• P-ISSN 0974-6846 E-ISSN 0974-5645

Indian Journal of Science and Technology


Indian Journal of Science and Technology

Year: 2023, Volume: 16, Issue: 42, Pages: 3795-3802

Original Article

A Discrete Wavelet Transform and Dense CNN for Hyperspectral Imaging-Based Bloodstain Classification

Received Date:07 July 2023, Accepted Date:30 September 2023, Published Date:13 November 2023


Objectives: To maximize the identification and improve the accuracy of classifying the bloodstain in a hyperspectral image (HSI) at the crime scene, a 3-D discrete wavelet transform (3-D DWT) Dense CNN deep learning model is proposed in this work. Methods: This work proposes the use of a 3-D DWT to pre-process HSI data to effectively extract both spatial and spectral information while maintaining robust feature representation capabilities. Then, 3-D CNN that integrates dense connections attaches great importance to the reuse of features for classification. The experiment was carried out with the initial training/testing ratio set to 10/90 of the data samples, and we compared the results with four different state-of-the-art CNN architectures. Findings: The experimental results show that the 3-D DWT Dense CNN deep learning model achieves 97% classification accuracy, smoother classification maps, and more discriminable features for hyperspectral image classification. Novelty and Application: This work provides a deep learning 3D dense CNN model with the 3-D DWT and achieves improved identification of bloodstains at a messy crime scene. The proposed model requires a smaller number of trainable parameters, less computational power, so it can be used in the field of forensic science, where substance classification at the scene is important.

Keywords: Hyperspectral Imaging, Blood Strain Classification, Discrete Wavelet Transform (DWT), 3­D CNN, Dense Connection, Forensic Science


  1. Achetib N, Falkena K, Swayambhu M, Aalders MCG, Dam Av. Specific fluorescent signatures for body fluid identification using fluorescence spectroscopy. Scientific Reports. 2023;13(1):1–13. Available from: https://doi.org/10.1038/s41598-023-30241-7
  2. Khan MJ, Khan HS, Yousaf A, Khurshid K, Abbas A. Modern Trends in Hyperspectral Image Analysis: A Review. IEEE Access. 2018;6:14118–14129. Available from: https://ieeexplore.ieee.org/document/8314827
  3. Majda A, Wietecha-Posłuszny R, Mendys A, Wójtowicz A, Łydżba-Kopczyńska B. Hyperspectral imaging and multivariate analysis in the dried blood spots investigations. Applied Physics A. 2018;124(4):1–8. Available from: https://doi.org/10.1007/s00339-018-1739-6
  4. Ahmad M, Shabbir S, Roy SK, Hong D, Wu X, Yao J, et al. Hyperspectral Image Classification—Traditional to Deep Models: A Survey for Future Prospects. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2021;15:968–999. Available from: https://ieeexplore.ieee.org/document/9645266/authors
  5. Zulfiqar M, Ahmad M, Sohaib A, Mazzara M, Distefano S. Hyperspectral Imaging for Bloodstain Identification. Sensors. 2021;21(9):1–20. Available from: https://doi.org/10.3390/s21093045
  6. Książek K, Romaszewski M, Głomb P, Grabowski B, Cholewa M. Blood Stain Classification with Hyperspectral Imaging and Deep Neural Networks. Sensors. 2020;20(22):1–24. Available from: https://doi.org/10.3390/s20226666
  7. Butt MHF, Ayaz H, Ahmad M, Li JP, Kuleev R. A Fast and Compact Hybrid CNN for Hyperspectral Imaging-based Bloodstain Classification. In: 2022 IEEE Congress on Evolutionary Computation (CEC). Padua, Italy, 18-23 July 2022. IEEE. p. 1–8.
  8. Cao Z, Li X, Jianfeng J, Zhao L. 3D convolutional siamese network for few-shot hyperspectral classification. Journal of Applied Remote Sensing. 2020;14(04). Available from: https://doi.org/10.1117/1.JRS.14.048504
  9. Wang W, Dou S, Jiang Z, Sun L. A Fast Dense Spectral–Spatial Convolution Network Framework for Hyperspectral Images Classification. Remote Sensing. 2018;10(7):1–19. Available from: https://doi.org/10.3390/rs10071068
  10. Xu H, Yao W, Cheng L, Li B. Multiple Spectral Resolution 3D Convolutional Neural Network for Hyperspectral Image Classification. Remote Sensing. 2021;13(7):1–21. Available from: https://doi.org/10.3390/rs13071248
  11. Anand R, Veni S, Aravinth J. Robust Classification Technique for Hyperspectral Images Based on 3D-Discrete Wavelet Transform. Remote Sensing. 2021;13(7):1–19. Available from: https://doi.org/10.3390/rs13071255
  12. Xu J, Zhao J, Liu C. An Effective Hyperspectral Image Classification Approach Based on Discrete Wavelet Transform and Dense CNN. IEEE Geoscience and Remote Sensing Letters. 2022;19:1–5. Available from: https://ieeexplore.ieee.org/document/9792310
  13. Romaszewski M, Głomb P, Sochan A, Cholewa M. A dataset for evaluating blood detection in hyperspectral images. Forensic Science International. 2021;320:110701. Available from: https://doi.org/10.1016/j.forsciint.2021.110701


© 2023 Sheth & Shah. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Published By Indian Society for Education and Environment (iSee)


Subscribe now for latest articles and news.