20 June 2019 in IEEE Transactions on Circuits and Systems for Video Technology
Considering that traditional image steganography technologies suffer from the potential risk of failure under lossy channels, an enhanced adaptive steganography with multiple robustness against image processing attacks is proposed, while maintaining good detection resistance. First, a robust domain constructing method is proposed utilizing robust element extraction and optimal element modification, which can be applied to both spatial and JPEG images. Then, a robust steganography is proposed based on “Robust Domain Constructing + RS-STC Codes„, combined with cover selection, robust cover extraction, message coding and embedding with minimized costs. In addition, to provide a theoretical basis for message extraction integrity, the fault tolerance of the proposed algorithm is deduced using error model based on burst errors and decoding damage. Finally, on the basis of parameter discussion about robust domain construction, performance experiments are conducted, and the recommended coding parameters are given for lossy channels with different attacks using the analytic results for fault tolerance. A series of experimental results demonstrate that the proposed algorithm can extract embedded messages with significantly higher accuracy after different attacks, such as compression, noising, scaling and other attacks, compared with state-of-theart adaptive steganography and robust watermarking algorithms, while maintaining good detection resistant performance.
24 March 2020 in International Journal of Computer Vision
10 January 2018 in IEEE Access
A great number of studies show that considering information from multiple views results in better performance than their single-view counterparts. However, many previous works aiming to improve classification performance fail to effectively tackle the inter-view correlation or the intra-class variability. Analysis dictionary learning (ADL) has theoretic significance and practical potential in classification tasks. Based on the ADL, this paper proposes a new method, namely, multi-view analysis dictionary learning (MvADL) for image classification. Specifically, multi-view analysis dictionaries are designed to reduce the intra-class variability in the transformed space in the multi-view scenario. Then, a marginalized classification term is incorporated to integrate the semantic information into the basic dictionary learning model. In the marginalized classification term, a marginalized target learning strategy is applied to improve the flexibility and discriminability of the whole model. Besides, an iteratively optimizing algorithm is designed to solve the proposed MvADL. Experiments on benchmark data sets demonstrate the superiority of our proposed method.
19 December 2016 in IEEE Transactions on Systems, Man, and Cybernetics: Systems
The task of semantic segmentation is to infer a predefined category label for each pixel in the image. For most cases, image segmentation is established as a fully supervised task. These methods all built on the basis of having access to sufficient pixel-wise annotated samples for training. However, obtaining the satisfied ground truth is not only labor intensive but also time-consuming, which severely hinders the generality of these fully supervised methods. Instead of pixel-level ground truth, weakly supervised approaches learn their models from much less prior information, e.g., image-level annotation. In this paper, we propose a novel conditional random field (CRF) based framework for weakly supervised semantic segmentation. Enlightened by jigsaw puzzles, we start the approach with merging superpixels from an image into larger pieces by a newly designed strategy. Then pieces from all the training images are gathered and associated with appropriate semantic labels by CRF. Thus, the piece library is constructed, achieving remarkable universality and flexibility. In the case of testing, we compare the superpixels with image pieces in the library and assign them the labels that minimize the potential energy. In addition, the proposed framework is fit for domain adaption and obtains promising results, which is of great practical value. Extensive experimental results on PASCAL VOC 2007, MSRC-21, and VOC 2012 databases demonstrate that our framework outperforms or is comparable to state-of-the-art segmentation methods.
29 August 2018 in IEEE Transactions on Multimedia
Semantic image segmentation can be accomplished by assigning a proper object category label to each meaningful region of an image. Beyond the original bottom-up models, the use of top-down categorization information has been applied to semantic segmentation to improve performance. An excellent example of such a top-down scheme is to integrate a Conditional Random Field (CRF) model with sparse dictionary learning. However, the existing solutions merely consider the discrimination of dictionaries to obtain better sparse codes, without considering the inherent data locality characteristics. In this paper, we explore such characteristics and propose a novel semantic segmentation framework based on an innovative CRF model with locality-consistent dictionary learning. In particular, we propose two new locality-consistent dictionary learning strategies by capturing the local consistencies in the feature space and the label space. In addition, we develop a joint dictionary and a CRF model parameter learning algorithm to seamlessly integrate the proposed locality-consistent dictionary learning strategies into the CRF model. Extensive experiments are conducted with two popular databases of different traits (i.e., Graz-02 and PASCAL-CONTEXT). The simulation results confirm the efficiency of the proposed scheme, especially when training data is limited.
20 February 2019 in IEEE Access
!The mainstream adaptive steganography algorithm is difficult to resist scaling attack, and the anti-detection performance of the algorithm based on quantization index modulation is not high enough. To solve the above problems, this paper proposes a spatial image adaptive steganography algorithm based on Zernike moment to resist scaling attack and statistic detection. First, the Zernike moment of the normalized cover image is extracted and the new cover is obtain by dither modulation algorithm. Second, the minimized distortion embedding is realized by S-UNIWARD and STCs coded. And finally the stego image is generated by change the original Zernike moment according to the modified amplitude of the new cover. Experimental results show that the proposed algorithm is robust to the three common scaling attacks, and the message extraction error rate is significantly lower than the S-UNIWARD steganography after the scaling attacks; compared with the steganography algorithm based on quantization index modulation, the proposed algorithm has higher detection resistance.