Search

A recently modern stochastic optimization algorithm has been developed by observing the life of slime mold physarum polycephalum in nature. The algorithm is called the slime mold algorithm (SMA) with an excellent exploratory capacity and exploitation inclination. Still, slipping into optimal local is easy to happen and slowly converges speed while dealing with complicated problems. This article proposes a new process of improving SMA (namely ISMA) by adapting the weight coefficient and cooperating the reverse learning strategy in the expression of agents updating locations to enhance the algorithm's optimization performance. Many selected benchmark functions and the optimal operation of cascade reservoirs are applied to evaluate the performance of the proposed algorithm. Comparisons of the proposed approach's results with the various algorithms under the case situations show that the recommended solution produces better performance than the different competing algorithms.

Most existing AMBTC (absolute moment block truncation coding)-based reversible data hiding (RDH) schemes cannot be decoded by traditional AMBTC decoders, because they change the coding structure of the AMBTC compressed code stream, which is unidentified for decoders. Even if some AMBTC-based RDH methods can be decoded by traditional AMBTC decoders, but the obtained payload is low. To this end, in this paper, a high-capacity and decodable AMBTC-based RDH scheme is presented. It is well observed that an m × n-sized bitmap has 2m×n combinations of `1' and `0'. However, all the bitmaps of an image occupy only a small part of all the combinations, and a large part are not used in this image. Motivated by this observation, we propose a one-to-many map between the used and unused combinations, in which one used bitmap can be mapped to multiple unused combinations, achieving high payloads (e.g., log2 25 bits for one bitmap of Lena), and more importantly, completely reserving the coding structure of the AMBTC-compressed code. Unlike existing decodable AMBTC-based RDH methods only capable of achieving a fixed payload for one test image, our method can adjust adaptively payloads according to the required visual quality by introducing a predefined threshold. The experimental results also demonstrate that our proposed scheme can largely increase the payload on the basis of maintaining good visual quality.

In Malik et al.'s method, each pixel can be embedded with log23 bits by being modified at most 1. Thus, their method achieves significant hiding capacity while maintaining good visual quality. However, in their method, the first lower and the first upper quantization levels must be excluded from data embedding in order to ensure reversibility. To this end, we propose a two-layer reversible data hiding (RDH) scheme in combination with (7,4) Hamming code. In the 1st-layer embedding, each block can be embedded with 16 bits. In the 2nd-layer embedding, each already-modified block can carry 6 bits or 12 bits by taking advantage of (7,4) Hamming code that hides three bits by modifying only one bit. At most 2-bit additional information is needed to help decoders to correctly extract the original lower and upper quantization levels. By means of two-layer embedding, our method achieves higher embedding capacity while maintaining almost the same visual quality, compared with Malik et al.'s method. Experimental results also demonstrate our effectivity.

The main purpose of data hiding is to hide secret data imperceptibly into multimedia, ensuring secure data transmission. Existing magic matrix-based data hiding schemes cannot achieve satisfactory visual quality for a given low payload because they adopt a single-layer embedding (i.e., the fixed-sized reference matrix (RM) embedding), rather than adaptive multi-layer embedding (i.e., variable-sized RM embedding). To this end, we propose an adaptive data hiding scheme by constructing multi-layer RM using mini-Sudoku. Our scheme can adjust the number of layers (e.g., one, two, or more) of the RM to obtain the desired payload (i.e., low, moderate, or large payloads). In addition, our method also has the capability of obtaining the optimal number of layers of RM achieving the highest visual quality for a given payload. For each pixel pair, our scheme selects the optimal pair having the smallest Euclidean distance with this pair as its stego pair, resulting in a large decrease in distortion. Experimental results show that our proposed scheme can obtain various payloads, and more importantly, it can achieve better or comparable rate-distortion performance than several existing magic matrix-based data hiding schemes.

Neural style transfer recently has become one of the most popular topics in academic research and industrial application. The existing methods can generate synthetic images by transferring different styles of some images to another given content images, but they mainly focus on learning low-level features of images with losses of content and style, leading to greatly alter the salient information of content images in the semantic level. In this paper, an improved scheme is proposed to keep the salient regions of the transferred image the same with that of content image. By adding the region loss calculated from a localization network, the synthetic image can almost keep the main salient regions consistent with that of original content image, which helps for saliency-based tasks such as object localization and classification. In addition, the transferred effect is more natural and attractive, avoiding simple texture overlay of the style image. Furthermore, our scheme can also extend to remain other semantic information (such as shape, edge, and color) of the image with the corresponding estimation networks.

