Cross-Sensor Fingerprint Enhancement Using Adversarial Learning and Edge Loss.

A fingerprint sensor interoperability problem, or a cross-sensor matching problem, occurs when one type of sensor is used for enrolment and a different type for matching. Fingerprints captured for the same person using various sensor technologies have various types of noises and artifacts. This problem motivated us to develop an algorithm that can enhance fingerprints captured using different types of sensors and touch technologies. Inspired by the success of deep learning in various computer vision tasks, we formulate this problem as an image-to-image transformation designed using a deep encoder-decoder model. It is trained using two learning frameworks, i.e., conventional learning and adversarial learning based on a conditional Generative Adversarial Network (cGAN) framework. Since different types of edges form the ridge patterns in fingerprints, we employed edge loss to train the model for effective fingerprint enhancement. The designed method was evaluated on fingerprints from two benchmark cross-sensor fingerprint datasets, i.e., MOLF and FingerPass. To assess the quality of enhanced fingerprints, we employed two standard metrics commonly used: NBIS Fingerprint Image Quality (NFIQ) and Structural Similarity Index Metric (SSIM). In addition, we proposed a metric named Fingerprint Quality Enhancement Index (FQEI) for comprehensive evaluation of fingerprint enhancement algorithms. Effective fingerprint quality enhancement results were achieved regardless of the sensor type used, where this issue was not investigated in the related literature before. The results indicate that the proposed method outperforms the state-of-the-art methods.

The optimisation of fingermark enhancement by VMD and Lumicyano™ on thermal paper.

The enhancement of fingermarks on thermal paper can be challenging due to background staining caused by polar solvents used in fingermark enhancement techniques such as ninhydrin. This study explored a commercial one-step superglue fuming process, Lumicyano™, and Vacuum Metal Deposition (VMD) to develop fingermarks on this substrate and overcome this issue. Different sequential treatments involving Lumicyano™ and a combination of VMD methods were investigated with varying degrees of success with some sequences being highly sensitive. The VMD processes, however, were observed to generally be more effective at enhancing marks, whereas Lumicyano™ provided little or no benefit on this paper type. The results indicate that Lumicyano™ is only beneficial as a pre-treatment when the entire sequence of gold/zinc and silver/zinc is taken to completion. The gold/zinc and silver/zinc VMD processes were optimised on five different thermal papers, and the optimised techniques were then directly compared to determine which was more successful on each thermal paper type as a single treatment.

A Large-Scale Study of Fingerprint Matching Systems for Sensor Interoperability Problem.

The fingerprint is a commonly used biometric modality that is widely employed for authentication by law enforcement agencies and commercial applications. The designs of existing fingerprint matching methods are based on the hypothesis that the same sensor is used to capture fingerprints during enrollment and verification. Advances in fingerprint sensor technology have raised the question about the usability of current methods when different sensors are employed for enrollment and verification; this is a fingerprint sensor interoperability problem. To provide insight into this problem and assess the status of state-of-the-art matching methods to tackle this problem, we first analyze the characteristics of fingerprints captured with different sensors, which makes cross-sensor matching a challenging problem. We demonstrate the importance of fingerprint enhancement methods for cross-sensor matching. Finally, we conduct a comparative study of state-of-the-art fingerprint recognition methods and provide insight into their abilities to address this problem. We performed experiments using a public database (FingerPass) that contains nine datasets captured with different sensors. We analyzed the effects of different sensors and found that cross-sensor matching performance deteriorates when different sensors are used for enrollment and verification. In view of our analysis, we propose future research directions for this problem.

The Influence of Selected Fingerprint Enhancement Techniques on Forensic DNA Typing of Epithelial Cells Deposited on Porous Surfaces.

Fingerprints deposited at crime scene can be a source of DNA. Previous reports on the effects of fingerprint enhancement methods have focused mainly on fingermarks deposited in blood or saliva. Here, we evaluate the effects of fingerprint enhancement methods on fingerprints deposited on porous surfaces. We performed real-time quantification and STR typing, the results of which indicated that two methods (iodine fuming and 1,2-indanedione in ethyl acetate enhancement) had no effect on the quantity of DNA isolated and resultant STR alleles when compared to control samples. DNA quantities and allele numbers were lower for samples enhanced with silver nitrate and 1,2-indanedione in acetic acid when compared to control samples. Based on DNA quantity, quality, and observable stochastic effects, our data indicated that iodine fuming and 1,2-indanedione in ethyl acetate were the preferred options for the enhancement of fingerprints on porous surfaces.

New incompatibilities uncovered using the Promega DNA IQ™ chemistry.

Over the years, the Promega DNA IQ™ System was proven an effective technology for the production of clean DNA from a wide variety of casework specimens. The capture of DNA using the DNA IQ™ paramagnetic beads, however, was shown to be affected by a few specific chemicals that could be present on exhibits submitted to the laboratory. In this study, various blood and latent fingerprint enhancement reagents/methods, marker pens and adhesive tapes, applied at the crime scene or in the forensic laboratory on casework exhibits or used to collect biological material, were tested for their compatibility with the DNA IQ™ technology. Although no impact on DNA recovery was observed for most reagents, the MAGNA™ Jet Black fingerprint powder and three 3M Scotch(®) adhesive tapes were shown to severely or completely inhibit DNA binding onto the DNA IQ™ beads. The effect of MAGNA™ Jet Black on DNA recovery could be counteracted by separating the magnetic powder from the lysates by centrifugation or filtration, prior to DNA extraction. High quality STR profiles were obtained from samples subjected to MAGNA™ Jet Black suggesting it does not impact DNA integrity.