Many textures such as woven fabrics and composites have a regular and repeating texture. This paper presents a new method to capture the texture information using adaptive wavelet bases. Wavelets are compact functions which can be used to generate a multiresolution analysis. Texture constraints are used to adapt the wavelets to better characterize specific textures. An adapted wavelet basis has very high sensitivity to the abrupt changes in the texture structure caused by defects. This paper demonstrates how adaptive wavelet basis can be used to locate defects in woven fabrics. © 1996 Society of Photo−Optical Instrumentation Engineers.