• Darshil Sukhadiya
• Abhishek Tete
• Aniruddha Deotale
• Dilip Thakur
• Er. A. P. Mohod

Digital forensics relies extensively on fingerprint evidence. Accurate matching is hampered by noise, smearing, or low resolution in fingerprint images captured via digital devices. To improve digital fingerprint detection for forensics, this work proposes applying Convolutional Neural Networks (CNNs) for image enhancement and feature extraction, together with OpenCV for pre-processing. Pre-processing techniques like noise reduction and binarization are made easier with OpenCV, setting up the fingerprint image for further CNN process. A CNN can identify and improve fingerprint ridge patterns after being trained on an extensive database of fingerprint images. After that, features are extracted from this improved image, possibly using OpenCV for fine-grained extraction. Lastly, a fingerprint database is compared with the derived features using a fingerprint-matching algorithm. By integrating CNN-powered feature extraction with OpenCV's image processing capabilities, there is a chance that fingerprint-matching accuracy may increase, producing stronger forensic evidence.

OpenCV, Image Processing, Recognition, SIFT, Authentication, FLANN-based matcher, CNNs, GUI.

"Enhancing Digital Fingerprint Identification in Forensics Using Convolution Neural Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.a562-a571, April-2024, Available :http://www.jetir.org/papers/JETIR2404071.pdf

"Enhancing Digital Fingerprint Identification in Forensics Using Convolution Neural Network", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppa562-a571, April-2024, Available at : http://www.jetir.org/papers/JETIR2404071.pdf