Keratoconus is a progressive eye disease that may lead to significant loss of visual acuity. Corneal cross-linking (CXL) is a surgical procedure that halts the progression of keratoconus. One commonly used clinical indicator of CXL success, albeit being an indirect one, is the presence and depth of stromal demarcation line. In addition, corneal haze beyond the demarcation line can be an ominous sign of loss of corneal transparency, which is a much dreaded side effect of CXL. To date, ophthalmologists evaluate the presence and depth of the demarcation line and grade corneal haze using slit lamp biomicroscopy and/or optical coherence tomography (OCT). Interpreting the output of the former is very biased at best, while analyzing the information presented by the latter is time consuming, potentially error prone, and observer dependent. In this paper, we propose the first method that employs image analysis and machine learning to automatically detect and measure corneal haze and demarcation line presence and depth in OCT images. The automated method provides the user with haze statistics as well as visual annotation, reflecting the shape and location of the haze and demarcation line in the cornea. Our experimental results demonstrate the efficacy and effectiveness of the proposed techniques vis-a-vis manual measurements in a much faster, repeatable, and reproducible manner.