Name
Abstract | ||
|---|---|---|
We propose a new method of no-reference (NR) image sharpness assessment. Our method is based on a multiscale decomposition of non-overlapping blocks, and on analyzing the statistics of Local-Mean Magnitude (LMM) maps. With the detected high-activity blocks, a set of inter-scale and inter-direction sharpness ratios are found. These sharpness ratios are closely correlated with the level of blurring, and is capable of measuring image sharpness effectively from a multiscale and a directional view. They are linearly combined using automatic estimated weighting parameters to induce an overall effective sharpness model. To enhance accuracy, a sharpness factor based on the blur effect on DCT edges and a log-energy sharpness model are also incorporated into the method. Experiments on a large number of public images have shown that our method consistently produces predictions that are highly correlated with human perceptual of image sharpness, and outperforms the current state-of-the-art algorithms. |
Year | Venue | Field |
|---|---|---|
2018 | ICME | Computer vision,Magnitude (mathematics),Weighting,Pattern recognition,Computer science,Discrete cosine transform,Reference image,Prediction algorithms,Artificial intelligence,Discrete cosine transforms |
DocType | Citations | PageRank |
Conference | 0 | 0.34 |
References | Authors | |
0 | 5 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Zheng Zhang | 1 | 2 | 2.06 |
| Yu Liu | 2 | 7 | 4.48 |
| Hanlin Tan | 3 | 15 | 3.00 |
| Xiaoqing Yi | 4 | 0 | 0.34 |
| Maojun Zhang | 5 | 314 | 48.74 |