Abstract
Due to the increased online activity, people of all ages, especially adolescents, may get exposed to objectionable image content such as internet pornography. These images are spread quickly and widely over the internet, which causes serious social problems. Many researchers have proposed objectionable image content classification models by utilizing deep neural networks to prevent such images from being retrieved while surfing the web. The performance of such models can be enhanced by the semi-supervised learning method by effectively utilizing the image data from an overwhelming number of unlabeled objectionable samples. For many such unlabeled objectionable images, this paper proposes a semi-supervised image content classification framework using a balanced sample inclusion mechanism based on a higher class probability outcome to include the pseudo labels effectively in the existing model. The proposed framework fully utilizes semi-supervised learning and gradually improves model classification accuracy and reliability.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Jevremovic, A., Veinovic, M., Cabarkapa, M., Krstic, M., Chorbev, I., Dimitrovski, I., Garcia, N., Pombo, N., Stojmenovic, M.: Keeping children safe online with limited resources: analyzing what is seen and heard. IEEE Access 9, 132, 723–132, 732 (2021). https://doi.org/10.1109/ACCESS.2021.3114389
Chen, J., Liang, G., He, W., Xu, C., Yang, J., Liu, R.: A pornographic images recognition model based on deep one-class classification with visual attention mechanism. IEEE Access 8, 122, 709–122, 721 (2020). https://doi.org/10.1109/ACCESS.2020.2988736
Brown, J.D., L’Engle, K.L.: X-Rated: Sexual attitudes and behaviors associated with U.S. early adolescents’ exposure to sexually explicit media. Commun. Res. 36(1), 129–151 (2009). https://doi.org/10.1177/0093650208326465
Ybarra, M.L., Strasburger, V.C., Mitchell, K.J.: Sexual media exposure, sexual behavior, and sexual violence victimization in adolescence. Clin. Pediatr. 53(13), 1239–1247 (2014). https://doi.org/10.1177/0009922814538700
Cohen-Almagor, R.: Online child sex offenders: challenges and counter-measures. Howard J. Crim. Justice 52(2), 190–215 (2013). https://doi.org/10.1111/hojo.12006
Ybarra, M.L., Mitchell, K.J., Hamburger, M., Diener-West, M., Leaf, P.J.: X-rated material and perpetration of sexually aggressive behavior among children and adolescents: is there a link? Aggressive Behavior 37(1) (2011). 10.1002/ab.20367
Lee, J.S., Kuo, Y.M., Chung, P.C., Chen, E.L.: Naked image detection based on adaptive and extensible skin color model. Pattern Recognit. 40(8), 2261–2270 (2007). https://doi.org/10.1016/j.patcog.2006.11.016
Zhu, H., Zhou, S., Wang, J., Yin, Z.: An algorithm of pornographic image detection. In: Fourth International Conference on Image and Graphics (ICIG 2007), pp. 801–804 (2007). https://doi.org/10.1109/ICIG.2007.29
Yan, C.C., Liu, Y., Xie, H., Liao, Z., Yin, J.: Extracting salient region for pornographic image detection. J. Vis. Commun. Image Represent. 25(5), 1130–1135 (2014). https://doi.org/10.1016/j.jvcir.2014.03.005
Srisaan, C.: A classification of internet pornographic images. Int. J. Electron. Commer. Stud. 7(1), 95–104 (2016). https://doi.org/10.7903/ijecs.1408
Zhuo, L., Geng, Z., Zhang, J., Li, X.G.: ORB feature based web pornographic image recognition. Neurocomputing 173, 511–517 (2016). https://doi.org/10.1016/j.neucom.2015.06.055
Zhang, F., Wu, T.Y., Zheng, G.: Video salient region detection model based on wavelet transform and feature comparison. EURASIP J. Image Vid. Process. 2019(1), 58 (2019). https://doi.org/10.1186/s13640-019-0455-2
Zhang, Y.J., Chen, J.Y., Lu, Z.M.: Face anti-spoofing detection based on color texture structure analysis. J. Netw. Intell. 7(2), 319–331 (2022)
Huu, P.N., Tien, D.N., Manh, K.N.: Action recognition application using artificial intelligence for smart social surveillance system. J. Inf. Hiding Multimed. Signal Process. 13(1), 1–11 (2022)
Kumar, S., Damaraju, A., Kumar, A., Kumari, S., Chen, C.M.: LSTM network for transportation mode detection. J. Internet Technol. 22(4), 891–902 (2021)
Gao, J., Zou, H., Zhang, F., Wu, T.Y.: An intelligent stage light-based actor identification and positioning system. Int. J. Inf. Comput. Secur. 18(1–2), 204–218 (2022). https://doi.org/10.1504/IJICS.2022.122920
