Books by Ravindra Hegadi
Automatic document processing plays a crucial role in the present society, due to the progressive... more Automatic document processing plays a crucial role in the present society, due to the progressive move towards the concept of “Paperless Office”. Multilingual document processing is one of the important steps of automatic document processing which leads to the paperless office automation. This book will explore methodologies for multilingual document analysis systems with particular focus on Script and language identification. The scope of script and language identification is defined to include number of algorithms that are capable of identifying more than one script/language in the same document at text block, text line and word level.
Papers by Ravindra Hegadi
Lecture Notes in Electrical Engineering, 2013
In pattern recognition, identifying Kannada handwritten numerals are a complex knot. This paper p... more In pattern recognition, identifying Kannada handwritten numerals are a complex knot. This paper portrays an avenue that pikes us to attain a most potent Kannada Numerals recognition process. In this, handwritten Kannada characters are captivated in document fashion and are subjected to Pre-processing and attribute extraction processes. Pre-processing entails steps like noise removal, binarization, normalization, skew amendment, and thinning. Features are extricated by exploiting strategies like Drift Length Count, Direction related progression code, DWT and Curvelet Transfiguration Wrapping. For an impressive classification process deep convolution neural network classifier is preferred. Isolation accuracy of Kannada numeral aimed here will outsource 96% of accuracy. Keywords Pre-processing Á Binarization Á Normalization Á Discrete wavelet transform (DWT) Á Curvelet transform wrapping Á DCNN and handwritten Kannada numeral (HKN)
In this paper, our task is to design and train a high efficient, accuracy Back Propagate Neural N... more In this paper, our task is to design and train a high efficient, accuracy Back Propagate Neural Network, in order to recognize the Kannada handwritten numbers from 0 to 9. Before we pass the data to the BP Neural Network, we have to use image processing to achieve the good accuracy. There are two major components constituting the module, image preprocessing and recognition. The preprocessing component consists of noise removal, binarization, skew detection, segmentation ect based on the type of the image. Here back-propagation networks to hand-written Kannada numeral recognition. Architecture of the network is extremely forced and specifically designed for recognition of hand written Kannada numeral recognition task. The input to the network consists of normalized binary images of isolated numerals. The method has achieved accuracy of 95%.
Proceedings of the International Conference & Workshop on Emerging Trends in Technology - ICWET '11, 2011
International Journal of Computer Applications, 2012
Department of Computer Science, Jun 10, 2020
Solapur University, Solapur, 2012
International Journal of Computer …, 2011
In the present information age, with the invent of new packages and programming languages, there ... more In the present information age, with the invent of new packages and programming languages, there is need of migrating the data from one platform to another as versions are changing, to perform quality assurance of any migrated data is tedious task which require more work force, time and quality checks. To perform efficient data migration process, legacy data should be mapped to new system by considering extraction and loading entities. The new system should handle all the data formats, the good design of data migration process should take minimal time for extraction and more time for loading. Post loading into new system results in verification and validation of data accurately, by comparing with the benchmark values and derive accuracy of data migration process. The manual data validation and verification process is time consuming and not accurate so automated data validation improve data quality in less time, cost and attaining good data quality, Author"s emphasis on Automation of Data migration process for quality and security across industries.
Iris recognition is one of the important authentication mechanisms; authentication needs verifica... more Iris recognition is one of the important authentication mechanisms; authentication needs verification of individuals for uniqueness hence converting iris data into barcode is an appropriate in authenticating individuals to identify uniqueness. Such converted barcode is unique for every iris image. In iris recognition, most applications capture the eye image; extract the iris features and stores into the database in digitized form. The size of the digitized form is equal to or little less than original iris image. This as leads to the drawbacks such as more usage of memory and more time required for searching and matching operations. To overcome these drawbacks we propose an approach wherein we convert extracted iris features into barcodes. This transformation of iris into barcode reduces the space for storage and the time required for searching and matching operations, which are essential features in real time applications.
Abstract. A simple multilayer feed forward neural network based classification of handwritten as ... more 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.
Zoning is one of the popular methods used for the optical character recognition of documents. ... more Zoning is one of the popular methods used for the optical character recognition of documents. In this paper the zoning approach is used for recognition of printed Kannada numerals. The input scanned document image containing printed Kannada numerals is binarized. The noise present in the document in the form of tiny dots is eliminated. The row segmentation followed by the column segmentation is performed on this document to segment out every numeral. The number of regions is obtained from this segmented numeral, which will be used as one of the feature during recognition stage. A morphological thinning algorithm is applied to thin this numeral. In the next stage the number of end points and the coordinate values of each end point are obtained. The zones in which the end points lie, and the regions that each numeral generates, are used for the recognition of the numeral. The proposed algorithm is applied on the document containing the printed Kannada numerals of different fonts generated using Nudi 4.0 software. The analysis of recognition using proposed method is also presented here.
