Predictive Uncertainty Estimation for Camouflaged Object Detection.

Uncertainty is inherent in machine learning methods, especially those for camouflaged object detection aiming to finely segment the objects concealed in background. The strong enquote center bias of the training dataset leads to models of poor generalization ability as the models learn to find camouflaged objects around image center, which we define as enquote model bias. Further, due to the similar appearance of camouflaged object and its surroundings, it is difficult to label the accurate scope of the camouflaged object, especially along object boundaries, which we term as enquote data bias. To effectively model the two types of biases, we resort to uncertainty estimation and introduce predictive uncertainty estimation technique, which is the sum of model uncertainty and data uncertainty, to estimate the two types of biases simultaneously. Specifically, we present a predictive uncertainty estimation network (PUENet) that consists of a Bayesian conditional variational auto-encoder (BCVAE) to achieve predictive uncertainty estimation, and a predictive uncertainty approximation (PUA) module to avoid the expensive sampling process at test-time. Experimental results show that our PUENet achieves both highly accurate prediction, and reliable uncertainty estimation representing the biases within both model parameters and the datasets.

Designing Two Secure Keyed Hash Functions Based on Sponge Construction and the Chaotic Neural Network.

In this paper, we propose, implement, and analyze the structures of two keyed hash functions using the Chaotic Neural Network (CNN). These structures are based on Sponge construction, and they produce two variants of hash value lengths, i.e., 256 and 512 bits. The first structure is composed of two-layered CNN, while the second one is formed by one-layered CNN and a combination of nonlinear functions. Indeed, the proposed structures employ two strong nonlinear systems, precisely a chaotic system and a neural network system. In addition, the proposed study is a new methodology of combining chaotic neural networks and Sponge construction that is proved secure against known attacks. The performance of the two proposed structures is analyzed in terms of security and speed. For the security measures, the number of hits of the two proposed structures doesn't exceed 2 for 256-bit hash values and does not exceed 3 for 512-bit hash values. In terms of speed, the average number of cycles to hash one data byte (NCpB) is equal to 50.30 for Structure 1, and 21.21 and 24.56 for Structure 2 with 8 and 24 rounds, respectively. In addition, the performance of the two proposed structures is compared with that of the standard hash functions SHA-3, SHA-2, and with other classical chaos-based hash functions in the literature. The results of cryptanalytic analysis and the statistical tests highlight the robustness of the proposed keyed hash functions. It also shows the suitability of the proposed hash functions for the application such as Message Authentication, Data Integrity, Digital Signature, and Authenticated Encryption with Associated Data.

Comparative Study of Three Steganographic Methods Using a Chaotic System and Their Universal Steganalysis Based on Three Feature Vectors.

In this paper, we firstly study the security enhancement of three steganographic methods by using a proposed chaotic system. The first method, namely the Enhanced Edge Adaptive Image Steganography Based on LSB Matching Revisited (EEALSBMR), is present in the spatial domain. The two other methods, the Enhanced Discrete Cosine Transform (EDCT) and Enhanced Discrete Wavelet transform (EDWT), are present in the frequency domain. The chaotic system is extremely robust and consists of a strong chaotic generator and a 2-D Cat map. Its main role is to secure the content of a message in case a message is detected. Secondly, three blind steganalysis methods, based on multi-resolution wavelet decomposition, are used to detect whether an embedded message is hidden in the tested image (stego image) or not (cover image). The steganalysis approach is based on the hypothesis that message-embedding schemes leave statistical evidence or structure in images that can be exploited for detection. The simulation results show that the Support Vector Machine (SVM) classifier and the Fisher Linear Discriminant (FLD) cannot distinguish between cover and stego images if the message size is smaller than 20% in the EEALSBMR steganographic method and if the message size is smaller than 15% in the EDCT steganographic method. However, SVM and FLD can distinguish between cover and stego images with reasonable accuracy in the EDWT steganographic method, irrespective of the message size.

NIQSV+: A No-Reference Synthesized View Quality Assessment Metric.

Benefiting from multi-view video plus depth and depth-image-based-rendering technologies, only limited views of a real 3-D scene need to be captured, compressed, and transmitted. However, the quality assessment of synthesized views is very challenging, since some new types of distortions, which are inherently different from the texture coding errors, are inevitably produced by view synthesis and depth map compression, and the corresponding original views (reference views) are usually not available. Thus the full-reference quality metrics cannot be used for synthesized views. In this paper, we propose a novel no-reference image quality assessment method for 3-D synthesized views (called NIQSV+). This blind metric can evaluate the quality of synthesized views by measuring the typical synthesis distortions: blurry regions, black holes, and stretching, with access to neither the reference image nor the depth map. To evaluate the performance of the proposed method, we compare it with four full-reference 3-D (synthesized view dedicated) metrics, five full-reference 2-D metrics, and three no-reference 2-D metrics. In terms of their correlations with subjective scores, our experimental results show that the proposed no-reference metric approaches the best of the state-of-the-art full reference and no-reference 3-D metrics; and outperforms the widely used no-reference and full-reference 2-D metrics significantly. In terms of its approximation of human ranking, the proposed metric achieves the best performance in the experimental test.

Joint source-channel coding: secured and progressive transmission of compressed medical images on the Internet.

The joint source-channel coding system proposed in this paper has two aims: lossless compression with a progressive mode and the integrity of medical data, which takes into account the priorities of the image and the properties of a network with no guaranteed quality of service. In this context, the use of scalable coding, locally adapted resolution (LAR) and a discrete and exact Radon transform, known as the Mojette transform, meets this twofold requirement. In this paper, details of this joint coding implementation are provided as well as a performance evaluation with respect to the reference CALIC coding and to unequal error protection using Reed-Solomon codes.