coming from a standard character database.

Scanning baggage by x-ray and analysing such images have become important technique for detecting illicit materials in the baggage at Airports. In order to provide adequate security, a reliable and fast screening technique is needed for baggage examination.This paper aims at providing an automatic method for detecting concealed weapons, typically a gun in the baggage by employing image segmentation method to extract the objects of interest from the image followed by applying feature extraction methods namely Shape context descriptor and Zernike moments. Finally the objects are classified using fuzzy KNN as illicit or non-illicit object.

In this paper, we present an algorithm for reconstruction from incomplete 2D scans for tifinagh characters. This algorithm is based on using correlation between the lost block and its neighbors. This system proposed contains three main parts: pre-processing, features extraction and recognition. In the first step<strong>,</strong> we construct a database of tifinagh characters. In the second step, we will apply "shape analysis algorithm". In classification part, we will use Neural Network. The simulation results demonstrate that the proposed method give good results.

This paper describes an Optical Character Recognition (OCR) System for printed text documents in Malayalam, a South Indian language. Indian scripts are rich in patterns while the combinations of such patterns makes the problem even more complex and these complex patterns are exploited to arrive at the solution. The system segments the scanned document image into text lines, words and further characters and sub-characters. The segmentation algorithm proposed is motivated by the structure of the script. A novel set of features, computationally simple to extract are proposed. The approaches used here are based on the distinctive structural features of machine-printed text lines in these scripts. A lateral cross-sectional analysis is performed along each row of the normalized binary image matrix resulting in distinct features. The final recognition is achieved through classifiers based on the Support Vector Machine (SVM) method. The proposed algorithms have been tested on a variety of printed Malayalam characters and currently achieve recognition rates between 90.22% and 95.31 %.

Analysis of degraded printed documents has been a research topic for last several years. In this article the contribution lies in segmentation of word images into symbols and recognition of the symbols of degraded printed document images of Bengali, the 7th most popular language in the world. A novel approach to symbol level segmentation based on a Multilayer Perceptron (MLP) network is proposed. A database of segmenting and non-segmenting image columns is developed from the ISIDDI page level database and segmentation is treated as a two-class classification problem. The MLP weights are learnt based on this database using the back propagation algorithm. We have introduced certain new metrics, based on which the F-score of the proposed segmentation algorithm is determined. Our method utilizes information that is relevant for character segmentation, ignoring other highly variable information contained in a printed text document, thus allowing for efficient transfer learning between datasets and alleviating the need for labelled training data. Other than Bengali, we have tested on English, Tamil and Devnagari scripts. For the classification purpose we have identified 336 symbols, and the corresponding training and test sets have been developed. The ISIDDI database is used for this purpose. Two classifiers, one CNN based and the other LSTM based, have been developed for this 336-class problem. The classification accuracies obtained on the test set by the CNN classifier and the LSTM classifier are 86.05% and 88.11%, respectively. The proposed classifiers outperform the existing classifiers for the ISIDDI database.

Writing is one of the most essential medium to communicate with people. This is why we created character recognition systems to facilitate man-machine interaction. Most methods of character recognition existing require lot of pre-processing. Based on the idea that any form is apprehended by the human perception, we present a structural approach to recognition of Tifinagh characters (alphabet used by the Amazighe, mainly Tuareg). After using pre-processing techniques, we uses graphs representation as a model for offline recognition of printed Tifinagh characters. This representation allows extracting the basic form of an independent letter and recognizes it. The proposed approach shows its effectiveness against problems such as size and orientation resulting performance gain, also in term of its speed.

In this article, a printed Tifinagh character recognition system is presented. It is composed of three main steps: pre-processing, features extraction and classification. In the pre-processing step, binarization, normalization and thinning are applied to enhance the quality of the image. In the feature extraction step, corners are extracted using Harris Corner Detection method then represented by graph. In the classification step, graphs are compared using a graph matching method. Experimental results are obtained using IRCAM database to test the effectiveness. The system shows good results in terms of accuracy.

This paper provides an approach to automatically recognize the Tifinagh characters. The proposed recognition system is based on Texture, Walsh transformation and GIST descriptors as feature extraction methods while the Bayesian Networks are used as a classifier. A comparative study between the Texture descriptor, Walsh transformation and GIST descriptor is given. The experimental results are obtained using a character database of isolated Amazigh characters. A recognition rate of 98.18% is achieved using GIST descriptors.