The endoscopic images do not contain sharp edges to segment using the traditional segmentation me... more The endoscopic images do not contain sharp edges to segment using the traditional segmentation methods for obtaining edges. Therefore, the active contours or snakes using level set method with the energy minimization algorithm is adapted here to segment these images. The result obtained from the above segmentation process will be of number of segmented regions. The analysis of the segmentation results shows that the abnormal images generate more number of regions as compared to the normal images.
ABSTRACT In this paper a graph cuts based active contours (GCBAC) approach proposed by Ning Xu [1... more ABSTRACT In this paper a graph cuts based active contours (GCBAC) approach proposed by Ning Xu [15] to is applied for segmenting the tumours from the endoscopic images. This method is a combination of active contours and the optimization tool of graph cuts. It differs ...
Abstract In this paper, three methods based on watershed segmentation for detecting possible pres... more Abstract In this paper, three methods based on watershed segmentation for detecting possible presence of abnormality in the endoscopic images are presented. Each method generates number of watershed regions. Based on the number of regions generated, the ...
ABSTRACT Image segmentation techniques have been widely applied in diagnosis systems with medical... more ABSTRACT Image segmentation techniques have been widely applied in diagnosis systems with medical image support. In this paper we propose the normalized cuts method for image segmentation problem, which is based on Graph Theory. These algorithms treat an image ...
Data-driven decision support systems, such as data warehouses can serve the requirement of extrac... more Data-driven decision support systems, such as data warehouses can serve the requirement of extraction of information from more than one subject area. Data warehouses standardize the data across the organization so as to have a single view of information. Data warehouses can provide the information required by the decision makers. Developing a data warehouse for educational institute is the less focused area since educational institutes are non-profit and service oriented organizations. In present day scenario where education has been privatized and cut throat competition is prevailing, institutes needs to be more organized and need to take better decisions. Institute's enrollments are increasing as a result of increase in the number of branches and intake. Now a day, any reputed Institute's enrollments count in to thousands. In view of these factors the challenges for the management are meeting the diverse needs of students and facing increased complexity in academic processes. The complexity of these challenges requires continual improvements in operational strategies based on accurate, timely and consistent information. The cost of building a data warehouse is expensive for any educational institution as it requires data warehouse tools for building data warehouse and extracting data using data mining tools from data warehouse. The present study provides an option to build data warehouse and extract useful information using data warehousing and data mining open source tools. In this paper we have explored the need of data warehouse / business intelligence for an educational institute, the operational data of an educational institution has been used for experimentation. The study may help decision makers of educational institutes across the globe for better decisions..
In current trend, every software development, enhancement, or maintenance project includes some q... more In current trend, every software development, enhancement, or maintenance project includes some quality assurance activities. Quality assurance attempts defects prevention by concentrating on the process of producing the rather than working on the defect detection after the product is built. Regression testing means rerunning test cases from existing test suites to build confidence that software changes have no unintended side-effects. Data warehouse obtains the data from a number of operational data source systems which can be relational tables or ERP package, etc. The data from these sources are converted and loaded into data warehouse in suitable form, this process is called Extraction, Transformation and Loading (ETL). In addition to the target database, there will be another data base to store the metadata, called the metadata repository. This data base contains data about data-description of source data, target data and how the source data has been transformed into target data. In data warehouse migration or enhancement projects, data quality checking process includes ensuring all expected data is loaded, data is transformed correctly according to design specifications, comparing record counts between source data loaded to the warehouse and rejected records, validating correct processing of ETL-generated fields such as surrogate keys. The quality check process also involves validating the data types in the warehouse are as specified in the design and/or the data model. In our work, have automated regression testing for ETL activities, which will saves effort and resource while being more accurate and less prone to any issues. Author experimented around 338 Regression test cases, manual testing is taking around 800 hrs so with RTA it will take around 88 hrs which is a reduction of 84%. This paper explains the process of automating the regression suite for data quality testing in data warehouse systems.
… and Networking, 2007 …, 2007
India is a multi-lingual and multi-script country where a line of a bilingual document page may c... more India is a multi-lingual and multi-script country where a line of a bilingual document page may contain text words in regional language and numerals in English. For optical character recognition (OCR) of such a document page, it is necessary to identify different script forms before running an individual OCR of the scripts. In this paper, we examine the use of discriminating features (aspect ratio, strokes, eccentricity, etc,) as a tool for determining the script at word level in three bilingual documents representing Kannada, Tamil and Devnagari containing English numerals, based on the observation that every text has the distinct visual appearance. The k-nearest neighbour algorithm is used to classify the new word images. The proposed algorithm is tested on 2500 sample words with various font styles and sizes. The results obtained are quite encouraging
Uploads
Books by Ravindra Hegadi
Papers by Ravindra Hegadi