Abstract
Latent fingerprint segmentation is a complex process of separating relevant areas called fingerprints from an irrelevant background in the latent fingerprint image which is of poor quality. A breakthrough in the field can be used to segment fingerprints accurately from the background by using optimal resources. Processing of unwanted background of the entire image can lead to false and missed detection of fingerprints. An early fingerprint distinction technique based on colour and saliency masks is proposed to detect potentially relevant areas out of the entire image area for further processing, using a non-learning approach. Later, the patches of early detected fingermarks are fed to a stacked convolutional autoencoder for separating imposters of fingerprint(s) region from relevant fingerprint(s) regions, using a deep learning approach. The inspiration to use the convolutional neural network in this hybrid approach is to effectively capture feature distinction from potential features similar to that of object detection and classification. The inspiration to use autoencoder in a stack is to provide better feature engineering for CNN. The use of the pre-trained convolutional neural network with a stack of autoencoders for image classification and segmentation produces better results than a naive convolutional neural network. The experiments are conducted on the IIIT-D database. The efficiency and effectiveness of the model over good quality images is evaluated by experimenting over different patch sizes, with and without the use of dropout in CNN, with and without use of Autoencoder with CNN. The early detection of contours along with patch-based classification-cum-segmentation using SCAE on good quality images produces 98.45% segmentation accuracy.



















Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Data availability
There is IIITD Latent fingerprint dataset with 150 classes and 1046 images. The database can be obtained go to the url:http://www.iab-rubric.org/resources.html.
References
Agarwal D, Bansal A (2021) A utility of pores as level 3 features in latent fingerprint identification. Multimed Tools Appl 80(15):23605–23624
Ali H, Sharif M, Yasmin M, Rehmani MH (2020) Colour-based template selection for detection of gastric abnormalities in video endoscopy. Biomed Signal Process Control 56(101668):101668
Amin J, Sharif M, Gul N, Raza M, Anjum MA, Nisar MW, Bukhari SAC (2019) Brain tumor detection by using stacked autoencoders in deep learning. J Med Syst 44(2):32
Azman AR, Mahat NA, Wahab RA, Ahmad WA, Puspanadan JK, Huri MAM, Kamaluddin MR, Ismail D (2021) Box-behnken design optimisation of a green novel nanobio-based reagent for rapid visualisation of latent fingerprints on wet. Non-porous substrates. Biotechnol Lett 43(4):881–898
Baur C, Denner S, Wiestler B, Navab N, Albarqouni S (2021) Autoencoders for unsupervised anomaly segmentation in brain mr images: a comparative study. Med Image Anal 69(101952):101952
Borji A (2015) What is a salient object? A dataset and a baseline model for salient object detection. IEEE Trans Image Process 24(2):742–756
Cao K, Jain AK (2015) Latent orientation field estimation via convolutional neural network. In: 2015 International conference on biometrics (ICB). IEEE
Chandraprabha K, Akila S (2019) Texture feature extraction for batik images using glcm and glrlm with neural network classification. Int J Sci Res Comput Sci Eng Inf Technol 06–15
Chen L-C, Papandreou G, Kokkinos I, Murphy K, Yuille AL (2018) DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Trans Pattern Anal Mach Intell 40(4):834–848
Chhabra M, Shukla MK, Ravulakollu KK (2020) Boosting the classification performance of latent fingerprint segmentation using cascade of classifiers. Intell Decis Technol 14(3):359–371