K-pass pixel value ordering (PVO) is an effective reversible data hiding (RDH) technique. In k-pass PVO, the complexity measurement may lead to a weak estimation result because the unaltered pixels in a block are excluded to estimate block complexity. In addition, the prediction-error is computed without considering the location relationship of the second largest and largest pixels or the second smallest and smallest pixels. To this end, an improved RDH technique is proposed in this paper to enhance the embedding performance. The improvement mainly lies in the following two aspects. First, some pixels in a block, which are excluded from data hiding in some existing RDH methods, are exploited together with the neighborhood surrounding this block to increase the estimation accuracy of local complexity. Second, the remaining pixels in a block, i.e., three largest and three smallest pixels are involved in data embedding. Taking three largest pixels for example, when the difference between the largest and third largest pixels is relatively large (e.g., > 1), we improve k-pass PVO by considering the location relationship of the second largest and largest pixels. The advantage of doing this is that the difference valued 3 between the maximum and the second largest pixel which is shifted in k-pass PVO, is able to carry 1 bit data in our method. In other words, a larger amount of pixels are able to carry data bits in our scheme compared with k-pass PVO. Abundant experimental results reveal that the proposed method achieves preferable embedding performance compared with the previous work, especially when a larger payload is required.

Image colorization is a creative process of reasonably adding colors on gray-scale images to generate well-pleasing colorized images. The existing colorization methods normally require user-supplied hints of color points and doodles, or handpicked color reference images for transferring colors, or diverse color images for predicting the colorized results; but the final colorized results generated by most of them may seem unnatural as a consequence of the unprofessional users' skills, inaccurately color transferring, or limited scale of color image collection. To overcome these limitations, a hybrid scheme consisting of two modules is proposed for images' region colorization by combining semantic segmentation and seamless fusion techniques in this paper. In the first module, the masks and category of input image's regions and background are derived from a Mask R-CNN model, and the corresponding reference images of each region are selected from a pre-classified color image database. In the second module, the background and various regions of an image are colorized by a U-Net model and a VGG model respectively. Then, the Poisson editing technique is applied for fusing all the colorized results to generate the final whole colorized image. The experiments show that our scheme can not only flexibly select the appropriate reference images for different regions of the image according their semantic information, but also effectively merge colorized results to generate a plausible colorful image. By reasonably combining different CNN-based models according to their superiority, our scheme avoids the limitation of failures caused by single-step methods, and achieves richer artistic visual effect compared with other existing methods.

After conducting deep research on all existing reversible data hiding (RDH) methods based on Alattar’s integer transform, we discover that the frequently-used method in obtaining the difference value list of an image block may lead to high embedding distortion. To this end, we propose an improved Alattar’s transform-based-RDH-method. Firstly, the irregular block partition method which makes full use of high correlation between two neighboring pixels is proposed to increase the embedding performance. Specifically, each image block is composed of a center pixel and several pixels surrounding this center pixel. Thus, the difference value list is created by using the center pixel to predict each pixel surrounding it. Since the center pixel is highly related to each pixel surrounding it, a sharp difference value histogram is generated. Secondly, the mean value of an image block in Alattar’s integer transform has embedding invariance property, and therefore, it can be used for increasing the estimation performance of a block’s local complexity. Finally, two-layer embedding is combined into our scheme in order to optimize the embedding performance. Experimental results show that our method is effective.

This paper proposes a joint coding and reversible data hiding method for absolute moment block truncation coding (AMBTC) compressed images. Existing methods use a predictor to predict the quantization levels of AMBTC codes. Equal-length indicators, secret bits and prediction errors are concatenated to construct the output code stream. However, the quantization levels might not highly correlate with their neighbors for predictive coding, and the use of equal-length indicators might impede the coding efficiency. The proposed method uses reversible integer transform to represent the quantization levels by their means and differences, which is advantageous for predictive coding. Moreover, the prediction errors are better classified into symmetrical encoding cases using the adaptive classification technique. The length of indicators and the bits representing the prediction errors are properly assigned according to the classified results. Experiments show that the proposed method offers the lowest bitrate for a variety of images when compared with the existing state-of-the-art works.

Passive video forensics has drawn much attention in recent years. However, research on detection of object-based forgery, especially for forged video encoded with advanced codec frameworks, is still a great challenge. In this paper, we propose a deep learning-based approach to detect object-based forgery in the advanced video. The presented deep learning approach utilizes a convolutional neural network (CNN) to automatically extract high-dimension features from the input image patches. Different from the traditional CNN models used in computer vision domain, we let video frames go through three preprocessing layers before being fed into our CNN model. They include a frame absolute difference layer to cut down temporal redundancy between video frames, a max pooling layer to reduce computational complexity of image convolution, and a high-pass filter layer to enhance the residual signal left by video forgery. In addition, an asymmetric data augmentation strategy has been established to get a similar number of positive and negative image patches before the training. The experiments have demonstrated that the proposed CNN-based model with the preprocessing layers has achieved excellent results.