The first function of the prototype system is to receive input images of broken or torn pieces photographed on a distinctive background. The system then extracts the contour of each piece and lets the user choose a segment of one of the contours as a target for matching. The system then conducts a search on the other contours, finds potential matches, and orders these candidates according to the quality of their fit with the target. Using the statistics from the second function of the prototype, the user can estimate the potential error rates of each candidate matching pair. The user can find the probabilities of a match being correct or incorrect for any specific value of matching error. Thus, it can compare matching pairs and determine which is the best evidence, even among different sizes or materials. This project used the second function in collecting statistics for different fracture-line lengths of three materials: silicon, metal coated paper, and Perspex. The total error rates (false negative plus false positive) for 1 cm matches were 0.007 for the silicon, 0.37 for the paper, and 0.4 for the Perspex. This function enables experts to present their findings to a court in a more quantitative manner. Extensive figures and tables, 6 references, and three appendixes with supplementary data
Downloads
Similar Publications
- Testing Gender-Differentiated Models of the Mechanisms Linking Polyvictimization and Youth Offending: Numbing and callousness versus dissociation and borderline traits
- Predicting Fall Parameters from Infant Skull Fractures Using Machine Learning
- An examination of commingled first tarsometatarsal and atlantoaxial joints by deviation analysis