Chhabra M, Shukla MK, Ravulakollu KK (2021) Bagging- and boosting-based latent fingerprint image classification and segmentation. Advances in intelligent systems and computing. Springer, Singapore, pp 189–201
Chhabra M, Shukla MK, Ravulakollu KK (2021) State-of-the-art: a systematic literature review of image segmentation in latent fingerprint foren. Recent Pat Comput Sci 13(6):1115–1125
Cornia M, Baraldi L, Serra G, Cucchiara R (2018) Paying more attention to saliency: image captioning with saliency and context attention. ACM Trans Multimed Comput Commun Appl 14(2):1–21
Daluz HM (2021) Courtroom testimony for fingerprint examiners. CRC Press, Florida
Deufel B, Mueller C, Duffy G, Kevenaar T (2013) BioPACE: biometric passwords for next generation authentication protocols for machine-readable travel documents. Datenschutz Datensicherheit - DuD 37(6):363–366
Diyasa GSM, Fauzi A, Idhom M, Setiawan A (2021) Multi-face recognition for the detection of prisoners in jail using a modified cascade classifier and CNN. J Phys Conf Ser 1844(1):012005
Ezeobiejesi J, Bhanu B (2016) Latent fingerprint image segmentation using fractal dimension features and weighted extreme learning machine ensemble. In: 2016 IEEE conference on computer vision and pattern recognition workshops (CVPRW). IEEE
Ezeobiejesi J, Bhanu B (2017) Latent fingerprint image segmentation using deep neural network. Deep learning for biometrics. Springer International Publishing, Cham, pp 83–107
Fan R, Li X, Lee S, Li T, Zhang HL (2020) Smart image enhancement using CLAHE based on an F-shift transformation during decompression. Electronics 9(9):1374
Haralick R, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybernet SMC 3(6):610–621
Henry ER (1900) Classification and uses of fingerprints. Routledge & Sons, London
Hsiao C-T, Lin C-Y, Wang P-S, Wu Y-T (2022) Application of convolutional neural network for fingerprint-based prediction of gender, finger position, and height. Entropy (Basel) 24:475. https://doi.org/10.3390/e24040475
Huang F, Zhang J, Zhou C, Wang Y, Huang J, Zhu L (2020) A deep learning algorithm using a fully connected sparse autoencoder neural network for landslide susceptibility prediction. Landslides 17(1):217–229
Igoe DP, Parisi AV, Downs NJ, Amar A, Turner J (2018) Comparative signal to noise ratio as a determinant to select smartphone image sensor colour channels for analysis in the UVB. Sensors and actuators. A, Physical 272:125–133
Jalali S, Boostani R, Mohammadi M (2021) Efficient fingerprint features for gender recognition. Multidimens Syst Signal Process. https://doi.org/10.1007/s11045-021-00789-6
Johnson BT, Riemen JAJM (2019) Digital capture of fingerprints in a disaster victim identification setting: a review and case study. Forensic Sci Res 4(4):293–302
Kalka ND, Beachler M, Hicklin RA (2020) LQMetric: a latent fingerprint quality metric for predicting AFIS performance and assessing the value of latent fingerprints. JFI 70(4):443–463
Khan AI, Wani MA (2019) Patch-based segmentation of latent fingerprint images using convolutional neural network. Appl Artif Intell AAI 33(1):87–100
Kharghanian R, Peiravi A, Moradi F, Iosifidis A (2021) Pain detection using batch normalized discriminant restricted boltzmann machine layers. J Vis Commun Image Represent 76(103062):103062
Krizhevsky A, Sutskever I, Hinton GE (2017) ImageNet classification with deep convolutional neural networks. Commun ACM 60(6):84–90
Kumar AS, Nair JJ (2019) Pair wise training for stacked convolutional autoencoders using small scale images. J Intell Fuzzy Syst 36(3):1987–1995
Li G, Yu Y (2016) Visual saliency detection based on multiscale deep CNN features. IEEE Trans Image Process Pub IEEE Signal Process Soc 25(11):5012–5024
