This paper presents a fast and stable imaging scheme using the localized nonlinear (LN) approximation of integral equation (IE) solutions for inverting electromagnetic data obtained in a crosswell survey. The medium is assumed to be cylindrically symmetric about a source borehole and to maintain the symmetry a vertical magnetic dipole is used as a source. To find an optimum balance between data fitting and smoothness constraint, we introduce an automatic selection scheme of Lagrange multiplier, which is sought at each iteration with a least misfit criterion. In this selection scheme, the IE algorithm is quite attractive in speed because Green's functions, a most time-consuming part in IE methods, are repeatedly reusable throughout the inversion process. The inversion scheme using the LN approximation has been tested to show its stability and efficiency using both synthetic and field data. The inverted image derived from the field data, collected in a pilot experiment of water flood monitoring in an oil field, is successfully compared with that of a 2.5-dimensional inversion scheme..