Artifact Effect Reduction Using Power and Entropy Algorithms

作者：Wu Ming Te

来源：International Journal of Pattern Recognition and Artificial Intelligence, 2017, 31(7): 1754012.

DOI：10.1142/S021800141754012X

• Artifact effect
• power threshold
• entropy measure
• subband coding
• multi-scale subband filtering

In this paper, a method is proposed to reduce artifact effect for images. The proposed approach first decomposes an original image into four subband images. The powers of the four sub-images are calculated and compared with a power threshold accompanying entropy measure to decide that whether the sub-images are reserved or not. The pixels of the reserved sub-images are then compared with a pixel threshold accompanying different entropy measure in order to determine that the pixel is discarded or not. The experimental results of this approach in comparison with other methods are performed both subjectively and qualitatively and shown that the proposed algorithms could reconstruct the desired recovered performance subjectively and objectively.

• 出版日期2017-7