Most of the reported works in the field of character recognition systems achieve modest results by using a single method for calculating the parameters of the character image and a single approach in the classification phase of the system. So, in order to improve the recognition rate, this document proposes an automatic system to recognize isolated printed Tifinagh characters by using a fusion of some classifiers and a combination of some features extraction methods. The Legendre moments, Zernike moments, Hu moments, Walsh transform, GIST and texture are used as descriptors in the features extraction phase due to their invariance to translation, rotation and scaling changes. In the classification phase, the neural network, the Bayesian network, the multiclass SVM (Support Vector Machine) and the nearest neighbour classifiers are combined together. The experimental results of each single features extraction method with each single classification method are compared with our approach to show its robustness. A recognition rate of 100 % is achieved by using some combined descriptors and classifiers.

Mathematical expression detection in scientific documents is a prerequisite step for developing a mathematical retrieval system that has attracted many researches recently. In the detecting process, one challenging issue is the detection of variables. The similar properties of variables and narrative text cause many errors in the detection in existing approaches. In the paper, a novel detection methodology of variables in inline mathematical expressions is proposed. The merit of the method is that it can operate directly on the variable images without the employment of character recognition. The proposed method uses the features of projection profile of images and the fine-tuning of different machine learning algorithms in the detection process. The achieved accuracy varies from 86.14% to 94% for the detection of variables in inline expressions in document images in various public benchmark datasets. The performance comparison with existing methods demonstrates the effectiveness of the proposed method.

3 A divide-and-conquer based algorithm is presented here to detect the skew angle in handwritten old age Modi document images. The skew angle detection range is estimated by determining the inclination of the document image. A new horizontal projection profile based criterion function is proposed and used here to compute the concentration of the black pixels. The criterion function is scrutinized to estimate the rotational angle range and detect the skew angle of the document image. The results prove that the proposed technique has corrected skew angle in diverse types of document images. This method accurately identifies skew angle in the clockwise or anticlockwise direction in estimated rotational angle range up to ±89 degree with angular resolution 0.1 degree. The Modi Lipi document image dataset and benchmark online datasets are used to test and compare the performance of the proposed approach.

On-line character recognition systems, usually, extract features like direction, curvature trajectory of the characters, pen-ups, velocity of the pen, etc., from the handwritten characters for recognition. Whereas, if wavelet features of characters are extracted, they represent combination of many of the conventional features and act as a simple novel candidate for character recognition. This paper reports the details of an on-line character recognition system developed by the authors, for the handwritten characters/words of Kannada, a National language of India, which employs the wavelet features of the character contour for recognition. The results obtained are most encouraging.

Analysis of degraded printed documents has been a research topic for last several years. In this article the contribution lies in segmentation of word images into symbols and recognition of the symbols of degraded printed document images of Bengali, the 7th most popular language in the world. A novel approach to symbol level segmentation based on a Multilayer Perceptron (MLP) network is proposed. A database of segmenting and non-segmenting image columns is developed from the ISIDDI page level database and segmentation is treated as a two-class classification problem. The MLP weights are learnt based on this database using the back propagation algorithm. We have introduced certain new metrics, based on which the F-score of the proposed segmentation algorithm is determined. Our method utilizes information that is relevant for character segmentation, ignoring other highly variable information contained in a printed text document, thus allowing for efficient transfer learning between datasets and alleviating the need for labelled training data. Other than Bengali, we have tested on English, Tamil and Devnagari scripts. For the classification purpose we have identified 336 symbols, and the corresponding training and test sets have been developed. The ISIDDI database is used for this purpose. Two classifiers, one CNN based and the other LSTM based, have been developed for this 336-class problem. The classification accuracies obtained on the test set by the CNN classifier and the LSTM classifier are 86.05% and 88.11%, respectively. The proposed classifiers outperform the existing classifiers for the ISIDDI database.

Most of the reported works in the field of character recognition systems achieve modest results by using a single method for calculating the parameters of the character image and a single approach in the classification phase of the system. So, in order to improve the recognition rate, this document proposes an automatic system to recognize isolated printed Tifinagh characters by using a fusion of some classifiers and a combination of some features extraction methods. The Legendre moments, Zernike moments, Hu moments, Walsh transform, GIST and texture are used as descriptors in the features extraction phase due to their invariance to translation, rotation and scaling changes. In the classification phase, the neural network, the Bayesian network, the multiclass SVM (Support Vector Machine) and the nearest neighbour classifiers are combined together. The experimental results of each single features extraction method with each single classification method are compared with our approach to show its robustness. A recognition rate of 100 % is achieved by using some combined descriptors and classifiers.

