DSpace Collection:
http://localhost:8080/xmlui/handle/123456789/3793
2026-06-23T06:29:58ZCombining Multiple Feature Extraction and Classification Methods to Study Performance of Handwritten Sanskrit Character Recognition
http://localhost:8080/xmlui/handle/123456789/3795
Title: Combining Multiple Feature Extraction and Classification Methods to Study Performance of Handwritten Sanskrit Character Recognition
Authors: Shelke, Shraddha V; Chandwadkar, D.M.; Ugale, S. P.
Abstract: The recognition of Sanskrit handwriting has been
found to be one of the most challenging research topics. The
Sanskrit language is written using the Devanagari Script. In
this paper, we implemented novel algorithm to recognize
handwritten characters using four different feature extraction
methods, resizing the image, Canny Edge detection, Hybrid
Discrete Wavelet-Discrete Cosine Transform (DWT-DCT),
Histogram of oriented Gradients (HOG). Classification is done
by using support vector machine with cubic kenrel and neural
network with ReLU activation function. When features are
extracted by HOG, the SVM provides classification accuracy of
97.10% while the neural network provides 91.40%. SVM has
been found to provide superior classification than neural
networks for all feature extraction strategies.2023-08-18T00:00:00ZA Combined Cryptography and Error Correction System based on Enhanced AES and LDPC
http://localhost:8080/xmlui/handle/123456789/3794
Title: A Combined Cryptography and Error Correction System based on Enhanced AES and LDPC
Authors: Chothe, R.V.; Ugale, S.P.; Chandwadkar, D.M.; Shelke, S.V.
Abstract: Any military organization nowadays depend on
networks and communications. Sensitive data that is essential
to national security relies on these networks and applications.
As a result, the need to safeguard and protect this data arises.
An authenticated crypto-coding (encryption combined with
channel coding) system is developed which incorporates improved Advanced Encryption Standard for security and Low
Density Parity Check codes for error correction. Image encryption and decryption is done with AES-256 with authentication. LDPC is incorporated as one of the rounds of Encryption. The entire communication system is implemented and
simulated using MATLAB. Encryption-encoding-scramblingmodulation is performed on transmit side. The channel model
of Additive white Gaussian noise with varying values of SNRSignal to Noise ratio is used. The results of Bit error rates
(BER), no. of errors, recovered images and histograms for different SNR values are added. The parameters like correlation,
entropy and noise variance are calculated and verified. The
Enhanced encryption offers a higher security compared to
conventional AES. Hence, the modified method can be used to
safeguard sensitive information2023-08-18T00:00:00Z