Estimation of edge direction for block error concealment using hypothesis testing problem

Authors:
Seung Hwa Hyun;Sang Soo Kim;Il Kyu Eom;Yoo Shin Kim
Affiliations:
Pusan National University, Jangjeon-dong, Kumjeong-gu, Pusan, Korea;Pusan National University, Jangjeon-dong, Kumjeong-gu, Pusan, Korea;Pusan National University, Jangjeon-dong, Kumjeong-gu, Pusan, Korea;Pusan National University, Jangjeon-dong, Kumjeong-gu, Pusan, Korea
Venue:
SIP '07 Proceedings of the Ninth IASTED International Conference on Signal and Image Processing
Year:
2007

Citing 8
Cited 0

Modern mathematical statistics

Modern mathematical statistics
Iterated Denoising for Image Recovery

DCC '02 Proceedings of the Data Compression Conference
Error concealment based on directional interpolation

IEEE Transactions on Consumer Electronics
Recovery of image blocks using the method of alternating projections

IEEE Transactions on Image Processing
Information loss recovery for block-based image coding techniques-a fuzzy logic approach

IEEE Transactions on Image Processing
Transform coded image reconstruction exploiting interblock correlation

IEEE Transactions on Image Processing
DCT coefficients recovery-based error concealment technique and its application to the MPEG-2 bit stream error

IEEE Transactions on Circuits and Systems for Video Technology
Novel sequential error-concealment techniques using orientation adaptive interpolation

IEEE Transactions on Circuits and Systems for Video Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present an error concealment technique that estimates the edge directions of lost block. We propose an adaptive block pair selection algorithm to estimate the edge direction of lost block in wavelet domain. For this estimation to be made, a hypothesis-testing problem is applied to the variance of wavelet coefficients. Here, we use an F-distribution. The strong edge has large amounts of variance because of its large coefficients. Therefore, our method decides the edge directions of the lost block from hypothesis-testing problem using the variance of the wavelet coefficients of the neighbouring blocks. The proposed method outperforms the previous methods that only used a predefined set of neighbouring blocks.