3 A divide-and-conquer based algorithm is presented here to detect the skew angle in handwritten old age Modi document images. The skew angle detection range is estimated by determining the inclination of the document image. A new horizontal projection profile based criterion function is proposed and used here to compute the concentration of the black pixels. The criterion function is scrutinized to estimate the rotational angle range and detect the skew angle of the document image. The results prove that the proposed technique has corrected skew angle in diverse types of document images. This method accurately identifies skew angle in the clockwise or anticlockwise direction in estimated rotational angle range up to ±89 degree with angular resolution 0.1 degree. The Modi Lipi document image dataset and benchmark online datasets are used to test and compare the performance of the proposed approach.

Today all kind of information is getting digitized and along with all this digitization, the huge archive of various kinds of documents is being digitized too. We know that, Optical Character Recognition is the method through which, newspapers and other paper documents convert into digital resources. But, it is a fact that this method works on texts only. As a result, if we try to process any document which contains non-textual zones, then we will get garbage texts as output. That is why; in order to digitize documents properly they should be prepossessed carefully. And while preprocessing, segmenting document in different regions according to the category properly is most important. But, the Optical Character Recognition processes available for Bangla language have no such algorithm that can categorize a newspaper/book page fully. So we worked to decompose a document into its several parts like headlines, sub headlines, columns, images etc. And if the input is skewed and rotated, t...

The subject of character recognition has received considerable attention in recent years. Character recognition is a process of converting handwritten or printed text images into machine readable code or text. Optical character recognition is used for many applications such as 1) Handwriting recognition systems, 2) Number plate recognition systems, 3) text recognition systems, 4) Data entry for business documents. In this, we are concerned with the recognition of printed Oriya script a popular Indian script. The development of OCR for this script is challenging as number of identified classes are more than 380. In the proposed approach, the digitized document image is first passed through preprocessing modules. The preprocessed data is segmented to the symbol level using horizontal and vertical projection profiling. The proposed approach use HOG feature extraction technique and SVM (Support Vector Machine) is used as a classifier. This approach is able to distinguishing between char...

The subject of character recognition has received considerable attention in recent years. Character recognition is a process of converting handwritten or printed text images into machine readable code or text. Optical character recognition is used for many applications such as 1) Handwriting recognition systems, 2) Number plate recognition systems, 3) text recognition systems, 4) Data entry for business documents. In this, we are concerned with the recognition of printed Oriya script a popular Indian script. The development of OCR for this script is challenging as number of identified classes are more than 380. In the proposed approach, the digitized document image is first passed through preprocessing modules. The preprocessed data is segmented to the symbol level using horizontal and vertical projection profiling. The proposed approach use HOG feature extraction technique and SVM (Support Vector Machine) is used as a classifier. This approach is able to distinguishing between char...

Skewing of the scanned image is an inevitable process and its detection is an important issue for document recognition systems. The skew of the scanned document image specifies the deviation of the text lines from the horizontal or vertical axis. This paper surveys methods to detect this skew in two steps, dimension reduction and skew estimation. These methods include projection profile analysis, Hough Transform, nearest neighbor clustering, cross-correlation, piece-wise painting algorithm, piece-wise covering by parallelogram, transition counts, morphology.

Intensive research has been done on optical character recognition ocr and a large number of articles have been published on this topic during the last few decades. Many commercial OCR systems are now available in the market, but most of these systems work for Roman, Chinese, Japanese and Arabic characters. There are no sufficient number of works on Indian language character recognition especially Kannada script among 12 major scripts in India. This paper presents a review of existing work on printed Kannada script and their results. The characteristics of Kannada script and Kannada Character Recognition System kcr are discussed in detail. Finally fusion at the classifier level is proposed to increase the recognition accuracy.

This paper proposes a structural description scheme using second order primitives, in particular circular arcs. In this framework, a distance measure between pairs of circular arcs and relations among them is introduced, and its main properties are discussed. This measure accomplishes some perceptive criteria for increasing its efficiency: it proved applicable in a wide class of application domains characterised by high variability in the shape of the visual patterns, where a structural approach is particularly useful. The description method together with the distance have been experimentally validated in the context of the recognition of handwritten digits coming from a standard character database.

