关键词: 信息处理, 非下采样剪切波, 融合策略, 客观评价, 平移不变性

Abstract: To enhance multi-source images fusion accuracy, an adaptive fusion method based on image quality assessment parameter in nonsubsampled shearlet transform (NSST) domain is proposed. Source images are decomposed to subband images with multi-scale and multi-direction by NSST. The low frequency subband fusion rule is based on structural similarity index with spatial frequency as coefficient weights and fusion rule of coefficient absolute value with neighborhood average energy consistency selection is adopted in the high frequency subbands. Fused low and high frequency coefficients are reconstructed to image by nonsubsampled shearlet inverse transform. Some fusion experiments are done by several sets of different modality images and objective performance assessments are fulfilled to fused results. The experimental results indicate that the proposed algorithm performs better in subjective and objective assessments than a few existing multi-scale fusion techniques in the literature and obtain better fusion performance.

Key words: information processing, nonsubsampled shearlet transform, fusion rule, objective assessment, shift-invariant