Recent train accidents, with associated direct and indirect costs as well as safety concerns, have reaffirmed the need for developing rail defect detection systems that are more effective than those used today. One of the recent developments in rail inspection is the use of ultrasonic guided waves and noncontact probing techniques to target transverse-type defects. Besides the obvious advantages of noncontact probing, which include robustness and potential for large inspection speed, such a system can detect transverse defects under horizontal shelling or head checks. A rail inspection prototype based on these concepts and funded by the FRA is under development at the University of California-San Diego. This work reports on the status of the prototype development, including hardware and software development. Key features of the software are the feature extraction and the automatic pattern recognition algorithms. The laboratory results demonstrate the detection and sizing of transverse, surface-breaking cracks that extend for less than 20% of the rail head cross-sectional area.