The performance of an astronomical telescope lens system can be quantitatively described using spatial frequency response and contrast transfer behavior. Imperfections in lens manufacturing, alignment errors, and atmospheric turbulence contribute to degradation in the modulation transfer function (MTF), resulting in reduced image sharpness and contrast.

Astronomical telescopes rely on optical lens systems to capture high-quality images of celestial objects. However, image degradation caused by optical aberrations, noise, and defocus often limits observation accuracy. This paper presents an AI-assisted approach for evaluating the performance of optical lens systems used in astronomical telescopes. Simulated telescope images are analyzed using image quality metrics and machine learning techniques to assess sharpness, contrast, and noise characteristics. The proposed method enables objective, low-cost, and repeatable evaluation of telescope lens performance. The results demonstrate that artificial intelligence can effectively support optical system assessment for astronomical, educational, and research applications.