P
Parshuram M. Kamble
Researcher at University of Solapur
Publications - 9
Citations - 123
Parshuram M. Kamble is an academic researcher from University of Solapur. The author has contributed to research in topics: Feature extraction & Marathi. The author has an hindex of 4, co-authored 8 publications receiving 98 citations.
Papers
More filters
Journal ArticleDOI
Handwritten Marathi character recognition using R -HOG Feature
TL;DR: The Rectangle Histogram Oriented Gradient representation is used as the basis for extraction of features of handwritten Marathi characters and high performance is demonstrated when classified using feed-forward Artificial Neural network, classification.
Proceedings ArticleDOI
Recognition of Marathi Handwritten Numerals Using Multi-Layer Feed-Forward Neural Network
TL;DR: This work has presented a method to recognize the handwritten Marathi numerals using multilayer feed-forward neural network, and the overall recognition rate is 97%.
Proceedings ArticleDOI
Geometrical Features Extraction and KNN Based Classification of Handwritten Marathi Characters
TL;DR: The k-nearest neighbor (KNN) algorithm with five fold validation has been used for result preparation and the accuracy of proposed method is 85.88 % obtained.
Journal Article
Deep neural network for handwritten Marathi character recognition
TL;DR: It is shown that the sparse autoencoder based feature extraction method in combination with deep neural network based classifier can produce enhanced results when applied to Marathi character recognition.
Book ChapterDOI
Comparative Study of Handwritten Marathi Characters Recognition Based on KNN and SVM Classifier
TL;DR: This work proposes feature extraction from handwritten Marathi characters using connected pixel based features like area, perimeter, eccentricity, orientation and Euler number and obtained high accuracy as compared with KNN classifier.