Papers by Ganapatsing Rajput
2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT)
Procedia Computer Science
International Journal of Computer Sciences and Engineering
International Journal of Advanced Computer Science and Applications
It is well known that the classic image compression techniques such as JPEG and MPEG have serious... more It is well known that the classic image compression techniques such as JPEG and MPEG have serious limitations at high compression rate; the decompressed image gets really fuzzy or indistinguishable. To overcome problems associated with conventional methods, artificial neural networks based method can be used. Genetic algorithm is a very powerful method for solving real life problems and this has been proven by applying to number of different applications. There is lots of interest to involve the GA with ANN for various reasons at various levels. Trapping in the local minima is one of the well-known problems of gradient decent based learning in ANN. The problem can be addressed using GA algorithm. But no work has been done to evaluate the performance of both learning methods from the image compression point of view. In this paper, we investigate the performance of ANN with GA in the application of image compression for obtaining optimal set of weights. Direct method of compression has been applied with neural network to get the additive advantage for security of compressed data. The experiments reveal that the standard BP with proper parameters provide good generalize capability for compression and is much faster compared to earlier work in the literature, based on cumulative distribution function. Further, the results obtained shows that general concept about GA, it performs better over gradient decent based learning, is not applicable for image compression.
Principles and Applications for Water Management, 2013
Lecture Notes in Computer Science, 2004
In this paper, a method for detecting possible presence of abnormality in the endoscopic images o... more In this paper, a method for detecting possible presence of abnormality in the endoscopic images of lower esophagus is presented. The preprocessed endoscopic color images are segmented using color segmentation based on 3σ-intervals around mean RGB values. The zero-crossing method of edge detection is applied on the gray scale image corresponding to the segmented image. For the large contours, the Gaussian smoothing is performed for eliminating the noise in the curve. The curvature for each point of the curve is computed considering the support region of each point. The possible presence of abnormality is identified, when curvature of the contour segment between two zero crossing has the opposite curvature signs to those of such neighboring contour segments on the same edge contours. The experimental results show successful abnormality detection in the test images using this proposed method.
Lecture Notes in Computer Science, 2007
This paper describes a system for isolated Kannada handwritten numerals recognition using image f... more This paper describes a system for isolated Kannada handwritten numerals recognition using image fusion method. Several digital images corresponding to each handwritten numeral are fused to generate patterns, which are stored in 8x8 matrices, irrespective of the size of images. The numerals to be recognized are matched using nearest neighbor classifier with each pattern and the best match pattern is considered as the recognized numeral.The experimental results show accuracy of 96.2% for 500 images, representing the portion of trained data, with the system being trained for 1000 images. The recognition result of 91% was obtained for 250 test numerals other than the trained images. Further to test the performance of the proposed scheme 4-fold cross validation has been carried out yielding an accuracy of 89%.
2013 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2013
Studies in Computational Intelligence, 2012
In a country like India where more number of scripts are in use, automatic identification of prin... more In a country like India where more number of scripts are in use, automatic identification of printed and handwritten script facilitates many important applications including sorting of document images and searching online archives of document images. In this paper, a multiple feature based approach is presented to identify the script type of the collection of handwritten documents. Eight popular Indian scripts are considered here. Features are extracted using Gabor filters, Discrete Cosine Transform, and Wavelets of Daubechies family. Experiments are performed to test the recognition accuracy of the proposed system at line level for bilingual scripts and later extended to trilingual scripts. We have obtained 100% recognition accuracy for bi-scripts at line level. The classification is done using k-nearest neighbour classifier.
International Journal of Computer Applications, 2010
Numeral recognition remains one of the most important problems in pattern recognition. To the bes... more Numeral recognition remains one of the most important problems in pattern recognition. To the best of our knowledge, little work has been done in Devnagari script compared with those for non Indian scripts like Latin, Chinese and Japanese. In this paper we propose an effective method for recognition of isolated Marathi handwritten numerals written in Devnagari script. Fourier Descriptors that describe the shape of Marathi handwritten numerals are used as feature. 64 dimensional Fourier Descriptors represents the shape of numerals, invariant to rotation, scale and translation. Three different classifiers, namely, nearest neighborhood (NN), K-nearest neighborhood (KNN) and Support Vector Machine (SVM) are used independently in order to recognize test numeral. These classifiers are trained with 64 dimensional Fourier Descriptors (FD) of training samples. The proposed system is experimented with a database of 13000 samples of Marathi handwritten numerals using fivefold cross validation method for result computation. An overall recognition rate of 97.05%, 97.04%and 97.85% are obtained for NN, KNN and SVM respectively.
