Flexible micro-endoscopes produce images having a `honeycomb' pattern (`noise' component) due to the spaces between the individual optical collection fibers of the imaging conduit. Upon Fourier analysis, this pattern was found to exhibit a definable spatial frequency discrete from that of the actual image of interest. A simple band-reject frequency filter was defined to allow removal of this `noise' component of the image. By applying the filter and by sharpening the contrast between adjacent pixels, it was possible to remove the honeycomb pattern without significant degradation to the quality of the image. The advantages and limitations of the image processing technique are discussed in light of implementing this image processing technique for real-time elimination of this objectionable honeycomb pattern emanating from endoscopes made with fiber optic conduit.