Ph.D. Tezi Görüntüleme

      Shoe marks are regarded as remarkable clues which can be usually detected in crime scenes where forensic experts use them for investigating crimes and identifying the criminals. Hence, developing a robust method for matching shoeprints with one another is of critical significance which can be used for recognizing criminals. In this thesis, promising methods are proposed for retrieving shoe marks and shoeprint by means of developing blocking sparse representation technique and Modified Multi-Block Local Binary Pattern method. The performance of the proposed methods were evaluated via the four methods. Accurate detection score was obtained in terms of the ratio of the number of accurately detected images to the total test images. The results of simulations indicated that the proposed methods were highly effective and efficient in retrieving shoe marks, whole shoeprints, partial toe and heel shoeprints. Furthermore, it was found that the proposed methods had better performance than the other methods with which it was compared. Accurate identification rate according to cumulative match score for the first n matches was measured. Also, the proposed methods were compared with the other methods in terms of rotation and scale distortions. The results indicated that the proposed methods were resistant to these distortions.