Raghunath S. Holambe

TL;DR: A new pattern recognition framework for face recognition based on the combination of Radon and wavelet transforms, which is invariant to variations in facial expression, and illumination, and robust to zero mean white noise is presented.

TL;DR: The proposed approach (THFB+ k-out-of-n.A) is capable of handling various artifacts, particularly segmentation error, eyelid/eyelashes occlusion, shadow of eyelids, head-tilt, and specular reflections during iris verification, and shows the superiority with some of the existing popular iris-recognition algorithms.

TL;DR: New feature extraction methods, which utilize wavelet decomposition and reduced order linear predictive coding (LPC) coefficients, have been proposed for speech recognition and the experimental results show the superiority of the proposed techniques over the conventional methods like linear predictive cepstral coefficients, Mel-frequency cep stral coefficient, spectral subtraction, and cepStral mean normalization in presence of additive white Gaussian noise.

TL;DR: This paper presents a new feature extraction technique for speaker recognition using Radon transform (RT) and discrete cosine transform (DCT) and highlights the superiority of the proposed method over some of the existing algorithms.

TL;DR: A pattern recognition framework for face recognition based on the combination of Radon and discrete cosine transforms (DCT) and the experimental results show the superiority of the proposed method compared to some of the existing algorithms.