IntroductionThe first time fingerprint comparison evidence was used in court against an accused was in 1892 in Argentina [1] For forensic identification purposes in law enforcement and other cases. In areas where human identification is necessary, fingerprints have been widely recognized as being of inestimable importance and have therefore been almost unanimously accepted as the gold standard for forensic evidence in biometric identity. However, recently, as has rarely happened in the past, the scientific basis of fingerprint expert testimony in court is beginning to be called into question [2]. Some commentators are now questioning the scientific validity of forensic fingerprint identification. Reference was made to the Daubert standard which specifies the conditions of acceptability of expert testimony [1], where the scientific methods and techniques used must themselves be based on testable and refutable theories having been the subject of of a peer review process. These methods must also have known and/or predictable error rates and must conform to recognized standards relevant to their application. These Daubert Principles, as they have been known in the United States since 1993, have reached beyond U.S. jurisdiction to influence the admissibility of expert testimony internationally. The UK Law Commission recently prescribed similar standards in its consultation paper on expert evidence in which it emphasized the scientific method much more than falsifiability [3]. The ACE-V method which has been used by expert fingerprint examiners (which has been the subject of controversy) has been the subject of several objections, some of which according to [2] are: - the contextual bias which arises of...... middle of article ......= {GPy,Ry, Nty}, and the continuous feature vectors xc and yc contain the remaining features in x and y respectively [5]. By this model, a value of 1 is assigned to the numerator of the discrete likelihood, while the frequencies of the region multiplied by the general model and minutiae-like probabilities were used to calculate the denominator. LRs between fingers and within the finger were also evaluated in two experiments. 216 fingerprints from 4 different fingers were used to evaluate the LR within the finger, while a dataset of 818 fingerprints was used to evaluate the LR between the fingers. Normally, the likelihood ratios for intra-finger tests should be higher than those between LR fingers[2].4.1.2 Model of Neumann et al (2012)Neumann et co. also in 2012 [8], proposed another LR model based on feature vectors but this time they proposed the use of radial triangulation. THE