Liu Y, Zhang Y, Coleman S, Bhanu B, Liu S (2020) A new patch selection method based on parsing and saliency detection for person reidentification. Neurocomputing 374:86–99
Liu Yisi, Wang X, Wang L, Liu D (2019) A modified leaky ReLU scheme (MLRS) for topology optimization with multiple materials. Appl Math Comput 352:188–204
Maltoni D, Maio D, Jain AK, Prabhakar S (2009) Handbook of fingerprint recognition. Springer-Verlag, Berlin
Marmanis D, Schindler K, Wegner JD, Galliani S, Datcu M, Stilla U (2018) Classification with an edge: improving semantic image segmentation with boundary detection. ISPRS J Photogramm Remote Sens Off Pub Int Soc Photogramm Remote Sens (ISPRS) 135:158–172
Masci J, Meier U, Cireşan D, Schmidhuber J (2011) Stacked convolutional auto-encoders for hierarchical feature extraction. Lecture notes in computer science. Springer, Berlin Heidelberg, pp 52–59
Mateescu VA, Bajic IV (2016) Visual attention retargeting. IEEE Multimed 23(1):82–91
Mehtre BM, Murthy NN, Kapoor S, Chatterjee B (1987) Segmentation of fingerprint images using the directional image. Pattern Recogn 20(4):429–435
Mújica-Vargas D, Kinani JMV, de Rubio J, J. (2020) Color-based image segmentation by means of a robust intuitionistic fuzzy C-means algorithm. Int J Fuzzy Syst 22(3):901–916
Murshed MGS, Kline R, Bahmani K, Hussain F, Schuckers S (2021) Deep slap fingerprint segmentation for juveniles and adults. In arXiv [cs.CV]. http://arxiv.org/abs/2110.04067
Nguyen D-L, Cao K, Jain AK (2018) Automatic latent fingerprint segmentation. In: 2018 IEEE 9th international conference on biometrics theory, applications and systems (BTAS). IEEE
Prasad V, Prasad L, Lukose S, Agarwal P (2021) Latent fingerprint development by using silver nanoparticles and silver nitrate-A comparative study. J Forensic Sci 66(3):1065–1074
Prost J, Cihak-Bayr U, Neacşu IA, Grundtner R, Pirker F, Vorlaufer G (2021) Semi-supervised classification of the state of operation in self-lubricating journal bearings using a random forest classifier. Lubricants (Basel, Switzerland) 9(5):50
Saguy M, Almog J, Cohn D, Champod C (2021) Proactive forensic science in biometrics: novel materials for fingerprint spoofing. J Forensic Sci. https://doi.org/10.1111/1556-4029.14908
Sankaran A, Vatsa M, Singh R (2014) Latent fingerprint matching: a survey. IEEE Access: Pract Innov Open Solut 2:982–1004
Sankaran A, Jain A, Vashisth T, Vatsa M, Singh R (2017) Adaptive latent fingerprint segmentation using feature selection and random decision forest classification. Int J Inf Fusion 34:1–15
Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw Off J Int Neural Netw Soc 61:85–117
Shenoy ES, Rosenthal ES, Shao Y-P, Biswal S, Ghanta M, Ryan EE, Suslak D et al (2018) Real-time, automated detection of ventilator-associated events: avoiding missed detections, misclassifications, and false detections due to human error. Infect Control Hosp Epidemiol Off J Soc Hosp Epidemiol Am 39(07):826–833
Shi J, Yan Q, Xu L, Jia J (2016) Hierarchical image saliency detection on extended CSSD. IEEE Trans Pattern Anal Mach Intell 38(4):717–729
Singh SP, Ayub S, Saini JP (2021) Analysis and comparison of normal and altered fingerprint using artificial neural networks. Int J Knowl Based Intell Eng Syst 25(2):243–249
Sonali S, Sahu AK, Singh S.P. Ghrera, Elhoseny M (2019) An approach for De-noising and contrast enhancement of retinal fundus image using CLAHE. Opt Laser Technol 110:87–98
Stojanović B, Marques O, Nešković A (2019) Latent fingerprint datasets. Segmentation and separation of overlapped latent fingerprints. Springer International Publishing, Cham, pp 9–20
