Name
Title | ||
|---|---|---|
Learning content-specific codebooks for blind quality assessment of screen content images. |
Abstract | ||
|---|---|---|
•This paper presents a novel blind quality assessment method for screen content images (SCIs) by learning content-specific codebooks.•Based on a codebook-based feature encoding technique, this method can automatically generate effective features without depending on any prior knowledge about the functionalities of human visual system and the mechanism of SCI quality degradation.•The differences on the characteristics between the textual and pictorial regions in SCIs are fully considered with the corresponding content-specific codebooks learned in an offline manner.•In view of the characteristics of the learned content-specific codebooks, a simple percentage-based local pooling scheme is designed to reduce the information loss in feature aggregation and improve the accuracy of the algorithm. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1016/j.sigpro.2019.03.013 | Signal Processing |
Keywords | Field | DocType |
Screen content image,Image quality assessment,No-reference,Content-specific codebooks,Feature encoding | Content type,Mathematical optimization,Pattern recognition,Regression,Segmentation,Pooling,Artificial intelligence,Mathematics,Computational complexity theory,Encoding (memory),Codebook | Journal |
Volume | ISSN | Citations |
161 | 0165-1684 | 3 |
PageRank | References | Authors |
0.35 | 0 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yongqiang Bai | 1 | 28 | 2.89 |
| Mei Yu | 2 | 542 | 86.20 |
| Qiuping Jiang | 3 | 148 | 22.19 |
| Gangyi Jiang | 4 | 865 | 105.98 |
| Zhu, Z.Q. | 5 | 27 | 3.79 |