The primary objective of multi-sensor data fusion, which offers both quantitative and qualitative benefits, is to be able to draw inferences that may not be feasible with data from a single sensor alone. In this study, data from two sets of sensors are fused to estimate the defect profile from magnetic flux leakage (MFL) inspection data. The two sensors measure the axial and circumferential components of the MFL field. Data is fused at the signal level. The two signals are combined as the real and imaginary components of a complex valued signal. Signals from an array of sensors are arranged in contiguous rows to obtain a complex valued image. Signals from the defect regions are then processed to minimize noise and the effects of lift-off. A boundary extraction algorithm is used not only to estimate the defect size more accurately, but also to segment the defect area. A wavelet basis function neural network (WBFNN) is then employed to map the complex valued image appropriately to obtain the geometric profile of the defect. The feasibility of the approach was evaluated using the data obtained from the MFL inspection of natural gas transmission pipelines. The results obtained by fusing the axial and circumferential component appear to be better than those obtained using the axial component alone. Finally, a WBFNN based boundary extraction scheme is employed for the proposed fusion approach. The boundary based adaptive weighted average (BBAWA) offers superior performance compared to three alternative different fusion methods employing weighted average (WA), principal component analysis (PCA), and adaptive weighted average (AWA) methods.