Figure 2 - uploaded by Akshay Agarwal
Content may be subject to copyright.
Two samples of latent fingerprint images lifted from the eight surfaces used in the database collection. (from left to right) First row: compact disc, steel glass, paperback cover, hardbound cover. Second row: transparent glass, ceramic plate, ceramic mug, compact disc mailer. (Best viewed in color and under zoom).
Context in source publication
Similar publications
Abstract With rapid development of the Internet, images are spreading more and more quickly and widely. The phenomenon of image illegal usage emerges frequently, and this has marked impacts on people’s normal life. Therefore, it is of great importance to protect image security and image owner’s rights. At present, most image protection is passive....
To study the bridge damage location and degree identification ability based on curvature mode, with a three-span continuous steel beam as the research object, compared with the damage location identification of curvature modal difference and displacement modal difference, analyzing the influence of damage location identification on the curvature mo...
Citations
... Public latent fingerprint databases and automatic fingerprint identification systems (AFIS) are required to benchmark latent fingerprint restoration algorithms. We experimented on four public latent datasets, including NIST-SD27 [8], IIITD-MOLF DB4 [42], IIITD-MFLSD [43], and NIST-SD302 [44]. The number of latent fingerprint images, corresponding fingerprint images, and background gallery fingerprint images from each dataset are summarized in Table 4. ...
... This dataset is always required in the latent fingerprint enhancement algorithms benchmark due to rich state-of-the-art results. # Gallery NIST-SD14 [34] COTS/Open-Source NIST-SD27 [8] 258 258 (rolled) 27,258/2,258 IIITD-MOLF [42] 4,400 4000 (slapped) 31,000/6,000 IIITD-MSLFD [43] 551 122 (slapped) 27,122/2,122 NIST-SD302 [44] 1,019 1,019 (rolled) 28,019/-Lately, several researchers have used the IIITD-MOLF DB4 dataset [42] for their latent fingerprint enhancement benchmark. This dataset contains a large number of latent fingerprint images. ...
... The third dataset is the IIITD-MSLFD dataset [43]. Latent fingerprints in this dataset were collected from eight different backgrounds in the laboratory. ...
Latent fingerprint restoration is one of the most challenging problems for fingerprint identification. According to the current next-generation identification (NGI) system fact sheet, the number of unsolved latent fingerprint cases is more than a million and is increasing daily. The current state-of-the-art algorithms utilize various deep-learning networks to restore latent fingerprints in the spatial domain. Unfortunately, these algorithms faced difficulty recovering genuine friction ridges from low-quality latent fingerprints with complex backgrounds and noise. Instead of using deep-learning models to restore latent fingerprints directly in the spatial domain, we used the deep-learning model to predict a frequency-domain filter for restoring each latent input partitioning block. We integrated this new filter predictor model within a progressive feedback framework. As a result, the proposed method can reveal genuine friction ridges from complex backgrounds, especially around very low-quality areas and singular point areas, which is crucial to the success of latent fingerprint identification. We benchmarked our proposed method against state-of-the-art methods with four public latent fingerprint datasets. In addition, we used one commercial-of-the-shelf (COTS) and another open-source fingerprint matchers in our benchmark. The experiments showed that the proposed method outperformed current state-of-the-art methods in identification accuracy. Compared to the state-of-the-art methods using deep learning in the spatial domain, the proposed method achieved an average rank-1 identification accuracy improvement of 3.75% and 3.19% of four public datasets with the COTS and open-source fingerprint matchers, respectively. Finally, the execution code was made publicly available for non-commercial purposes at https://github.com/skconan/SFP-Progressive-Feedback-Latent-Fingerprint-Restoration.
... Sankaran et al. [22] Random decision forest NIST SD4/27 IIITD-CLF [17] R50-IA=0.723 ...
Latent fingerprints are among the most important and widely used evidence in crime scenes, digital forensics and law enforcement worldwide. Despite the number of advancements reported in recent works, we note that significant open issues such as independent benchmarking and lack of large-scale evaluation databases for improving the algorithms are inadequately addressed. The available databases are mostly of semi-public nature, lack of acquisition in the wild environment, and post-processing pipelines. Moreover, they do not represent a realistic capture scenario similar to real crime scenes, to benchmark the robustness of the algorithms. Further, existing databases for latent fingerprint recognition do not have a large number of unique subjects/fingerprint instances or do not provide ground truth/reference fingerprint images to conduct a cross-comparison against the latent. In this paper, we introduce a new wild large-scale latent fingerprint database that includes five different acquisition scenarios: reference fingerprints from (1) optical and (2) capacitive sensors, (3) smartphone fingerprints, latent fingerprints captured from (4) wall surface, (5) Ipad surface, and (6) aluminium foil surface. The new database consists of 1,318 unique fingerprint instances captured in all above mentioned settings. A total of 2,636 reference fingerprints from optical and capacitive sensors, 1,318 fingerphotos from smartphones, and 9,224 latent fingerprints from each of the 132 subjects were provided in this work. The dataset is constructed considering various age groups, equal representations of genders and backgrounds. In addition, we provide an extensive set of analysis of various subset evaluations to highlight open challenges for future directions in latent fingerprint recognition research.
