Significant progress is made in the field of object tracking recently. Especially, trackers based on deep learning and correlation filters both have achieved excellent performance. However, object tracking still faces some challenging problems such as deformation and illumination. In such kinds of situations, the accuracy and precision of tracking algorithms plunge as a result. It is imminent to find a solution to this situation. In this paper, we propose a tracking algorithm based on features extracted by residual network called Resnet features and cascaded correlation filters to improve precision and accuracy. Firstly, features extracted by a deep residual network trained on other image processing datasets, are robust enough and retain higher resolution, therefore, we exploit Resnet-101 pretrained offline to obtain features extracted by middle and high layers for target appearance model representation. Resnet-101 is deeper compared with other deep neural networks which means it contains more semantic information. Then, the method we propose to combine our correlation filters is superior. We propose cascaded correlation filters generated by handcraft, middle-level and high-level features from residual network to gain better competence. Handcraft features localize target precisely because they contain more spatial details while Resnet features are robust to the target appearance change because they retain more semantic information. Finally, we conduct extensive experiments on OTB2013 and OTB2015 benchmark. The experimental results show that our tracker achieves high performance under all kinds of challenges and performs favorably against other state-of-the-art trackers.

Visual object tracking based on residual network and cascaded correlation filters

Information security has become a key issue of public concern recently. In order to radically resist the decryption and analysis in the field of image information hiding and significantly improve the security of the secret information, a novel coverless information hiding approach based on deep learning is proposed in this paper. Deep learning can select the appropriate carrier according to requirements to achieve real-time image data hiding and the high-level semantic features extracted by CNN are more accurate than the low-level features. This method does not need to employ the designated image for embedding the secret data but transfer a set of real-time stego-images which share one or several visually similar blocks with the given secret image. In this approach, a group of real-time images searched online are segmented according to specific requirements. Then, the DenseNet is used to extract the high-level semantic features of each similar block. At the same time, a robust hash sequence with feature sequence, DC and location is generated by DCT. The inverted index structure based on the hash sequence is constructed to attain real-time image matching efficiently. At the sending end, the stego-images are matched and sent through feature retrieval. At the receiving end, the secret image can be recovered by extracting similar blocks through the received stego-images and stitching the image blocks according to the location information. Experimental results demonstrate that the proposed method without any modification traces provides better robustness and has higher retrieval accuracy and capacity when compared with some existing coverless image information hiding.

Coverless real-time image information hiding based on image block matching and dense convolutional network

Welcome to San Diego, California and the 2005 IEEE Society Conference on Computer Vision and Pattern Recognition (CVPR), held on June 20-26. This year's conference is the twenty-third in the CVPR series. Besides the main conference, CVPR includes a series of workshops and tutorials, demonstrations and exhibits, and a video proceedings. Conforming with recent CVPR's, registrants for the main conference have a passport to attend any of the other events, and all of the proceedings are presented on a single DVD. We hope that you'll explore all that CVPR has to offer.

Conference on Computer Vision and Pattern Recognition

Existing image inpainting algorithms based on neural network models are affected by structural distortions and blurred textures on visible connectivity. As a result, overfitting and overlearning phenomena can easily emerge during the image inpainting procedure. Image inpainting refers to the repairing of missing parts of an image, given an image that is broken or incomplete. After the repairing operation is complete, there are obvious signs of repair in damaged areas, semantic discontinuities, and unclearness. This paper proposes an improved image inpainting method based on a new encoder combined with a context loss function. In order to obtain clear repaired images and ensure that the semantic features of images are fully learned, a generative network based on the fusion model of squeeze-and-excitation networks deep residual learning has been proposed to improve the application of network features in order to obtain clear images and reduce network parameters. At the same time, a discriminative network based on the squeeze-and-excitation residual Network has been proposed to strengthen the capability of the discriminative network. In order to make the generated image more realistic, so that the restored image will be more similar to the original image, a joint context-awareness loss training method (contextual perception loss network) has also been proposed to generate the similarity of the local features of the network constraint, with the result that the repaired image is closer to the original picture and more realistic. The experimental results can demonstrate that the proposed algorithm demonstrates better adaptive capability than the comparison algorithms on a number of image categories. In addition, the processing results of the image inpainting procedure were also superior to those of five state-of-the-art algorithms.

The improved image inpainting algorithm via encoder and similarity constraint

The importance of image security in the field of medical imaging is challenging. Several research works have been conducted to secure medical healthcare images. Encryption, not risking loss of data, is the right solution for image confidentiality. Due to data size limitations, redundancy, and capacity, traditional encryption techniques cannot be applied directly to e-health data, especially when patient data are transferred over the open channels. Therefore, patients may lose the privacy of data contents since images are different from the text because of their two particular factors of loss of data and confidentiality. Researchers have identified such security threats and have proposed several image encryption techniques to mitigate the security problem. However, the study has found that the existing proposed techniques still face application-specific several security problems. Therefore, this paper presents an efficient, lightweight encryption algorithm to develop a secure image encryption technique for the healthcare industry. The proposed lightweight encryption technique employs two permutation techniques to secure medical images. The proposed technique is analyzed, evaluated, and then compared to conventionally encrypted ones in security and execution time. Numerous test images have been used to determine the performance of the proposed algorithm. Several experiments show that the proposed algorithm for image cryptosystems provides better efficiency than conventional techniques.

