A deep learning approach for the forensic evaluation of sexual assault

Kelwin Fernandes*, Jaime S. Cardoso, Birgitte Schmidt Astrup

*Corresponding author for this work

Research output: Contribution to journalJournal articleResearchpeer-review


Despite the existence of patterns able to discriminate between consensual and non-consensual intercourse, the relevance of genital lesions in the corroboration of a legal rape complaint is currently under debate in many countries. The testimony of the physicians when assessing these lesions has been questioned in court due to several factors (e.g., a lack of comprehensive knowledge of lesions, wide spectrum of background area, among others). Therefore, it is relevant to provide automated tools to support the decision process in an objective manner. In this work, we evaluate the performance of state-of-the-art deep learning architectures for the forensic assessment of sexual assault. We propose a deep architecture and learning strategy to tackle the class imbalance on deep learning using ranking. The proposed methodologies achieved the best results when compared with handcrafted feature engineering and with other deep architectures.

Original languageEnglish
JournalPattern Analysis and Applications
Issue number3
Pages (from-to)629–640
Publication statusPublished - 1. Aug 2018


  • Classification
  • Deep learning
  • Digital colposcopy
  • Forensics
  • Genital injury
  • Image processing
  • Neural networks
  • Segmentation
  • Transfer learning


Dive into the research topics of 'A deep learning approach for the forensic evaluation of sexual assault'. Together they form a unique fingerprint.

Cite this