BloodNet-Benchmark

<em><strong>BloodNet: An attention-based deep network for accurate, efficient, and costless bloodstain time since deposition inference</strong></em> <br> The time since deposition (TSD) of a bloodstain, i.e., the time of a bloodstain formation is an essential piece of biological evidence in crime scene investigation. The practical usage of some existing microscopic methods (e.g., spectroscopy or RNA analysis technology) is limited, as their performance strongly relies on high-end instrumentation and/or rigorous laboratory conditions. This paper presents a practically applicable deep learning-based method (i.e., <strong>BloodNet</strong>) for efficient, accurate, and costless TSD inference from a macroscopic view, i.e., by using easily accessible bloodstain photos. To this end, we established a benchmark database containing around 50,000 photos of bloodstains with varying TSDs. Capitalizing on such a large-scale database, BloodNet adopted attention mechanisms to learn from relatively high-resolution input images the localized fine-grained feature representations that were highly discriminative between different TSD periods. Also, the visual analysis of the learned deep networks based on the Smooth Grad-CAM tool demonstrated that our BloodNet can stably capture the unique local patterns of bloodstains with specific TSDs, suggesting the efficacy of the utilized attention mechanism in learning fine-grained representations for TSD inference. As a paired study for BloodNet, we further conducted a microscopic analysis using Raman spectroscopic data and a machine learning method based on Bayesian optimization. Although the experimental results show that such a new microscopic-level approach outperformed the state-of-the-art by a large margin, its inference accuracy is significantly lower than BloodNet, which further justifies the efficacy of deep learning techniques in the challenging task of bloodstain TSD inference. Our code is publically accessible via <em>https://github.com/shenxiaochenn/BloodNet</em>. ----data.zip All the bloodstain images have been placed in the appropriate folders according to the corresponding categories.The name of the folder is the tag information corresponding to the image. ----bloodnet50_new.pth The weights corresponding to the classification model. ----bloodnet50_reg.pth The weights corresponding to the regression model. ----bloodnet(small).pth The weights corresponding to the small classification model. ----seresnet50-60a8950a85b2b.pkl The weights corresponding to the Imagenet pretrain model. ----bloodstain_information.csv The detailed information of each bloodstain. <br>**BloodNet：一款基于注意力机制的深度学习网络，用于精准、高效且无额外成本的血迹沉积时间推断** 血迹的沉积后时间（time since deposition, TSD），即血迹形成的时刻，是犯罪现场勘查中不可或缺的生物物证。现有部分显微分析方法（如光谱学技术或RNA分析技术）的实际应用存在局限，因其性能高度依赖高端仪器设备及严苛的实验室环境。本文提出了一种可实际应用的基于深度学习的方法——BloodNet，可从宏观视角出发，通过易于获取的血迹照片实现高效、精准且无额外成本的TSD推断。为此，我们构建了一个基准数据集，包含约5万张不同TSD的血迹照片。 依托该大规模数据集，BloodNet采用注意力机制，从相对高分辨率的输入图像中学习局部细粒度特征表示，此类特征在不同TSD时段间具备高度区分性。此外，基于Smooth Grad-CAM工具对训练完成的深度学习网络开展可视化分析后发现，BloodNet能够稳定捕捉特定TSD血迹的独特局部模式，这证实了所采用的注意力机制在学习用于TSD推断的细粒度特征方面的有效性。 作为BloodNet的对照研究，我们进一步使用拉曼光谱数据开展显微分析，并采用基于贝叶斯优化的机器学习方法。尽管实验结果表明，这种新型显微级方法大幅优于当前最优技术，但其推断精度显著低于BloodNet，这进一步验证了深度学习技术在血迹TSD推断这一挑战性任务中的有效性。 本研究的代码可通过以下链接公开获取：https://github.com/shenxiaochenn/BloodNet。 ----data.zip：所有血迹图像已按照对应类别存入相应文件夹，文件夹名称即为图像对应的标签信息。 ----bloodnet50_new.pth：分类模型对应的权重文件。 ----bloodnet50_reg.pth：回归模型对应的权重文件。 ----bloodnet(small).pth：小型分类模型对应的权重文件。 ----seresnet50-60a8950a85b2b.pkl：Imagenet预训练模型对应的权重文件。 ----bloodstain_information.csv：各血迹的详细信息文件。