Name
Abstract | ||
|---|---|---|
Micro traces analysis is a new and growing area of research within forensic science. One of the possible applications of this knowledge is to assist in determining the area of origin of criminal elements. Micro traces of insects are found in many crime contexts such as inside narcotics, money bags or even in remains. Forensic entomology has been increasingly used to characterize insects found in these contexts. Insect characterization is a slow and complex process, mainly because specimens are usually found in pieces. To simplify and accelerate this analysis, this paper presents the use of a deep neural network to characterize insects or their parts up to the taxonomic level of the family from specimen images. The developed system reached a classification accuracy of 75.0% among five evaluated entomological families: Buprestidae, Calliphoridae, Formicidae, Muscidae and Pentatomidae. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/SSCI44817.2019.9003145 | 2019 IEEE Symposium Series on Computational Intelligence (SSCI) |
Keywords | Field | DocType |
forensic science,entomological micro traces images,deep neural networks,insect family classification | Forensic entomology,Pentatomidae,Geography,Cartography,Deep neural networks,Buprestidae,Calliphoridae | Conference |
ISBN | Citations | PageRank |
978-1-7281-2486-5 | 0 | 0.34 |
References | Authors | |
0 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Adriano C. A. da Cruz | 1 | 0 | 0.34 |
| Felipe A. Schwab | 2 | 0 | 0.34 |
| Ozana M. A. Maia | 3 | 0 | 0.34 |
| Rubens A. de Faria | 4 | 0 | 0.34 |
| Gustavo B. Borba | 5 | 0 | 0.34 |
| Valfredo Pilla Jr | 6 | 0 | 0.34 |