Lecture Notes in Electrical Engineering, 2013
ABSTRACT Diabetic retinopathy is an ocular disorder resulting in patients with long history of di... more ABSTRACT Diabetic retinopathy is an ocular disorder resulting in patients with long history of diabetes. It is a progressive disease characterized by numerous features like, microaneurysms (MA), hard exudates, soft exudates, veins bleeding, and hemorrhages. Presence of microaneurysms is the early signs of Diabetic retinopathy. In this paper, automatic detection of microaneurysms, that alternates the tedious and time-consuming manual process, is presented. Thresholding and morphological operations are used for microaneurysms detection from fundus images. In the first step, optic disk and blood vessels are eliminated to facilitate the detection of MA. Secondly, the candidate features are extracted based on their size. Experiments are performed on a set of 100 fundus images and have yielded encouraging results.
Automatic handwritten character recognition system represents the ability of a computer system to... more Automatic handwritten character recognition system represents the ability of a computer system to receive and interpret handwriting input present in the form of scanned images. In this paper, we present a novel method for automatic recognition of Devanagari and Kannada isolated handwritten numerals. Chain code and Fourier Descriptors that capture the information about the shape of the numeral are used as features. After preprocessing the numeral image, the normalized chain code and the Fourier descriptors of the contour of the numeral are extracted. These features are then fed in the Support Vector Machine (SVM) for classification. The proposed method is experimented on a database of 12690 samples of Devanagari and 5100 samples of Kannada handwritten numerals using fivefold cross validation. We have obtained recognition accuracy of 98.15% and 98.65% for Devanagari and Kannada isolated handwritten numerals, respectively.
The steady flow of blood through vessels of exponential divergence under the influence of periodi... more The steady flow of blood through vessels of exponential divergence under the influence of periodic body acceleration has been studied. Blood is considered as a Couple stress fluid. With the help of finite Hankel transform technique an exact solution is obtained. Analytical expressions for axial velocity and flow rate have been obtained. The effects of small increasing rates of vessel divergence and body acceleration on the blood flow have been discussed. The results have been compared with other existing models and discussed about its applicability to realistic problems.
In this work, we present a fovea center localization method in digital color photographs of the r... more In this work, we present a fovea center localization method in digital color photographs of the retina (color eye fundus images). The proposed method is based on prior knowledge of optic disk center and optic disk diameter. The detection of this anatomical feature is a prerequisite for the computer aided diagnosis of several retinal diseases, such as Diabetic Maculopathy. The proposed method is evaluated on 33 retinal photographs from public DRIVE data set. The experimental results demonstrate that the proposed method is able to detect the fovea center by providing encouraging results
2011 Third National Conference on Computer Vision, Pattern Recognition, Image Processing and Graphics, 2011
Every country has their own language and script. This may or may not common to other countries. T... more Every country has their own language and script. This may or may not common to other countries. To communicate with each other we need to have a common language. English is the language that is performing that role. So most of the countries (other than Roman) use bi-script documents. But for countries like India where we have a total of 12 official scripts (and 22 languages) things are more complex. So to have an OCR we need to identify the script by which the script the document is written (even the document is not itself multi-script). Postal document, pre-printed forms are good example of such documents. So identification of the script from a document may be written with any of these 13 scripts is a very challenging work. In this paper we have tried to identify scripts written by any of the 6 official languages of India. Here we have used very simple and efficient feature at component level for the same. Using Fractal-based features, component based feature and Topological features, series of classifiers were used. Overall accuracy of the proposed system is at present 89.48% on the test set without rejection.
Lecture Notes in Computer Science, 2013
This paper presents an efficient zoning based method for recognition of handwritten Kannada chara... more This paper presents an efficient zoning based method for recognition of handwritten Kannada characters using two sets of features, namely, crack codes (the line between the object pixel and background) and the density of the object pixels. A multi-level SVM is used for the classification purpose. The proposed method is implemented in two stages. In the first stage, similar shaped characters are combined into groups resulting in 22 classes instead of 49 classes, one class per character. Crack codes are used to assign the input character image to one of the groups. In the second stage, object pixel density is used to assign label to the input character image within that identified group. Experiments are performed on handwritten Kannada characters consisting of 24500 images with 500 samples for each character. Five-fold cross validation is used for result computation and average recognition rate of 91.02 % is obtained.
Computer and Communication …, 2011
... Page 3. Figure 2. Sample data sheet These handwritten documents were scanned using HP-Scanjet... more ... Page 3. Figure 2. Sample data sheet These handwritten documents were scanned using HP-Scanjet 2400 scanner at 300 dpi which usually yields a low noise and good quality document image. ... 4768/2008, pp 251-264, 2008. [16] Niranjan SK, Vijaya Kumar,Hemantha Kumar G ...
Multi-disciplinary Trends in Artificial Intelligence, 2011
In this paper, we present an efficient method for recognition of basic characters (vowels) of han... more In this paper, we present an efficient method for recognition of basic characters (vowels) of handwritten Kannada text, which is thinning free and independent of size of handwritten characters. Crack codes and Fourier descriptors are used for computing features. The ...
Uploads
Papers by Ganapatsing Rajput