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网络，用于精准、高效且无成本的血迹沉积后时间推断**
血迹的沉积后时间（time since deposition, 以下简称TSD），即血迹形成的时刻，是犯罪现场勘查中至关重要的生物证据。现有部分微观检测方法（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。本文提出了一种具备实际应用价值的深度学习方法——BloodNet，可从宏观视角出发，通过易于获取的血迹照片实现TSD推断，兼具高效、精准与无成本的优势。为此，我们构建了一个基准数据集，包含约5万张不同TSD时长的血迹照片。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具有局部细粒度的特征表征，这些特征在不同TSD时段间具备极强的区分度。此外，基于Smooth Grad-CAM（Smooth Grad-CAM）工具对训练完成的深度网络进行可视化分析后发现，BloodNet能够稳定捕捉到特定TSD时长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推断的细粒度特征表征方面的有效性。作为BloodNet的对照研究，我们还利用拉曼光谱数据开展了微观分析，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，这种新型微观级方法在性能上大幅优于现有最优方法，但其推断精度仍显著低于BloodNet，这进一步验证了深度学习技术在极具挑战性的血迹TSD推断任务中的有效性。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（Imagenet）预训练模型对应的权重文件。
----bloodstain_information.csv：每条血迹的详细信息文件。

搜集汇总

背景与挑战

背景概述

BloodNet-Benchmark是一个包含约50,000张血液痕迹照片的数据集，用于训练和评估基于注意力机制的深度学习模型BloodNet，以实现高效、准确且低成本的血液痕迹沉积时间推断。数据集还包括模型权重文件和血液痕迹的详细信息文件。