Stojanović B, Marques O, Nešković A (2019) Machine learning based segmentation of overlapped latent fingerprints. Segmentation and separation of overlapped latent fingerprints. Springer International Publishing, Cham, pp 29–34
Sudharshan PJ, Petitjean C, Spanhol F, Oliveira LE, Heutte L, Honeine P (2019) Multiple instance learning for histopathological breast cancer image classification. Expert Syst Appl 117:103–111
Tembusai ZR, Mawengkang H, Zarlis M (2021) K-nearest neighbor with K-fold cross validation and analytic hierarchy process on data classification. Int J Adv Data Inf Syst. https://doi.org/10.25008/ijadis.v2i1.1204
Venosa AD, King DW, Sorial GA (2002) The baffled flask test for dispersant effectiveness: a round robin evaluation of reproducibility and repeatability. Spill Sci Technol Bull 7(5–6):299–308
Wan GC, Li MM, Xu H, Kang WH, Rui JW, Tong MS (2020) XFinger-net: pixel-wise segmentation method for partially defective fingerprint based on attention gates and U-net. Sensors (Basel, Switzerland) 20(16):4473
Wang S-H, Muhammad K, Hong J, Sangaiah AK, Zhang Y-D (2020) Alcoholism identification via convolutional neural network based on parametric ReLU, dropout, and batch normalization. Neural Comput Appl 32(3):665–680
Wang H-J, Hou W-Y, Kang J, Zhai X-Y, Chen H-L, Hao Y-W, Wan G-Y (2021) The facile preparation of solid-state fluorescent carbon dots with a high fluorescence quantum yield and their application in rapid latent fingerprint detection. Dalton Trans (Cambridge, England: 2003) 50(35):12188–12196
Xu X, Mu N, Chen L, Zhang X (2016) Hierarchical salient object detection model using contrast-based saliency and color spatial distribution. Multimed Tools Appl 75(5):2667–2679
Yan Y, Nie F, Li W, Gao C, Yang Y, Xu D (2016) Image classification by cross-media active learning with privileged information. IEEE Trans Multimed 18(12):2494–2502
Yang D, Karimi HR, Sun K (2021) Residual wide-kernel deep convolutional auto-encoder for intelligent rotating machinery fault diagnosis with limited samples. Neural Netw Off J Int Neural Netw Soc 141:133–144
Yuan X, Feng Z, Norton M, Li X (2019) Generalized batch normalization: towards accelerating deep neural networks. Proceedings of the ...AAAI conference on artificial intelligence. AAAI Conf Artif Intell 33:1682–1689
Zdilla MJ, Hatfield SA, McLean KA, Cyrus LM, Laslo JM, Lambert HW (2016) Circularity, solidity, axes of a best fit ellipse, aspect ratio, and roundness of the foramen ovale: a morphometric analysis with neurosurgical considerations: a morphometric analysis with neurosurgical considerations. J Craniofac Surg 27(1):222–228
Zhang Y, Gao C, Li Z, Lv Y, Zhu K (2021) A method of fingermark anti-counterfeiting for forensic document identification. Pattern Recogn Lett 152:86–92
Zhou D-X (2020) Theory of deep convolutional neural networks: downsampling. Neural Netw Off J Int Neural Netw Soc 124:319–327
Zhou H, Yu G (2021) Research on fast pedestrian detection algorithm based on autoencoding neural network and adaboost. Complexity 2021:1–17
Zhu F, Kong X, Fu H, Tian Q (2018) A novel two-stream saliency image fusion CNN architecture for person re-identification. Multimedia Syst 24(5):569–582
Acknowledgements
The authors are thankful to IIITD for providing the latent fingerprint database. We would also like to acknowledge UPES, Dehradun, India, for providing the computing resources for experimentation.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
The authors find no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Chhabra, M., Ravulakollu, K.K., Kumar, M. et al. Improving automated latent fingerprint detection and segmentation using deep convolutional neural network. Neural Comput & Applic 35, 6471–6497 (2023). https://doi.org/10.1007/s00521-022-07894-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-022-07894-y