Adaptive threshold based fuzzy directional filter design using background information

• In this paper fuzzy logic based novel noise detection and removal technique has been presented.
• Adaptively computes the fuzzy membership functions for noise detection and restoration purposes.
• Noisy pixel's background information is used by the technique for accurate analysis.
• Based on quantitative measures, proposed technique outperforms the existing methods.

A novel adaptive fuzzy directional median filter is proposed in this paper which considers the directional pixels (horizontal, vertical and two diagonal directions) for estimation of adaptive threshold and incorporates the remaining background pixels based on directional statistics for efficient noise detection. The proposed filter consists of two phases: adaptive fuzzy noise detection phase followed by fuzzy filtering phase. In fuzzy noise detection phase, intensity differences from the central pixel in a 5 × 5 sliding window are calculated in four main directions, i.e., horizontal, vertical and two diagonal directions. Average value and central pixel value of 5 × 5 sliding window of newly constructed intensity differences image are exploited with fuzzy membership function to adaptively estimate threshold parameters. These parameters are then merged with fuzzy rules to detect the noise especially in detailed regions of an image. In filtering phase, simple median filter and directional median filters are smartly used based on edge and background information to restore the noisy pixels detected as noisy in adaptive fuzzy noise detection process. Experimental results based on well known quantitative measures shows the effectiveness of the proposed technique.

Figure optionsDownload as PowerPoint slide