Sains Malaysiana 42(9)(2013): 1339–1344

Pendekatan Pengesanan Titik Sauh Secara Automatik bagi Kesan Pin Peletup Senjata Api

(Automatic Anchor Point Detection Approach for Firearms Firing Pin Impression)

Zun Liang Chuan¹, Nor Azura Md Ghani², Choong-Yeun Liong¹* & Abdul Aziz Jemain¹

¹Pusat Pengajian Sains Matematik, Fakulti Sains dan Teknologi, Universiti Kebangsaan Malaysia

43600 UKM Bangi, Selangor D.E, Malaysia

²Pusat Pengajian Statistik dan Sains Pemutusan, Fakulti Sains Komputer dan Matematik

Universiti Teknologi MARA, 40450 Shah Alam, Selangor D.E,Malaysia

Diserahkan: 22 Mei 2012 / Diterima: 10 Mac 2013

ABSTRAK

Oleh sebab kejadian jenayah bersenjata api semakin berleluasa, pengecaman senjata api yang digunakan oleh penjenayah amat diperlukan sebagai bahan bukti dalam mahkamah. Beberapa sistem pengecaman senjata api telah diutarakan sebagai pengganti kepada cara penyiasatan tradisional yang amat bergantung kepada kepakaran ahli balistik. Pemetakan rantau tumpuan (ROI) berdasarkan kedudukan titik sauh (PAP) sempadan bulatan kesan pin peletup pada tapak kelongsong peluru merupakan langkah yang amat penting dalam sistem pengecaman senjata api automatik. Walau bagaimanapun, kaedah yang digunakan dalam kajian lepas bagi mengesan (PAP) sempadan bulatan tersebut adalah sangat kompleks dan memerlukan masa pemprosesan yang panjang. Kajian ini menerokai algoritma yang efisien dan berkemampuan untuk mengesan PAP sempadan bulatan secara automatik. Algoritma yang diutarakan merupakan gabungan daripada penapis penajaman reruang, penormalan histogram, pengambangan dan penganggar kuasa dua terkecil tak berpemberat. Dua kaedah pengambangan yang terkenal telah diuji dan dibandingkan, iaitu kaedah pengambangan berasaskan pengelompokan dan kaedah berasaskan entropi. Di samping itu, penerokaan kesan saiz dan bentuk (ROI) terhadap kadar pengelasan senjata api turut dipersembahkan. Sebanyak 747 imej kesan pin peletup jenis sempadan bulatan peletup yang dihasilkan oleh lima pucuk pistol yang berlainan daripada jenis yang sama digunakan untuk menguji algoritma yang diutarakan. Kadar pengelasan imej kesan pin peletup yang memberangsangkan (> 95%) telah dicapai dengan algoritma yang dicadangkan. Kajian juga mendapati bahawa saiz dan bentuk pemetakan ROI mempunyai kesan langsung terhadap kadar pengelasan senjata api.

Kata kunci: Balistik forensik; rantau tumpuan; senjata api; titik sauh

ABSTRACT

Since the number of crimes involving firearms is becoming rampant, identification of firearms used by criminals is a crucial step in the court. Several automatic firearm identification systems have been developed to improve on the traditional investigation method which relies heavily on the expertise of the forensic ballistics experts. An important step in automatic firearm identification is partitioning of the region of interest (ROI) based on the position of the anchor point (PAP) within the circular boundary of a firing pin impression. However, in the previous studies, the methods used to determine the PAP of a circular boundary are very complex and time consuming. This study explored algorithms that are efficient and able to detect the anchor point of a circular boundary automatically. The proposed algorithms are a combination of sharpening spatial filter, histogram normalization, thresholding and an unweighted least square estimator. Two popular threshold selection methods, namely clustering-based and entropy-based threshold selection methods, have been investigated and compared. In addition, exploration on the effects of size and shape of ROI on the firearm classification accuracy rates were discussed. A total of 747 images of circular boundary firing pin impression produced by five different pistols of the same model were used to test the proposed algorithms. Encouraging classification rates of the firing pin impression images (> 95%) were achieved with the proposed algorithms. This study also found that the size and the shape of the ROI partition have a direct effect on the firearms classification rates.

