Logo des Repositoriums
 

Automatic Classification of Bloodstains with Deep Learning Methods

Kurzanzeige
dc.contributor.authorBergman, Tommy
dc.contributor.authorKlöden, Martin
dc.contributor.authorDreßler, Jan
dc.contributor.authorLabudde, Dirk
dc.date.accessioned2023-01-18T13:07:32Z
dc.date.available2023-01-18T13:07:32Z
dc.date.issued2022
dc.description.abstractThe classification of detected bloodstains into predetermined categories is a crucial component of the so-called bloodstain pattern analysis. As in other forensic disciplines, deep learning methods may help to reduce human subjectivity within this process, may increase the classification accuracy, shorten the calculation time and thus, enable high-throughput analysis. In this work, an approach is presented in which a convolutional neural network (Inception v3) was trained from 965 drip stains (passive origin) and 1595 blood spatters (active origin). The trained CNN was evaluated with a test data set consisting of 366 images of drip stains and blood spatters. The success rate was 99.73% which suggests that neural networks could also be used to automatically classify other classes of bloodstain patterns to speed up the investigation process in the future.de
dc.identifier.doi10.1007/s13218-022-00760-y
dc.identifier.pissn1610-1987
dc.identifier.urihttp://dx.doi.org/10.1007/s13218-022-00760-y
dc.identifier.urihttps://dl.gi.de/handle/20.500.12116/40043
dc.publisherSpringer
dc.relation.ispartofKI - Künstliche Intelligenz: Vol. 36, No. 2
dc.relation.ispartofseriesKI - Künstliche Intelligenz
dc.subjectBlood
dc.subjectClassification
dc.subjectCNN
dc.subjectCrime scene reconstruction
dc.subjectCriminal event
dc.subjectDeep learning
dc.subjectInception v3
dc.subjectTensorflow
dc.titleAutomatic Classification of Bloodstains with Deep Learning Methodsde
dc.typeText/Journal Article
gi.citation.endPage141
gi.citation.startPage135

Dateien

Sammlungen

Künstliche Intelligenz 36(2) - September 2022