In this paper, an algorithm is designed to recognize the handwritten Kannada vowels based on shape features such as normalized chain codes and wavelet filters. A normalized chain code and wavelet decomposition co-efficients are extracted as a feature vector of size 22 from the normalized binary images of size 40x40 and KNN classifier is applied for classification of vowels. A sample of 1400 Kannada vowels image are used for experiment. The average recognition accuracy of the proposed algorithm is 95.07% for Kannada vowels. General Terms Pattern Recognition, Document Image Analysis.

Recognition of bilingual script in an image of a document page is of primary importance for a system processing bilingual document. In this paper two essential sub stages of recognition phase, feature extraction and classification has been discussed for segmented Gurmukhi and Roman characters. Structural and Statistical features have been proposed for machine printed bilingual characters. Three classifiers such as k-nearest neighbor (KNN), artificial neural networks (ANN) and Support Vector Machines (SVM) schemes have been proposed for analyzing the error rate for recognition. It has been found that error rate is dropped when statistical features are used simultaneously with structural features. It has also been observed that SVM outperform among all the classifiers.

In the last half century, the English character recognition was studied and the results were of such type that’s it can produce technology driven applications. But the same approach cannot be used in case of Indian languages due to the nature of complication in terms of structure and computation. Now days there are different methodologies which are growing fastly in the area of Indian languages and character recognition. The offices, banks, schools and other organisations are working in the field of digital document processing. Devnagari is the national language of India and generally spoken by 600 million people in India. Devnagari should be given more special consideration for analysis and document retrieval due to its popularity. This paper is mainly concern for the people who are working in the Devnagari Optical character and it provides an overview about Devnagari character recognition system (DCR). In this paper the current status of DCR is presented and future research is also

This paper presents multi-font/multi-size Kannada numerals and vowels recognition based on spatial features. Directional spatial features viz stroke density, stroke length and the number of stokes in an image are employed as potential features to characterize the printed Kannada numerals and vowels. Based on these features 1100 numerals and 1400 vowels are classified with Multi-class Support Vector Machines (SVM). The proposed system achieves the recognition accuracy as 98.45% and 90.64% for numerals and vowels respectively.

In this chapter we analyze the performance of D-DCT algorithms for the recognition of cursive english alphabets, These are statistical methods suitable for the recognition of cursive English characters. These methods are used for feature extraction and classification of English characters. We have used Directional Discrete Cosine Transform Method as a classifier.

The Optical Character Recognition (OCR) is becoming popular areas of research under pattern recognition and smart device applications. It requires the intelligence like human brain to recognize the various handwritten characters. Artificial Neural Network (ANN) is used to gather the information required to recognize the characters adaptively. This paper presents a performance analysis of character recognition by two different methods (1) compressed Lower Dimension Feature(LDF) matrix with a perceptron network, (2) Scale Invariant Feature (SIF) matrix with a Back Propagation Neural network (BPN). A GUI based OCR system is developed using Matlab. The results are shown for the English alphabets and numeric. This is observed that the perceptron network converges faster, where as the BPN can handle the complex script recognition when the training set is enriched.

Skew angle estimation is an important component of an Optical Character Recognition ,OCR) and Document Analysis Systems (DAS). In this paper, a novel and efficient (i n terms of accuracy and computations) method to estimate skew angle of a seaMed document image is proposed. The proposed technique works based on fixing a boundary for connected components and growing boundaries. The technique uses Hough Transfonn (HT) to estimate skew angles. However, the technique works based• on the assumption that the space between the two adj acent text lines is greater than the space between the successive characters present in a text line. The proposed method is compared with other existing methods. The experimental results are also presented.

The research activity related to Optical Character Recognition (OCR) for almost all Indian languages is very less. Gujarati script is one of the scripts for which very less literature is available, as far as OCR activities are concerned. This paper describes one of the important phase of OCR, segmentation of handwritten words into its basic components namely basic characters, conjunct characters and modifiers, which are essential for recognition of a word. The paper describes methods for identification of zone boundaries for a word and usage of zone boundaries details for segmenting the word into its subcomponents. Connected component labeling is applied to detect subcomponents of a word, which can be further dissected if needed to obtain other subcomponents of word. It is the first attempt to dissect handwritten Gujarati words into its subcomponents.

