Automatic estimation of a scale resolution in forensic images. (February 2018)

• Record Type: Journal Article
• Authors: Gertsovich, I.; Nilsson, M.; Bartůněk, J.S.; Claesson, I.
• Is Part Of: Forensic science international. Volume 283(2018)
• Page Start: 58
• Page End: 71
• Publication Date: 2018-02
• Subjects: Gray level co-occurrence matrix -- Near regular texture -- Scale resolution estimation -- Shoeprint image -- Texture pattern periodicity; Medical jurisprudence -- Periodicals; Chemistry, Forensic -- Periodicals; Forensic Medicine -- Periodicals; Médecine légale -- Périodiques; Chimie légale -- Périodiques; Gerechtelijke geneeskunde; Gerechtelijke chemie; Gerechtelijke psychiatrie; Chemistry, Forensic; Medical jurisprudence; Electronic journals; Periodicals; Electronic journals; 614.1
• DOI: 10.1016/j.forsciint.2017.12.007
• Languages: English
• ISSNs: 0379-0738

Abstract

Highlights: An automatic estimation of a scale resolution in a shoeprint image is proposed. GLCM and DFT can be used to automatically estimate a scale resolution. A robust performance was achieved in poor and high quality images. Method performance is comparable to a human expert. Performance of human experts evaluated on one image varies. Abstract: This paper proposes a new method for an automatic detection of a resolution of a scale or a ruler with graduation marks in the shoeprint images. The method creates a vector of the correlations estimated from the co-occurrence matrices for every row in a shoeprint image. The scale resolution is estimated from maxima in Fourier spectrum of the correlations' vectors. The proposed method is evaluated on over 500 images taken at crime scenes and in a forensics laboratory. The experimental results indicate the possibility of applying the proposed method to automatically estimate the scale resolution in forensic images. The automatic detection of a scale resolution could be used to automatically rescale a forensic image before the printing this image in "one-to-one" scale. Furthermore, the proposed method could be used to automatically rescale images to an equal scale thus allowing to compare the images digitally.