Search

Recent research on shape retrieval render highly acute feature descriptors that are computationally intensive. Hence, a simple approach through a novel tessellated version of the Tetrakis Square tiling scheme for acute feature descriptor aiding supervised shape retrieval is contributed in this paper. The proposed descriptor labeled as Triangulated Second-Order Shape Derivative (TSOSD) performs feature characterization and abstraction by fusing hybrid geometrical concepts with image derivative operators. First, the mechanism tessellates the image into square tiles that are later organized as right-angled triangles. Secondly, the derivatives from the right-angled triangular neighbors interact locally using the trigonometric identities to produce an angle-based feature map. Finally, the feature descriptor is then formulated by local segmentation of the attained feature maps to produce the shape histogram. Experimental results on three standard benchmark databases demonstrate the effectiveness of the proposed approach, particularly rendering a consistent retrieval rate greater than 95% in comparison with the state-of-the-art methods.

EMG is the recording of electrical activity of the muscles that can be used in diagnosing muscular diseases like myopathy and neuropathy and in generating control signals for operating artificial prosthetic arms and limbs. Various forms of artifacts get introduced into the EMG during the acquisition process that limits its proper analysis and characterization. This paper proposes a novel noise suppression method for EMG signals employing orthogonal Wave Atom Transform (WAT) followed by statistical modelling of wavelet coefficients by using a Generalized Autoregressive Conditional Heteroscedasticity (GARCH) model with maximum a-posteriori (MAP) estimator for signal recovery from noisy EMG signals. The proposed algorithm was evaluated on signals taken from the standard Physionet ATM database that was manually corrupted by different levels of Additive White Gaussian Noise (AWGN) noise. The efficiency of the proposed algorithm is studied using the standard metrics namely, Signal to Noise Ratio (SNR) in dB, and Percent Root Mean Square Deviation (PRD). Results indicate that the hybrid denoising scheme was able to reduce noise from EMG signals more effectively quantified by average SNR of 22.98 dB and PRD of 0.00029, across different datasets, in comparison with the currently employed noise reduction algorithms.