Improved Procedure for Multi-Focus Image Quality Enhancement Using Image Fusion with Rules of Texture Energy Measures in the Hybrid Wavelet Domain

Feature extraction is a collection of the necessary detailed information from given source, which holds for further analysis. The quality fused image depends on many parameters, particularly its directional selectivity and shift-invariance. On other hand, traditional wavelet-based transforms produce ringing distortions artifacts due to poor directionality shift invariance. Dual-Tree Complex Wavelet Transforms (DTCWT) combined with Stationary Transform (SWT) as hybrid wavelet fusion algorithm overcomes deficiencies preserves invariance properties. purpose SWT decompose source into approximate sub-bands. Further, sub-bands are decomposed DTCWT. In this extraction, low-frequency components considered implement Texture Energy Measures (TEM), high-frequency absolute-maximum rule. For sub-bands, rule implemented. texture energy rules have significantly classified improved output image’s accuracy after fusion. Finally, inverse applied generate an extended image. Experimental results evaluated show that proposed approach outperforms approaches reported earlier. This paper proposes method based SWT, DTCWT, TEM address inherent defects both Parameter Adaptive-Dual Channel Pulse coupled neural network (PA-DCPCNN) Multiscale Transform-Convolutional Sparse Representation (MST-CSR).