Shoeprints are often recovered at crime scenes and are the most abundant form of evidence at a crime scene, and in some cases, it is proved to be as accurate as fingerprints. The basis for shoeprint impression evidence is determining the source of a shoeprint impression recovered from a crime scene. This shoeprint evidence collected are often noisy and unclear. To obtain a clear image, the shoeprint evidence should be enhanced by de-noising and improving the quality of the picture.

In the thesis, we introduced a novel shoeprint enhancement algorithm based on sparse representation for obtaining the complete dictionary from a set of shoeprint patches which allows us to represent them as a sparse linear combination of dictionary atoms. In the proposed algorithm, we first pre-process the image by SMQT method, and then Daubechies first level DWT is applied. The SVD of the image is computed, and Inverse Discrete Wavelet Transform(IDWT) is applied. To the singular value decomposed image, l₁-norm minimization sparse representation employed by the K-SVD algorithm is computed where the image is divided into predefined shoeprint image patches of size 8 by 8. Shoeprint images of three different databases with different image quality are tested.

The performance of the algorithm is assessed by comparing the original shoeprint image and the image obtained after proposed algorithm based on objective and subjective parameters like PSNR, MSE, and MOS. The results show the proposed method gives better performance in terms of contrast (Variance) and brightness (Mean). Finally, as a conclusion, we state that the proposed algorithm enhances the image better than the existing method DWT-SVD.