Crime Detection and Criminal Recognition to Intervene in Interpersonal Violence Using Deep Convolutional Neural Network With Transfer Learning

Mohammad Reduanul Haque, Rubaiya Hafiz, Alauddin Al Azad, Yeasir Adnan, Sharmin Akter Mishu, Amina Khatun, Mohammad Shorif Uddin

Source Title: International Journal of Ambient Computing and Intelligence (IJACI)12(4)

ISSN: 1941-6237|EISSN: 1941-6245|EISBN13: 9781799860297|DOI: 10.4018/IJACI.20211001.oa1

Cite Article Cite Article

MLA

Haque, Mohammad Reduanul, et al. "Crime Detection and Criminal Recognition to Intervene in Interpersonal Violence Using Deep Convolutional Neural Network With Transfer Learning." IJACI vol.12, no.4 2021: pp.154-167. http://doi.org/10.4018/IJACI.20211001.oa1

APA

Haque, M. R., Hafiz, R., Al Azad, A., Adnan, Y., Mishu, S. A., Khatun, A., & Uddin, M. S. (2021). Crime Detection and Criminal Recognition to Intervene in Interpersonal Violence Using Deep Convolutional Neural Network With Transfer Learning. International Journal of Ambient Computing and Intelligence (IJACI), 12(4), 154-167. http://doi.org/10.4018/IJACI.20211001.oa1

Chicago

Haque, Mohammad Reduanul, et al. "Crime Detection and Criminal Recognition to Intervene in Interpersonal Violence Using Deep Convolutional Neural Network With Transfer Learning," International Journal of Ambient Computing and Intelligence (IJACI) 12, no.4: 154-167. http://doi.org/10.4018/IJACI.20211001.oa1

Export Reference

Favorite Full-Issue Download

View Full Text HTML

View Full Text PDF

Abstract

Interpersonal violence, such as physical and sexual abuse, eve-teasing, bullying, and taking hostages, is a growing concern in our society. The criminals who directly or indirectly committed the crime often do not go into the trial for the lack of proper evidence as it is very tough to collect photographic proof of the incident. A subject's corneal reflection has the potentiality to reveal the bystander images. Motivated with this clue, a novel approach is proposed in the current paper that uses a convolutional neural network (CNN) along with transfer learning in identifying crime as well as recognizing the criminals from the corneal reflected image of the victim called the Purkinje image. This study found that off-the-shelf CNN can be fine-tuned to extract discriminative features from very low resolution and noisy images. The procedure is validated using the developed datasets comprising six different subjects taken at diverse situations. They confirmed that it has the ability to recognize criminals from corneal reflection images with an accuracy of 95.41%.