The paper introduces a novel feature-similarity (FSIM) index for image quality assessment (IQA), which aims to measure image quality based on the human visual system's (HVS) perception of low-level features. The FSIM index uses phase congruency (PC) and gradient magnitude (GM) as primary and secondary features, respectively. PC, a dimensionless measure of local structure significance, and GM, which captures contrast information, are complementary in characterizing image content. The FSIM index is designed for grayscale images but can be extended to color images (FSIM_C) by incorporating chrominance information. Experimental results on six benchmark databases show that FSIM and FSIM_C achieve higher consistency with subjective evaluations compared to other state-of-the-art IQA metrics, demonstrating their robustness and effectiveness.The paper introduces a novel feature-similarity (FSIM) index for image quality assessment (IQA), which aims to measure image quality based on the human visual system's (HVS) perception of low-level features. The FSIM index uses phase congruency (PC) and gradient magnitude (GM) as primary and secondary features, respectively. PC, a dimensionless measure of local structure significance, and GM, which captures contrast information, are complementary in characterizing image content. The FSIM index is designed for grayscale images but can be extended to color images (FSIM_C) by incorporating chrominance information. Experimental results on six benchmark databases show that FSIM and FSIM_C achieve higher consistency with subjective evaluations compared to other state-of-the-art IQA metrics, demonstrating their robustness and effectiveness.