Boosting and bagging are two widely used ensemble methods for classification. Their common goal is to improve the accuracy of a classifier combining single classifiers which are slightly better than random guessing. Among the family of boosting algorithms, AdaBoost (adaptive boosting) is the best known, although it is suitable only for dichotomous tasks. AdaBoost.M1 and SAMME (stagewise additive modeling using a multi-class exponential loss function) are two easy and natural extensions to the general case of two or more classes. In this paper, the adabag R package is introduced. This version implements AdaBoost.M1, SAMME and bagging algorithms with classification trees as base classifiers. Once the ensembles have been trained, they can be used to predict the class of new samples. The accuracy of these classifiers can be estimated in a separated data set or through cross validation. Moreover, the evolution of the error as the ensemble grows can be analysed and the ensemble can be pruned. In addition, the margin in the class prediction and the probability of each class for the observations can be calculated. Finally, several classic examples in classification literature are shown to illustrate the use of this package.

https://www.ijert.org/zonal-moments-based-handwritten-marathi-barakhadi-recognition

https://www.ijert.org/research/zonal-moments-based-handwritten-marathi-barakhadi-recognition-IJERTV1IS6489.pdf

Handwritten character recognition (HCR) is an important subset within the pattern recognition area. Very little work is happening on Marathi Barakhadi characters which are formed by the combination of one of the 12 vowels and 36 consonants resulting in 432 characters. As the number of characters to be uniquely identified is very large, the proposed method aims at recognizing Marathi language Barakhadi characters by recognizing a vowel and a consonant separately. Based on the Devanagiri characters shape analysis and data set, the whole image is split into top region image with information above the header line and middle region image with information below the header line. The middle region is further processed to detect and separate the side modifiers if any, for vowel recognition. Invariant moment features are extracted from the top region and from the side modifiers and classified using quadratic classifier for recognition of vowel matra. If no vowel matra found, the image is cut by 20-30% from the bottom for detecting the presence of lower modifiers. Invariant moment features are extracted from the cut image and classified using quadratic classifier. Core consonant is divided into various zones and invariant moment features are extracted from each zone. These features are compressed using principle component analysis and classified using quadratic classifier for consonant recognition. These features will be trained and tested for both vowel and consonant recognition using quadratic classifier.

Today most of people are e-reader. Gujarati documents are mostly in hardcopy; very less e-material is available. For converting those hardcopies into editable text form we need digitization. Optical Character Recognition is a technique for converting scanned documents into digitized text. So also for Gujarati language, optical character recognition system is required. For the recognition of printed characters of Indian languages like Gujarati, Marathi and many more; optical character recognition is required. Efforts of many researchers are going on for developing efficient OCR systems for Indian languages, especially for Gujarati, a popular language state Gujarat. There is very less material available for Gujarati script. Devnagari language is the base of Gujarati language. Only difference is shirorekha. Since 1999, efforts are going on for Gujarati character recognition but still that much accuracy cannot be obtained as compared to other Indic languages.

This paper presents a literature review on character recognition techniques. (OCR) Optical Character Recognition frameworks are able to identify varieties of text styles and printed characters. This means that by scanning a document the device is able to essentially " read " the content. Character identification is a requesting specialization of pattern recognition, machine learning, and advance image processing. Various work has been done as such far for independent Indian language like Hindi, Urdu, Gujarati, Punjabi and onward. The latest research in this area has been capable to grow some new methodologies to overcome the difficulty of Odia writing style. Be that as it may, narrow exploration has been done over on odia content. Thus far various techniques are projected for segmentation, feature extraction, classification, and recognition tasks of Odia characters. This paper tries to review, their relative strength and weakness unit layout done by various research worker over on Odia content in last few years. The basic objective of this paperwork is to nearby present an overview of different existing methods that have been developed to recognize Odia character throughout last decade. The paper may be a concern the individuals who are interested to work in the fields of acknowledgment of Odia script.

