http://localhost:8080/xmlui/handle/123456789/2372 Tue, 23 Jun 2026 06:27:58 GMT 2026-06-23T06:27:58Z http://localhost:8080/xmlui/handle/123456789/3556 Title: De-noising SAR image using filtering techniques Authors: Taras, Surekha H.; Jadhav, Vaidahee U.; Kale, Rohini B.; Kokate, Supriya S. Abstract: In image processing, noise reduction and restoration of image is expected to improve the quality of image. Noise can occur during image capture, transmission etc. In general the result of the noise removal have a strong influence on the quality of the image processing technique. In noise reduction several linear, non-linear filtering method have been proposed. In this paper we present result for different filtering technique used to remove the noise. Filters are best for removing noise from the image. Tue, 15 Apr 2014 00:00:00 GMT http://localhost:8080/xmlui/handle/123456789/3556 2014-04-15T00:00:00Z http://localhost:8080/xmlui/handle/123456789/3544 Title: An Approach to Handle Dynamic Graph Partitioning Authors: Jagdale, Rupali J.; Kamalapur, S. M. Abstract: Large Dynamic Graphs are the big data structures. Now days it is important to study the dynamic graphs as there are different graphs are prepared like facebook, twitter, network analysis. Large Dynamic graphs are difficult to analyze. More memory is required to load this kind of graphs. Large graphs consist of complex data structure. To view these graphs in understandable form one has to make the partitions of the graph. Making partition will create overlapping sub graphs. Overlapping sub graphs will contain repeating nodes or some common nodes. These partitions can easily be analyzed and used for further processing. Dynamic graph always gets the addition or deletion of the contents like edge insertion or deletion and node insertion and deletion. There are updations which can be reflected in the sub graphs. The proposed system works on the same kind of graphs where large graph is partitioned into sub graphs. Thu, 15 Oct 2015 00:00:00 GMT http://localhost:8080/xmlui/handle/123456789/3544 2015-10-15T00:00:00Z http://localhost:8080/xmlui/handle/123456789/3543 Title: A Study to Handle Dynamic Graph Partitioning Authors: Jagdale, Rupali; Kamalapur, S. M. Abstract: Large dynamic graphs are popular and are used in areas like social sites, bio-informatics etc. Huge memory is required to load large graph. Therefore partitioning of large graphs is important in graph analysis. Dynamic updating of the graph can be done with different sub graphs of a large dynamic graph. Different methods of partitioning worked on static graphs. New methods of partitioning can be achieved through combinations of available methods. The proposed work will analyze the large dynamic graph by partitioning it. Also the system will update graph when multiple nodes and edges will be inserted or deleted at runtime. Certain works also focus on generating overlapped nodes in sub graphs. A method to represent large graph in abstract view is also be proposed. Sun, 12 Oct 2014 00:00:00 GMT http://localhost:8080/xmlui/handle/123456789/3543 2014-10-12T00:00:00Z http://localhost:8080/xmlui/handle/123456789/3535 Title: Neural Network based Classification of Pollen Grains Authors: Dhawale, V. R.; Tidke, J. A.; Dudul, S. V. Abstract: Palynological data are used in a wide range of applications. A new classification algorithm is proposed for pollen grains. With a view to extract features from pollen images, an classifier algorithm is developed which proposes two-dimensional discrete Walsh-Hadamard Transform domain coefficients in addition to image statistics and shape descriptor. The suitability of classifiers based on Multilayer Perceptron (MLP) Neural Network, Generalized Feedforward (GFF) Neural Network, Support Vector Machine (SVM), Radial Basis Functions (RBF) Neural Networks, Recurrent Neural Networks (RNN) and Modular Neural Network (MNN) is explored with the optimization of their respective parameters in view of reduction in time as well as space complexity. Performance of all six classifiers has been compared with respect to MSE, NMSE, and Classification accuracy. The Average Classification Accuracy of MNN comprising of two hidden layers and four parallel MLP neural networks organized in a typical topology is found to be superior (85 % on Cross Validation dataset) amongst all classifiers. Finally, optimal classifier algorithm has been developed on the basis of the best performance. The algorithm suggested could be easily modified to classify more than 10 species. The classifier algorithm will provide an effective alternative to traditional method of pollen image analysis for plant taxonomy and species identification. Sat, 01 Jun 2013 00:00:00 GMT http://localhost:8080/xmlui/handle/123456789/3535 2013-06-01T00:00:00Z