Speech Enhancement Using Modified MMSE-LSA and Phase Reconstruction in Voiced and Unvoiced Speech

Hairong, Jia; Weimei, Wang; Wang, Dong; Zhang, Xueying

doi:10.1142/s0218001419580023

Cited by 4 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 5 shows a sample input image containing a traffic sign and the images reconstructed from the magnitude and phase of its discrete cosine transform. It can be seen that the phase reconstructed image [46] contains more visual information compared to magnitude reconstructed image. This renders the DCT transformed phase image more suitable for the purpose of extracting invariant features [42].…”

Section: Multiscale Spectral Feature Extractionmentioning

confidence: 99%

Cognition based Recognition of Partially Occluded Traffic Signs

et al. 2022

View full text Add to dashboard Cite

Computer vision based traffic sign detection and recognition is an active field of research but the task becomes challenging when the sign of interest is partially occluded by nearby objects like a tree, pole or vehicle. Another difficulty posed especially in the developing countries is the lost colors problem that arises due to aging and poor maintenance. This work presents an automatic technique that focuses on visible parts only and suppresses occluded portions. Features are collected using a convolutional neural network inspired invariant feature extraction technique augmented with feature interaction based dimensionality reduction. Further, with the use of dynamic parameter estimation, an adaptive system for continuous learning is also proposed. Since the effect of partial occlusion has not been thoroughly studied, there is no benchmark database available for this purpose. We have prepared two datasets by combining originally and synthetically occluded images taken from field surveys and from famous GTSRB database. Experiments revealed that our technique outperforms state of the art recognition methods previously used for visible and occluded signs by obtaining 0.81 precision and 0.79 recall values on the average. The proposed method also shows a remarkably low error rate as the amount of occlusion is increased.

show abstract

Section: Multiscale Spectral Feature Extractionmentioning

confidence: 99%