Keywords: Anchor point; firearms; forensic ballistics; region of interest

RUJUKAN

Geradts, Z., Bijhold, J., Hersen, R. & Murtagh, F. 2001. Image matching algorithms for breech face marks and firing pins in a database of spent cartridge cases of firearms. Forensic Science International 119(1): 97-106.

Ghani, N.A., Liong, C-Y, & Jemain, A.A. 2009. Analysis of geometric moments as features for identification of forensic ballistics specimen. Lecture Notes in Computer Science: LNCS 5518. Berlin: Springer.

Ghani, N.A. 2010. Analisis spesimen balisitik forensik untuk pengecaman senjata api. Tesis Dr. Fal, Pusat Pengajian Sains Matematik, Universiti Kebangsaan Malaysia (tidak diterbitkan).

Ghani, N.A., Liong, C-Y. & Jemain, A.A. 2010. Analysis of geometric moments as features for firearm identification. Forensic Science International 198(1-3): 143-149.

Gupta, M.R., Jacobson, N.P. & Garcia, E.K. 2007. OCR binarization and image pre-processing for searching historical documents. Pattern Recognition 40: 389-397.

Hu, M-K. 1962. Visual pattern recognition by moment invariants. IRE Transactions on Information Theory 8(2): 179-187.

Kapur, J.N., Sahoo, P.K. & Wong, A.K.C. 1985. A new method for gray-level picture thresholding using the entropy of the histogram. Computer Vision, Graphics, and Image Processing 29: 273-285.

Leng, J. & Huang, Z. 2012. On analysis of circle moments and texture features for cartridge images recognition. Expert Systems with Applications 39: 2092-2101.

Li, D.G. 2003. Image processing for the positive identification of forensic ballistics specimens. Proceedings of the 6th International Conference on Information Fusion 2003.

Mukundan, R., Ong, S.H. & Lee, P.A. 2001. Image analysis by Tchebichef moments. IEEE Transactions on Image Processing 10(9): 1357-1364.

Otsu, N. 1979. A threshold selection method form gray-level histograms. IEEE Transactions on Systems, Man and Cybernetics SMC-9(1): 62-66.

Pan, F. & Keane, M. 1994. A new set of moment invariants for handwritten numeral recognition. Proceedings of the International Conference on Image Processing, hlm 154-158.

Pattanachai, N., Covavisaruch, N. & Sinthanayothin, C. 2012. Tooth recognition in dental radiographs via Hu’s moment invariants. Proceedings of the 9th International Conferenceon Electrical Engineering/ Electronics, Computer, Telecommunications and Information Technology, hlm. 1-4.

Radhika, K.R., Venkatesha, M.K. & Sekhar, G.N. 2011. An approach for on-line signature authentication using Zernike moments. Pattern Recognition Letters 32: 749-769.

Shih, F.Y. 2010. Image Processing and Pattern Recognition: Fundamentals and Techniques. Hoboken, New Jersey: John Wiley & Sons.

Shu, H., Zhang, H., Chen, B., Haigron, P. & Luo, L. 2010. Fast computation of Tchebichef Moments for binary and grayscale images. IEEE Transactions on Image Processing 19(12): 3171-3180.

Tang, Y., Mu, W., Zhang, Y. & Zhang, X. 2011. A fast recursive algorithm based on fuzzy 2-partition entropy approach for threshold selection. Neurocomputing 74(17): 3072-3078.

Teague, M.R. 1980. Image analysis via the general theory of moments. Journal of the Optical Society of America 70(8): 920-930.

Thomas, S.M. & Chan, Y.T. 1989. A simple approach for the estimation of circular arc center and its radius. Computer Vision, Graphics, and Image Processing 45: 362-370.

Wu, W-Y. & Yu, W-B. 2009. Subpixel detection of circular objects using geometric property. World Academy of Science, Engineering and Technology 56: 236-240.

Xin, L.P., Zhou, J. & Rong, G. 2000. A cartridge identification system for firearms authentication. Proceedings of the 5th International Conference on Signal Processing, WCCC-ICSP 2000, hlm. 1405-1408.

Zhou, J., Xin, L.P., Gao, D.S., Zhang, C.S. & Zhang, D. 2001. Automated identification for firearms authentication. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition CVPR’01, hlm 749-754.

*Pengarang untuk surat-menyurat; email: lg@ukm.my