Abstract Unlike single-image steganography, the scheme of payload distribution on different images plays a pivotal role in the security performance of multi-image steganography. In this paper, a novel multi-image steganography scheme: image stitching sender (ISS) is proposed, which achieves optimal payload distribution by optimizing the stitching scheme of multi-cover-images. In the ISS scheme, we employ peak signal-to-noise ratio as the similarity evaluation metric for the stitched cover image and stego image. Besides, genetic algorithm is used to find the local optimal solution for the similarity, corresponding to a locally optimal multi-image steganographic stitching scheme. The experiment demonstrates that ISS exhibits enhanced anti-detection capabilities in comparison to other multi-image steganography schemes. Furthermore, when combined with non-additive embedding methods, the ISS can achieve a more substantial improvement in security compared to additive embedding methods.

In this article, we investigate the cross-media retrieval between images and text, that is, using image to search text (I2T) and using text to search images (T2I). Existing cross-media retrieval methods usually learn one couple of projections, by which the original features of images and text can be projected into a common latent space to measure the content similarity. However, using the same projections for the two different retrieval tasks (I2T and T2I) may lead to a tradeoff between their respective performances, rather than their best performances. Different from previous works, we propose a modality-dependent cross-media retrieval (MDCR) model, where two couples of projections are learned for different cross-media retrieval tasks instead of one couple of projections. Specifically, by jointly optimizing the correlation between images and text and the linear regression from one modal space (image or text) to the semantic space, two couples of mappings are learned to project images and text from their original feature spaces into two common latent subspaces (one for I2T and the other for T2I). Extensive experiments show the superiority of the proposed MDCR compared with other methods. In particular, based on the 4,096-dimensional convolutional neural network (CNN) visual feature and 100-dimensional Latent Dirichlet Allocation (LDA) textual feature, the mAP of the proposed method achieves the mAP score of 41.5%, which is a new state-of-the-art performance on the Wikipedia dataset.

Independent component analysis with soft reconstruction cost (RICA) has been recently proposed to linearly learn sparse representation with an overcomplete basis, and this technique exhibits promising performance even on unwhitened data. However, linear RICA may not be effective for the majority of real-world data because nonlinearly separable data structure pervasively exists in original data space. Meanwhile, RICA is essentially an unsupervised method and does not employ class information. Motivated by the success of the kernel trick that maps a nonlinearly separable data structure into a linearly separable case in a high-dimensional feature space, we propose a kernel RICA (kRICA) model to nonlinearly capture sparse representation in feature space. Furthermore, we extend the unsupervised kRICA to a supervised one by introducing a class-driven discrimination constraint, such that the data samples from the same class are well represented on the basis of the corresponding subset of basis vectors. This discrimination constraint minimizes inhomogeneous representation energy and maximizes homogeneous representation energy simultaneously, which is essentially equivalent to maximizing between-class scatter and minimizing within-class scatter at the same time in an implicit manner. Experimental results demonstrate that the proposed algorithm is more effective than other state-of-the-art methods on several datasets.

In this paper, we propose a cross-media regularization framework to enhance image understanding which can benefit image retrieval, classification and so on. The goal of cross-media regularization is to find regularization projections by exploiting the correlations between visual features and textual features. Thus, the original noisy distribution of visual features can be refined by leveraging the discriminative distribution of the corresponding textual features. Within the proposed cross-media regularization framework, a mid-level representation is built by jointly projecting both visual and textual features into a shared feature subspace, which leads to transferring of the discriminative semantic characteristic embedded in the textual modality into the corresponding visual modality. Meanwhile, the discriminative characteristic of textual features can also be boosted simultaneously. The experimental results demonstrate that the proposed mid-level space learning process can remarkably improve the search quality and outperform the existing semantic regularization methods.

Nonnegative matrix factorization (NMF) is a useful technique to explore a parts-based representation by decomposing the original data matrix into a few parts-based basis vectors and encodings with nonnegative constraints. It has been widely used in image processing and pattern recognition tasks due to its psychological and physiological interpretation of natural data whose representation may be parts-based in human brain. However, the nonnegative constraint for matrix factorization is generally not sufficient to produce representations that are robust to local transformations. To overcome this problem, in this paper, we proposed a topographic NMF (TNMF), which imposes a topographic constraint on the encoding factor as a regularizer during matrix factorization. In essence, the topographic constraint is a two-layered network, which contains the square nonlinearity in the first layer and the square-root nonlinearity in the second layer. By pooling together the structure-correlated features belonging to the same hidden topic, the TNMF will force the encodings to be organized in a topographical map. Thus, the feature invariance can be promoted. Some experiments carried out on three standard datasets validate the effectiveness of our method in comparison to the state-of-the-art approaches.

Independent Component Analysis (ICA) is an effective unsupervised tool to learn statistically independent representations. However, ICA is not only sensitive to whitening but also difficult to learn an over-complete basis set. Consequently, ICA with soft Reconstruction cost(RICA) was presented to learn sparse representations with over-complete basis even on unwhitened data. Nevertheless, this model may not be an optimal discriminative model for classification tasks, because it failed to consider the association between the training sample and its class. In this paper, we propose a supervised Discriminative ICA model with Reconstruction constraint for image classification, named DRICA. DRICA brings in class information to learn the over-complete basis by incorporating inhomogeneous representation cost constraint into the RICA framework. This constraint leads to partition the set of basis vectors into several subsets corresponding to the sample classes, where each subset could sparsely model data samples from the same class but not others. Therefore, the proposed ICA model can learn an over-complete basis and an optimal multi-class classifier jointly. Some experiments carried out on several standard image databases validate the effectiveness of DRICA for image classification.

In this paper, a novel genetic clustering algorithm based on dynamic niching (DNGA) for image segmentation is proposed. It is an effective and robust approach to image segmentation on the basis of a total similarity function relating to the approximate density shape estimation. In the new algorithm, a dynamic identification of the niches is performed at each generation to automatically evolve the proper number of clusters and appropriate cluster centers of the data set. Moreover, a local search method is embeded in the evolutionary process which makes the dynamic niching method insensitive to the radius of the niche. Compared to existing methods, DNGA algorithm does not need to pre-specify the number of segmentation. Several images are used to demonstrate its superiority. The experimental results show that DNGA algorithm has high performance, effectiveness and flexibility.