Image blockyness reduction

4Picture Summary

Error and noise model for Broadcasting and Surveillance systems

br0

Distortions in broadcast systems [Courtesy: KBS]

br1

Full description

br2

we incorporate light weighted human vision measurement system like edge information  to measure video artifacts in real time. Then simple bucket filling approach is applied, where the particular bucket contains the maximum value also indicating the block boundaries that are passed to the report module. After computing distortion measure a proposed detection approach is used to capture the distorted frames.

Generate Distortion Metric:

br3

Detect Distorted Frames:
To compute the distortion measure value of every frame we compare the value with previous frame. If the value is within a certain threshold value then it is considers as successful undistorted frame. Otherwise it is consider as distorted frame and forwarded to next step. First we consider previous frames matrices and then compute the mean of the frames and the standard deviation of the frames.

\[ \begin{align} \text{F}r &= \sum_{n=0}^N B_{mir}(n)\\ M_i &= \frac{F_r}{n} – \frac{\sum_{n=0}^N B_{mir}(n)}{n}\\ \sigma_i &= \sqrt{\sum_{n=0}^N \{B_{mir}(n) – M_i \}^2} \end{align} \]

Here \(n\) is the number of frames we want to consider and also \(M_i\), \(\sigma_i\) are the mean and standard deviation respectively. After computing the mean and standard deviation we have to consider how much deviation we allow the frame to be considered as distorted frame. In this paper after extensive experiment on various video frames we observe that the desirable condition of a frame to be considered as distorted is:

\[(\sigma_i – \sigma_{i-1}) > \left[ \frac{(B_{mir}(n) – B_{mir}(n-1))}{2} \right]\]

 

Experimental Results

br4

References

International Conferences:

▷ Md. Mehedi Hasan, Kiok Ahn, Oksam Chae, “Measuring Blockiness of Videos using Edge Enhancement Filtering”, International conference on Signal Processing, Image Processing and Pattern Recognition, CCIS 260, pp. 10-19, 2011.

▷ Md. Mehedi Hasan, Kiok Ahn, Md. Shariful Haque, Oksam Chae , “Blocking Artifact Detection by Analyzing the Distortions of Local Properties in Images”, 14th IEEE International Conference on Computer and Information Technology, 2011.

Comments are closed.