Abstract
Object content understanding in images and videos draws more and more attention nowadays. However, only few existing methods have addressed the problem of bloody scene detection in images. Along with the widespread popularity of the Internet, violent contents have affected our daily life. In this paper, we propose region-based techniques to identify a color image being bloody or not. Firstly, we have established a new dataset containing 25431 bloody images and 25431 non-bloody images. These annotated images are derived from the Violent Scenes Dataset, a public shared dataset for violent scenes detection in Hollywood movies and web videos. Secondly, we design a bloody image classification method with global visual features using Support Vector Machines. Thirdly, we also construct a novel bloody region identification approach using Convolutional Neural Networks. Finally, comparative experiments show that bloody image classification with local features is more effective.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
We compared all bloody images and non-bloody images in our dataset and found this number is a quite reasonable threshold to distinguish these two kind of images.
- 2.
Normally, an image in TSGF contains mutiple red-like regions. Not all these regions are bloodstain and some are red car, red clothes, red light or human face etc. Thus all extracted red-like regions are mixed together at first and need manual sortation.
- 3.
Height \(\times \) Width.
- 4.
That means the neural network passes through training set for 100 times.
References
Ying-Wei, W., et al.: Bloodstain segmentation in color images. In: Proceedings of the 2011 First International Conference on Robot, Vision and Signal Processing (RVSP 2011), pp. 52–55 (2011)
de Dios, J.J., et al.: Face detection based on a new color space YCgCr. In: Proceedings of the IEEE International Conference on Image Processing, vol. 3, pp. 902–912, September 2003
de Dios, J.J., Garcia, N.: Fast face segmentation in component color space. In: 2004 International Conference on Image Processing (ICIP) (IEEE Cat. No. 04CH37580), vol. 191, pp. 191–194 (2004)
Yoo, S., Park, R.H.: Red-Eye detection and correction using inpainting in digital photographs. IEEE Trans. Consum. Electron. 55(3), 1006–1014 (2009)
Yan, G., et al.: Region-based blood color detection and its application to bloody image filtering. In: Proceedings of 2015 International Conference on Wavelet Analysis and Pattern Recognition (ICWAPR), pp. 45–50 (2015)
Wang, D., et al.: Baseline results for violence detection in still images. In: 2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance (AVSS), pp. 54–57 (2012)
Li, B., Hu, W., Xiong, W., Wu, O., Li, W.: Horror image recognition based on emotional attention. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010. LNCS, vol. 6493, pp. 594–605. Springer, Heidelberg (2011). doi:10.1007/978-3-642-19309-5_46
Guermazi, R., et al.: Violent web images classification based on MPEG7 color descriptors. In: 2009 IEEE International Conference on Systems, Man and Cybernetics, pp. 3106–3111 (2009)
Lopes, A.P.B., et al.: A bag-of-features approach based on Hue-SIFT descriptor for nude detection. In: 2009 17th European Signal Processing Conference (EUSIPCO 2009), pp. 1552–1556 (2009)
Ulges, A., et al.: Automatic detection of child pornography using color visual words. In: 2011 IEEE International Conference on Multimedia and Expo (2011)
Violent Scenes Dataset. http://www.technicolor.com/en/innovation/research-innovation/scientific-data-sharing/violent-scenes-dataset. Accessed 25 May 2016
Demarty, C.H., et al.: VSD, a public dataset for the detection of violent scenes in movies: design, annotation, analysis and evaluation. Multimedia Tools Appl. 74(17), 7379–7404 (2015)
Schedi, M., et al.: VSD2014: a dataset for violent scenes detection in Hollywood movies and web videos. In: 2015 Proceedings of 13th International Workshop on Content-Based Multimedia Indexing (CBMI), p. 6 (2015)
Acar, E., et al.: Detecting violent content in Hollywood movies by mid-level audio representations. In: Czuni, L., Schoffmann, K., Sziranyi, T. (eds.) 2013 11th International Workshop on Content-Based Multimedia Indexing, pp. 73–78 (2013)
Gong, Y., Wang, W., Jiang, S., Huang, Q., Gao, W.: Detecting violent scenes in movies by auditory and visual cues. In: Huang, Y.-M.R., Xu, C., Cheng, K.-S., Yang, J.-F.K., Swamy, M.N.S., Li, S., Ding, J.-W. (eds.) PCM 2008. LNCS, vol. 5353, pp. 317–326. Springer, Heidelberg (2008). doi:10.1007/978-3-540-89796-5_33
Penet, C., et al.: Multimodal information fusion and temporal integration for violence detection in movies. In: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2393–2396 (2012)
Bermejo Nievas, E., Deniz Suarez, O., Bueno García, G., Sukthankar, R.: Violence detection in video using computer vision techniques. In: Real, P., Diaz-Pernil, D., Molina-Abril, H., Berciano, A., Kropatsch, W. (eds.) CAIP 2011. LNCS, vol. 6855, pp. 332–339. Springer, Heidelberg (2011). doi:10.1007/978-3-642-23678-5_39
Deniz, O., et al.: Fast violence detection in video. In: Proceedings of 9th International Conference on Computer Vision Theory and Applications (VISAP 2014), pp. 478–485 (2014)
Zhijie, Y., et al.: Violence detection based on histogram of optical flow orientation. In: Proceedings of the SPIE - The International Society for Optical Engineering (2013)
Wang, X., Han, T.X., Yan, S.: An HOG-LBP human detector with partial occlusion handling. In: Proceedings of IEEE ICCV, September 2009
Chang, C.C., Lin, C.J.: LIBSVM: A Library for Support Vector Machines. In: ACM Trans. Intell. Syst. Technol. 2(3) (2011)
Xu-Cheng, Y., et al.: Shallow classification or deep learning: an experimental study. In: 2014 22nd International Conference on Pattern Recognition (ICPR), pp. 1904–1909 (2014)
MatConvNet: CNNs for MATLAB. http://www.vlfeat.org/matconvnet/. Accessed 25 May 2016
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Chen, SL., Yang, C., Zhu, C., Yin, XC. (2016). Bloody Image Classification with Global and Local Features. In: Tan, T., Li, X., Chen, X., Zhou, J., Yang, J., Cheng, H. (eds) Pattern Recognition. CCPR 2016. Communications in Computer and Information Science, vol 663. Springer, Singapore. https://doi.org/10.1007/978-981-10-3005-5_31
Download citation
DOI: https://doi.org/10.1007/978-981-10-3005-5_31
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-3004-8
Online ISBN: 978-981-10-3005-5
eBook Packages: Computer ScienceComputer Science (R0)