دانلود رایگان مقاله درباره ارزش اعتبار تصویر دیجیتال

Abstract

Digital images are facing a crisis of trustworthiness with the emergence of various digital image processing and steganography tools. This paper proposes a novel approach that can evaluate the trustworthiness of a digital image. In this approach, an information fusion method is used to combine base digital image forensic models at the feature level and the decision level. When using different kinds of base forensic models to get supporting evidence for different kinds of digital image manipulations, there exist uncertainties introduced by base forensic models and conflicts among evidence provided by different forensic models. We use the Dempster-Shafer (D-S) evidence theory and an improved least square method to tolerate the uncertainties of forensic models and reduce the evidence conflicts. The lower and upper limits of digital image trustworthiness can then be reliably evaluated by the D-S theory. Three information fusion models based on the D-S theory are proposed. The first model uses the D-S theory at the feature fusion level. The second uses the D-S theory at the decision fusion level, where an improved least square method is designed to reduce the evidence conflicts. The last model is a combination of the first and the second one, where the D-S theory is applied at both the feature fusion and decision fusion levels. Experiments are carried out on four kinds of digital image manipulations. The experimental results show that the three proposed models are very stable in evaluating different kinds of natural images and tampering images. While the first model can only give the upper limit of the trustworthiness of a digital image, the second and the third one can give both lower and upper limits of the trustworthiness of a digital image, as well as the uncertainties of the evidence produced by base forensics models. Compared with the second model, the third one can further reduce the uncertainties. The experimental results also show that when a digital image undergoes many kinds of manipulations, our models can validly compute a soft degree to measure the trustworthiness of the image, while current ordinary digital image forensic models may fail to predict it correctly. Experimental results also demonstrate that the proposed digital image trustworthiness evaluation models can be adapted as digital image forensic classification models with very high detection accuracy.

5. Conclusions and future work

Digital images are facing a crisis of trustworthiness. This paper proposed a method to evaluate digital image trustworthiness. Our method is different from existing digital image forensics as our method does not need the help of digital watermarking or image hash. We proposed three models based on the D-S evidence theory and data fusion. Among them, DSTM1 directly uses the D-S theory to evaluate the Pl value of trustworthiness, and uses the feature combinations to resolve the problem of evidence combinations. DSTM2 uses the least square method to compute the evidence matrix before directly using the Dempster’s rule of combination. The uncertainty degree can also be evaluated in this model. DSTM3 is a combination of DSTM1 and DSTM2. Compared to DSTM2, DSTM3 improves the evaluation reliability, and also greatly reduces the uncertainty by using the feature combination method. Simulation results have shown that the three models are effective in evaluating trustworthiness of digital images. The main contributions of this work are summarized as follows: 1 We proposed a new approach that can measure the trustworthiness of a digital image. The trustworthiness of a digital image is a reference value to tell the degree of trustworthiness of the image based on the trustworthiness evaluation indexes a user selected according to her application requirements. Typical application scenarios include online digital image retrieval, image fusion, online social network digital image sharing, etc. To the best of our knowledge, our work is the first research on how to measure the trustworthiness of digital images in a quantitative way. 2 We proposed three digital image trustworthiness evaluation models based on information fusion for measuring the trustworthiness of a digital image. Experimental results demonstrated that the three models are reliable and effective in evaluating the trustworthiness of natural images. 3 We applied the D-S theory at the feature fusion level, the decision fusion level, and the combination level of feature fusion and decision fusion, respectively, to calculate the trustworthiness value of a digital image, and at the same time compute the uncertainties introduced by base forensic models. In addition, an improved least square method was proposed (in the second and third models) to reduce conflicts among forensic evidence provided by different forensic models.