Today all kind of information is getting digitized and along with all this digitization, the huge archive of various kinds of documents is being digitized too. We know that, Optical Character Recognition is the method through which, newspapers and other paper documents convert into digital resources. But, it is a fact that this method works on texts only. As a result, if we try to process any document which contains non-textual zones, then we will get garbage texts as output. That is why; in order to digitize documents properly they should be pre-processed carefully. And while preprocessing, segmenting document in different regions according to the category properly is most important. But, the Optical Character Recognition processes available for Bangla language have no such algorithm that can categorize a newspaper/book page fully. So we worked to decompose a document into its several parts like headlines, sub headlines, columns, images etc. And if the input is skewed and rotated, then the input was also de-skewed and de-rotated. To decompose any Bangla document we found out the edges of the input image. Then we find out the horizontal and vertical area of every pixel where it lies in. Later on the input image was cut according to these areas. Then we pick each and every sub image and found out their height-width ratio, line height. Then according to these values the sub images were categorized. To de skew the image we found out the skew angle and de skewed the image according to this angle. To de-rotate the image we used the line height, matra line, pixel ratio of matra line.

In this paper, an improvement approach of Hough transform for tables detection and extraction from scanned document images is achieved as one of the main stages in document recognition to recognize between original and faked documents. The improvements fundamentally originate from the modulation of the standard Hough transform (SHT)parameter selection, peak threshold and voting scheme. Peakvalues formed by noise edges are thus lowered compared with those formed by clear edges. Experimental results show the proposed method leads to significant suppression of false peaks in Hough space and is thus effective. The parameters can be determined empirically in advance, which their advantage to use the proposed method in fully automated lines detection applications.

Abstract. This paper presents a robust automatic shape classifier using modular wavelet networks (MWNs). A shape descriptor is constructed based on a combination of global geometric features (modified Zernike moments and circularity features) and local intensity features (ordered histogram of image gradient orientations). The proposed method utilizes a supervised modular wavelet network to perform shape classification based on the extracted shape descriptors. Affine invariance is achieved using a novel eigen-based normalization ...

Data gravitation based classification (DGC) is a novel data classification technique based on the concept of data gravitation. The basic principle of DGC algorithm is to classify data samples by comparing the data gravitation between the different data classes. In the DGC model, a kind of ''force" called data gravitation between two data samples is computed. Data from the same class are combined as a result of gravitation. On the other hand, data gravitation between different data classes can be compared. A larger gravitation from a class means the data sample belongs to a particular class. One outstanding advantage of the DGC, in comparison with other classification algorithms is its simple classification principle with high performance. This makes the DGC algorithm much easier to be implemented. Feature selection plays an important role in classification problems and a novel feature selection algorithm is investigated based on the idea of DGC and weighted features. The proposed method is validated by using 12 well-known classification data sets from UCI machine learning repository. Experimental results illustrate that the proposed method is very efficient for data classification and feature selection.

In this paper, we implement an anomaly detection
system using the Dempster-Shafer method. Using two standard
benchmark problems we show that by combining multiple
signals it is possible to achieve better results than by using a
single signal. We further show that by applying this approach
to a real-world email dataset the algorithm works for email
worm detection. Dempster-Shafer can be a promising method
for anomaly detection problems with multiple features (data
sources), and two or more classes.

In this paper a new text extraction algorithm is proposed. In real scenes the text is usually overlapped or is part of the background. To identify the text regions, in complex conditions, a method exploiting a "multiresolution feature based method" for extracting text with undefined dimension has been developed. Once identified, the multi-resolution information are merged and skimmed through a set of Support Vector Machines (SVM). The tests and the comparisons with other techniques, performed on heterogeneous images, have shown the effectiveness of the proposed methodology.

Intensive research has been done on optical character recognition ocr and a large number of articles have been published on this topic during the last few decades. Many commercial OCR systems are now available in the market, but most of these systems work for Roman, Chinese, Japanese and Arabic characters. There are no sufficient number of works on Indian language character recognition especially Kannada script among 12 major scripts in India. This paper presents a review of existing work on printed Kannada script and their results. The characteristics of Kannada script and Kannada Character Recognition System kcr are discussed in detail. Finally fusion at the classifier level is proposed to increase the recognition accuracy.

The paper describes the K-winner machine (KWM) model for classification. KWM training uses unsupervised vector quantization and subsequent calibration to label data-space partitions. A K-winner classifier seeks the largest set of best-matching prototypes agreeing on a test pattern, and provides a local-level measure of confidence. A theoretical analysis characterizes the growth function of a K-winner classifier, and the result leads to tight bounds to generalization performance. The method proves suitable for high-dimensional multiclass problems with large amounts of data. Experimental results on both a synthetic and a real domain (NIST handwritten numerals) confirm the approach effectiveness and the consistency of the theoretical framework.