This study aims to explore the application of Siamese Neural Networks (SNN) in Full-Reference Image Quality Assessment (FR-IQA). The goal is to develop an efficient and accurate model to predict perceived image quality and correlate it with human scores. While deep learning has gained popularity in FR-IQA, the potential of Siamese Neural Networks still needs to be explored. The research addresses the challenges associated with capturing complex and nonlinear distortions and accurately assessing perceptual image quality in line with human judgment. The proposed method represents a significant advancement in image quality assessment (IQA) by harnessing the capabilities of SNNs. It introduces an approach to accurately measuring and evaluating image quality with the publicly available KADID-10k dataset. The FR-IQA model proposed in this research has undergone thorough evaluation and comparison with existing techniques. This evaluation provides valuable insights into the strengths and weaknesses of different approaches, ultimately highlighting the effectiveness of the SNN-based model. We achieved a Pearson Linear Correlation Coefficient (PLCC) of 0.781, surpassing the Structural Similarity Index Measure (SSIM) with a PLCC of 0.671. Furthermore, the Spearman Rank Order Correlation Coefficient (SROCC) and Kendall Rank Order Correlation Coefficient (KROCC) of our proposed model exhibit higher values of 0.823 and 0.804, respectively, compared to other image quality metrics. The study showcases the versatility and capacity to enhance the SNN-based model through fine-tuning. The drawbacks of the suggested model have been addressed, and potential strategies to overcome these limitations and achieve superior performance have been highlighted.