Sperm hunting on optical microscope slides for forensic analysis with deep convolutional networks – a feasibility study

Organization

Zurich Institute of Forensic Medicine

Description

Finding sperm cells under an optical microscope is a task which is time-consuming and difficult for a human being. This study shows how convolutional neural networks can be used to speed up the process. Two networks were tested based on the VGG19 architecture with a resulting accuracy of over 90%. Human oversight is still necessary to rule out false positives. The oversight is aided by a simple visual guide that can be provided to the overseeing experts which helps determine the accuracy of any given result.

File
PIIS1872497321001393.pdf
Link
https://www.fsigenetics.com/article/S1872-4973(21)00139-3/fulltext
Tags
Perpetrators
Type
Research (peer reviewed)
Year
2022
Stella Polaris Knowledge Center
Stella Polaris Knowledge Center
/
All reports
/
Sperm hunting on optical microscope slides for forensic analysis with deep convolutional networks – a feasibility study
Prediction of the development of depression and post-traumatic stress disorder in sexually abused children using a random forest classifier
Prediction of the development of depression and post-traumatic stress disorder in sexually abused children using a random forest classifier

Uskudar University Medical Faculty, Istanbul, Turkey

Research (peer reviewed)
Clustering/ClassificationMachine learningPost-crime effortsChild-focusedPost-traumatic stress (PTS)
Child Abuse and Domestic Abuse: Content and Feature Analysis from Social Media Disclosures
Child Abuse and Domestic Abuse: Content and Feature Analysis from Social Media Disclosures

Victoria University and University of Melbourne

Research (peer reviewed)
Artificial intelligenceMachine learningPreventionChild Sexual Abuse Material (CSAM)
Sperm hunting on optical microscope slides for forensic analysis with deep convolutional networks – a feasibility study