Summary of Towards Automation Of Human Stage Of Decay Identification: An Artificial Intelligence Approach, by Anna-maria Nau et al.
Towards Automation of Human Stage of Decay Identification: An Artificial Intelligence Approach
by Anna-Maria Nau, Phillip Ditto, Dawnie Wolfe Steadman, Audris Mockus
First submitted to arxiv on: 19 Aug 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper explores the feasibility of automating two common human decomposition scoring methods using artificial intelligence (AI). The goal is to determine the stage of decomposition (SOD) for different anatomical regions, including the head, torso, and limbs. Two deep learning models, Inception V3 and Xception, were trained on a large dataset of human decomposition images to classify SODs. The Xception model achieved the best classification performance, with macro-averaged F1 scores ranging from .702 to .881 for different regions. An interrater study was also conducted to assess the reliability of AI models compared to human forensic examiners. Results show that AI can determine SOD at a reliability level comparable to a human expert. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper uses artificial intelligence (AI) to help identify how far along a body has decomposed. This is important for figuring out how long ago someone died and helping police find missing people or identify bodies. Right now, people have to look at pictures of decomposition and score them by hand, which takes a lot of time and can be tricky. The AI models were trained on lots of pictures of different stages of decomposition and could correctly identify what stage they are in most of the time. |
Keywords
* Artificial intelligence * Classification * Deep learning