Zhang, F., Wu, T.Y., Pan, J.S., Ding, G., Li, Z.: Human motion recognition based on SVM in VR art media interaction environment. Hum.-Centric Comput. Inf. Sci. 9(1), 40 (2019). https://doi.org/10.1186/s13673-019-0203-8
Wang, R.B., An, Z.W., Wang, W.F., Yin, S., Xu, L.: A multi-stage data augmentation approach for imbalanced samples in image recognition. J. Netw. Intell. 6(1), 94–106 (2021)
Tawfeeq, L.A., Hussein, S.S.: Predication of most significant features in medical image by utilized CNN and heatmap. J. Inf. Hiding Multimed. Signal Process. 12(4), 217–225 (2021)
Yan, H.: Detect and depornize pornographic images using pre-trained CNN models. In: 2020 International Conference on Computing and Data Science (CDS), pp. 48–51 (2020). https://doi.org/10.1109/CDS49703.2020.00017
Cheng, F., Wang, S.L., Wang, X.Z., Liew, A.W.C., Liu, G.S.: A global and local context integration DCNN for adult image classification. Pattern Recognit. 96, 106, 983 (2019). https://doi.org/10.1016/j.patcog.2019.106983
Nian, F., Li, T., Wang, Y., Xu, M., Wu, J.: Pornographic image detection utilizing deep convolutional neural networks. Neurocomputing 210, 283–293 (2016). https://doi.org/10.1016/j.neucom.2015.09.135
Shen, R., Zou, F., Song, J., Yan, K., Zhou, K.: EFUI: an ensemble framework using uncertain inference for pornographic image recognition. Neurocomputing 322, 166–176 (2018). https://doi.org/10.1016/j.neucom.2018.08.080
Lin, X., Qin, F., Peng, Y., Shao, Y.: Fine-grained pornographic image recognition with multiple feature fusion transfer learning. Int. J. Mach. Learn. Cybern. 12(1), 73–86 (2021). https://doi.org/10.1007/s13042-020-01157-9
Dong, Z., Chen, Z.: Semi-supervised cell classification based on deep learning. In: The 6th International Conference on Control Engineering and Artificial Intelligence, CCEAI 2022, pp. 49–52. Association for Computing Machinery, New York, NY, USA (2022). https://doi.org/10.1145/3522749.3523086
Wu, M.E., Syu, J.H., Chen, C.M.: Kelly-based options trading strategies on settlement date via supervised learning algorithms. Comput. Econ. 59(4), 1627–1644 (2022). https://doi.org/10.1007/s10614-021-10226-2
Zeng, X., Martinez, T.R.: Distribution-balanced stratified cross-validation for accuracy estimation. J. Exp. Theor. Artif. Intell. 12(1), 1–12 (2000). https://doi.org/10.1080/095281300146272
Tseng, K.K., Zhang, R., Chen, C.M., Hassan, M.M.: DNetUnet: a semi-supervised CNN of medical image segmentation for super-computing AI service. J. Supercomput. 77(4), 3594–3615 (2021). https://doi.org/10.1007/s11227-020-03407-7
Yu, G., Sun, K., Xu, C., Shi, X.H., Wu, C., Xie, T., Meng, R.Q., Meng, X.H., Wang, K.S., Xiao, H.M., Deng, H.W.: Accurate recognition of colorectal cancer with semi-supervised deep learning on pathological images. Nat. Commun. 12(1), 6311 (2021). https://doi.org/10.1038/s41467-021-26643-8
Rubin, M., Stein, O., Turko, N.A., Nygate, Y., Roitshtain, D., Karako, L., Barnea, I., Giryes, R., Shaked, N.T.: TOP-GAN: stain-free cancer cell classification using deep learning with a small training set. Med. Image Anal. 57, 176–185 (2019). https://doi.org/10.1016/j.media.2019.06.014
Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2261–2269 (2017). https://doi.org/10.1109/CVPR.2017.243
Bisong, E.: Google Colaboratory. Building Machine Learning and Deep Learning Models on Google Cloud Platform, pp. 59–64 (2019). https://doi.org/10.1007/978-1-4842-4470-8_7
Acknowledgements
The work was supported by the Council of Scientific and Industrial Research (CSIR), Ministry of Science and Technology, Govt. of India (Sanction No.: 22(0836)/20/EMR-II).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Mondal, S., Pal, A.K., Islam, S.H., Samanta, D. (2023). Objectionable Image Content Classification Using CNN-Based Semi-supervised Learning. In: Ni, S., Wu, TY., Geng, J., Chu, SC., Tsihrintzis, G.A. (eds) Advances in Smart Vehicular Technology, Transportation, Communication and Applications. Smart Innovation, Systems and Technologies, vol 347. Springer, Singapore. https://doi.org/10.1007/978-981-99-0848-6_23
Download citation
DOI: https://doi.org/10.1007/978-981-99-0848-6_23
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-0847-9
Online ISBN: 978-981-99-0848-6
eBook Packages: EngineeringEngineering (R0)