Infrared Image Segmentation by Combining Fractal Geometry with Wavelet Transformation

An infrared image is decomposed into three levels by discrete stationary wavelet transform (DSWT). The noise is reduced by Wiener filter in high resolution levels in the DSWT domain. Nonlinear gray transformation operation is used to enhance the details in the low resolution levels in the DSWT domain. The enhanced infrared image is obtained by inverse DSWT and is divided into many small blocks. The fractal dimensions of all the blocks are computed. The region of interest (ROI) is extracted by combining all the blocks, which have similar fractal dimensions. The ROI is segmented by global threshold method. The man-made objects are efficiently separated from the infrared image by the proposed method.