№ | Слайд | Текст |
1 |
 |
Aline Martin alinemartin@wiscedu ECE738 Project – Spring 2005 Detecting blurring artifacts in jpeg2000 compressed images using Classification |
2 |
 |
• Problem statement • Previous work • Proposed approach:classification • Results • Conclusion and future work outline 2 |
3 |
 |
Problem StatementJpeg2000 creates blurring artifacts Blurred patches in highly textured regions 3 |
4 |
 |
Previous workRajas A. Sambhare: “Detecting Artifacts and Textures in Wavelet Coded Images” ECE 783 Project – Spring 2003 Targets Source Original image Texture detection Blurring artifacts detection 4 |
5 |
 |
Previous workAlgorithm: 1 – Detect Textured Regions 2 – Segmentation: k-mean algorithm 3 – Identification of Textured Segments 4 – Identification of segments adjacent to textured Segments For each Textured Segment For each adjacent segment if |mean Source – mean adjacent segment| < 0.2 then target segment end end 5 |
6 |
 |
Previous workProposed Approach: Use Classification to automatically classify smooth regions as blurring artifacts or smooth regions Drawbacks: Heuristic Threshold Does not perform well on other images 6 |
7 |
 |
Proposed ApproachClass0: Source is a texture and Target is not a blurring artifact Class1: Source is a texture and Target is a blurring artifact Algorithm: 1 – Detect Textured Regions 2 – Segmentation: k-mean algorithm 3 – Identification of Textured Segments 4 – Identification of segments adjacent to textured Segments For each Textured Segment For each adjacent segment compute feature vector classify it as Class0 or Class1 end end 7 |
8 |
 |
Proposed ApproachOriginal Image Identification of Textured areas Segmentation Segments edges Textured Segments 8 |
9 |
 |
Proposed ApproachClassification 1- Features extraction -> 6-d Feature vector - mean Source Segment - variance Source Segment - mean Target Segment - variance Target Segment - | mean Source Segment - mean Target Segment | - | mean Source Segment - mean Target Segment | 9 |
10 |
 |
Proposed ApproachClassification 2- Training the classifier Compute m0, m1 : 6 by 1 So, S1 : 6 by 6 10 |
11 |
 |
Proposed ApproachClassification 3- Classifier x: 6-d feature vector computed from a possible Target P0(x) ~ N(m0,S0) P1(x) ~ N(m1,S1) If P1(x) > P0(x) then Class 1 If P0(x) > P1(x) then Class 0 11 |
12 |
 |
Results12 |
13 |
 |
Results13 |
14 |
 |
ResultsLimitations due to segmentation Refinement? 14 |
15 |
 |
Conclusion and Future workAn algorithm to detect blurring artifacts in jpeg2000 compressed images was developed Need to improve segmentation: Refinement? Need a better segmentation algorithm for black and white images Need to increase the images database 15 |
«Aline Martin alinemartinwisc» |
http://900igr.net/prezentacija/bez_uroka/aline-martin-alinemartinwisc-195239.html