The subject of this dissertation is the development of three-dimensional (3D) surface profilers for semiconductor back-end inspection. The value of this study is: 1) to provide a new phase-to-height relationship for Fourier Transform Profilometry (FTP) that is universal as it allows alternate FTP system architectures for a micrometer scale object measurement, and 2) to provide a new method for full field substrate warpage and ball grid array (BGA) coplanarity inspection using machine vision. The desire to increase electronic device performance has resulted in denser and smaller IC packaging. As the dimensions of the devices decrease, the requirements for substrate flatness and surface quality become critical in avoiding device failure. For a high yield production, there is an increasing demand in the requirement for the dimensional verification of height, which requires 3D inspection. Based on the current demands from the semiconductor industry, this dissertation addresses the development of fast in-line surface profilers for large volume IC package inspection. Specifically, this dissertation studies two noncontact surface profilers. The first profiler is based on FTP for measuring the IC package front surface, the silicon die and the epoxy underfill profile. The second profiler is based on stereovision and it is intended for inspecting the BGA coplanarity and the substrate warpage. A geometrical shape based matching algorithm is also developed for finding point correspondences between IC package images. The FTP profiler provides a 1 σRMS error of about 4 μm for an IC package sample in an area of 14 mm x 6.5 mm with a 0.13 second data acquisition time. For evaluating the performance of the stereovision system, the linearity between our system and a confocal microscope is studied by measuring a particular IC sample with an area of 38 mm x 28.5 mm. The correlation coefficient is 0.965 and the 2σdifference in the two methods is 26.9 μm for the warpage measurement. For BGA coplanarity inspection the correlation coefficient is 0.952 and the 2difference is 31.2 μm. Data acquisition takes about 0.2 seconds for full field measurements.