The traditional diagnostics of print quality requires to print a professionally designed test-page and visually evaluated by an expert, which is very costly and time-consuming. Instead, a system that could automatically diagnose a customer's printer without any human's interference is proposed in this paper. The system relies on scanning user's printed output from user's printer. Print defects such as banding, streaking, etc. will be reflected on its scanned page and can be captured by comparing to its master image. The master image is the digitally generated original from which the page is printed. Once the print quality drops below a specified acceptance criteria level, the system can notify the user of the presence of print quality issues.. The current process has only concentrated on one type of print defect: text fading. The scanned page will initially be aligned with its master image with a feature based image registration algorithm. Text regions of the two pages are then extracted and compared directly.