In this thesis, we propose an algorithm for evaluating the quality of DCT-based compressed images, called the Psychovisually-Based Objective Image Quality Evaluator (POIQE). The POIQE evaluates the image quality using two psychovisually-based fidelity indexes:​ blockiness and similarity. Blockiness measures the patterned square artifact created as a by-product of the lossy DCT-based compression technique used by PEG and MPEG, while similarity measures the perceivable detail remaining after compression. The blockiness and similarity are combined into a single POIQE iudex used to assess quality. The POIQE model is tuned using subjective assessment results from five subjects evaluating six sets of images. Then, the capability of the model is verified by validation experiments involving four new subjects and five new sets of images.