Name
Abstract | ||
|---|---|---|
A new method to assess the presence and the strength of the blurring artifact in video frames, without using a reference ideal image, is presented. The estimation is performed first through a global and simple measure over the whole picture, then through a finer, local analysis of the sharpness of the objects borders. The subjective relevance of the scene content is accounted for in choosing the image parts where this local blurriness measurement is performed. Relevant parts are selected using an existing measurement of the saliency of each pixel as well as a simple method to detect human faces, which are a particularly attracting content for the viewer. In the so selected parts, an objective measurement of the blurriness artifact is performed, based on the presence of fine detail and on the local edge width. Then the scene activity, or clutter, is measured by counting the number of distinct picture regions. In an active scene, indeed, a blurred object is deemed to be less apparent. The combination of quantified objective blurriness with clutter yields a final index, which proved to appropriately reproduce the judgements of human observers on images of different quality, resulting from different video encodings. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1007/s11760-010-0198-0 | Signal, Image and Video Processing |
Keywords | Field | DocType |
Edge blurriness, Detail loss, Human perception, Visual attention map, Face detection, Clutter | Computer vision,Pattern recognition,Clutter,Salience (neuroscience),Image processing,Artificial intelligence,Pixel,Face detection,Local analysis,Perception,Mathematics | Journal |
Volume | Issue | ISSN |
5 | 3 | 1863-1711 |
Citations | PageRank | References |
4 | 0.44 | 19 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Francesca Dardi | 1 | 11 | 1.67 |
| Leonardo Abate | 2 | 6 | 1.48 |
| Giovanni Ramponi | 3 | 381 | 51.84 |