... Both datasets contain fingermarks lifted from various surfaces by trained forensic examiners in a simulated environment. We also considered the IIITD MOLF [74] and IIITD MSFLD datasets [75] but could not confirm whether the fingermarks were collected by trained forensic examiners. The scale (in PPI) at which the fingermarks were captured is not specified, and the images are often blurred or were captured in inadequate lighting conditions, thus do not conform with established best practices in forensic dactyloscopy [76]. ...
The quality assessment of fingermarks (latent fingerprints) is an essential part of a forensic investigation. It indicates how valuable the fingermarks are as forensic evidence, it determines how they should be further processed, and it correlates with the likelihood of successful identification, i.e., finding a matching fingerprint in a reference database. Since the environments in which fingermarks are found are not controlled, this task proves challenging even with modern machine learning solutions. In this work, we propose a predictive framework for automated fingermark quality assessment (AFQA). With this iteration of AFQA, we bridge the gap between the classic machine learning approach with handcrafted features and the modern deep learning paradigm, evaluate the advantages and disadvantages of these methodologies, and provide the rationale and direction for future development of AFQA methods. We present a significantly improved AFQA toolbox and provide a quality aggregation method capable of fusing together multiple predicted quality values from an ensemble of quality assessment models. The proposed ensemble approach provides improved prediction performance while reducing processing time compared to existing state-of-the-art solutions.
... Dataset and data augmentation Fingerprints were acquired from IIITD MSLFD database [19]. Database consists of 551 latent fingerprints from 51 people on 8 different surfaces (ceramic plate, ceramic mug, transparent glass, steel glass, CD, CD mailer, paperback book cover and hardbound book cover). ...
... Emphasis has been put on using Level 1 features which were incorporated by 2-D linear symmetric structure tensor and orientation field. Sankaran et al. [12] investigated the quality of latent which was lifted from eight different surfaces. Cao et al. [13] have proposed a fully automatic method based on minutiae, ridge quality, ridge flow, core and delta points for latent value determination. ...
... It contains 449 latent images acquired using powder method along with 449 mated rolled prints at a resolution of 1000 ppi. IIITD Multi-Surface Latent Fingerprint Database (IIITD MSLFD) [9]: This database has been made available since 2015 by the IIIT-Delhi. It contains 551 latent images lifted using black powder dusting process from 51 subjects along with 1020 optical slap images. ...
Latent fingerprint is considered as the key evidence during crime scene investigations. Various powder and chemical methods are available for visualizing the latent fingerprints as these finger impressions are not directly visible through the naked eye. However, these methods may damage the finger impressions in case if they are not properly lifted and handled carefully. Preserving the evidential value of the located latent fingerprints, hence becomes pivotal for analyzing and identifying the suspected individual. Nowadays, optical touchless technology is being prevalent for developing and visualizing the latent finger impressions. Reflected Ultra Violet Imaging System (RUVIS) is one such optical touchless device. There are number of powder based latent fingerprint databases available. However, database of latent fingerprints using optical touchless technology is not available in the literature. The paper presents the latent fingerprint database developed and captured using the touch-less acquisition device (RUVIS). Extraction of level 3 features from the latent fingerprints plays a significant role in matching these latent impressions with plain impressions. Further in this paper, level 3 features, particularly pores are extracted using Fully Convolution Neural Network (FCN) from the collected latent fingerprints using the RUVIS.
Latent fingerprint recognition involves acquisition and comparison of latent fingerprints with an exemplar gallery of fingerprints. The diversity in the type of surface leads to different procedures to recover the latent fingerprint. The appearance of latent fingerprints vary significantly due to the development techniques, leading to large intra-class variation. Due to lack of large datasets acquired using multiple mechanisms and surfaces, existing algorithms for latent fingerprints enhancement and comparison may perform poorly. In this study, we propose a Multi-Surface Multi-Technique (MUST) Latent Fingerprint Database. The database consists of more than 16,000 latent fingerprint impressions from 120 unique classes (120 fingers from 12 participants). Including corresponding exemplar fingerprints (livescan and rolled) and extended gallery, the dataset has nearly 21,000 impressions. It has latent fingerprints acquired under 35 different scenarios and additional four subsets of exemplar prints captured using live scan sensor and inked-rolled prints. With 39 different subsets, the database illustrates intra-class variations in latent fingerprints. The database has a potential usage towards building robust algorithms for latent fingerprint enhancement, segmentation, comparison, and multi-task learning. We also provide annotations for manually marked minutiae, acquisition PPI, and semantic segmentation masks are also provided. We also present the experimental protocol and the baseline results for the proposed dataset. We assert that the availability of the proposed database can encourage research in handling intra-class variation in latent fingerprint recognition.