/pdf/lightweight-encryption-technique-to-enhance-medical-image-4x3tigevhd.pdf

Lightweight Encryption Technique to Enhance Medical Image Security on Internet of Medical Things Applications

The encrypted image retrieval in cloud computing is a key technology to realize the massive images of storage and management and images safety. In this paper, a novel feature extraction method for encrypted image retrieval is proposed. First, the improved Harris algorithm is used to extract the image features. Next, the Speeded-Up Robust Features algorithm and the Bag of Words model are applied to generate the feature vectors of each image. Then, Local Sensitive Hash algorithm is applied to construct the searchable index for the feature vectors. The chaotic encryption scheme is utilized to protect images and indexes security. Finally, secure similarity search is executed on the cloud server. The experimental results show that compared with the existing encryption retrieval schemes, the proposed retrieval scheme not only reduces the time consumption but also improves the image retrieval accuracy.

/pdf/an-encrypted-image-retrieval-method-based-on-harris-corner-4vx5trc67u.pdf

An Encrypted Image Retrieval Method Based on Harris Corner Optimization and LSH in Cloud Computing

Recently, researches have shown that coverless image steganography can resist the existing steganalysis tools effectively. On this basis, a novel coverless image steganography algorithm based on image retrieval of DenseNet features and DWT sequence mapping is proposed in this paper. Firstly, DenseNet convolutional neural network model in deep learning is used to extract the features of image datasets. Supervised learning is adopted to retrieve the image, and the retrieval results can be used as the information carrier. Secondly, the selected images are divided into 4 × 4 sub-blocks for block discrete wavelet transform. Then the D W T coefficient are calculated based on the low-frequency components after block transformation, and the coefficients between blocks are scanned according to the Zigzag scan, such that the robust feature sequences are generated. Finally, the secret information is divided into segments with the same length as the feature sequence, and an inverted index is established with feature sequence, the position of blocks, D W T coefficient and image path. The image with the same feature sequence as the secret information segment is selected through index as the carriers. The experimental results and analysis show that this method has better robust and security performance resisting most image attacks compared with the state-of-the-art methods.

Coverless steganography based on image retrieval of DenseNet features and DWT sequence mapping

The rapid development of big data and cloud computing technologies greatly accelerate the spreading and utilization of images and videos. The copyright protection for images and videos is becoming increasingly serious. In this paper, we proposed the robust non-blind watermarking schemes in YCbCr color space based on channel coding. The source watermark image is encoded and singular value decomposed. Subsequently, the singular value matrixes are embedded into the Y, Cb, and Cr components of the host image after four-level discrete wavelet transform (DWT). The embedding factor for each component is calculated based on the just-noticeable distortion and the singular vectors of HL subband of DWT. The peak signal-to-noise ratio of the watermarked image and the normalized correlation coefficient of the extracted watermark are investigated. It is shown that the proposed channel coding-based schemes can achieve near exact watermark recovery against all kinds of attacks. Considering both robustness and transparency, the convolutional code-based additive embedding scheme is optimal, which can also achieve good performance for video watermarking after extension.

/pdf/a-robust-watermarking-scheme-in-ycbcr-color-space-based-on-2fbs9mhywf.pdf

A Robust Watermarking Scheme in YCbCr Color Space Based on Channel Coding

With the digitalization of information, a lot of multimedia data are under attack, information security has become a key issue of public concern. Image steganography, aiming at using cover images to convey secret information has become one of the most challenge and important subjects in the field of information security recently. Different from the traditional image steganography, coverless image steganography does not need to employ the designated cover image for embedding the secret data but directly transfers secret information through its own properties such as pixel brightness value, color, texture, edge, contour and high-level semantics. Therefore, it radically resist the detection of steganalysis tools and significantly improves the security of the image. Its basic idea is to analyze the attributes of the image and map them to the secret information according to certain rules based on the characteristics of the attributes. This paper includes more than 50 key contributions to provide a comprehensive survey in this field, covers the main aspects of coverless image steganography research: the fundamental frameworks, pre-processing, feature extraction, generation of hash sequence and mapping relationships. The existing methods are evaluated and the prospect of future work is also summarized.

/pdf/coverless-image-steganography-a-survey-4hr7abb62e.pdf

Coverless Image Steganography: A Survey

Most of the existing coverless steganography approaches have poor robustness to geometric attacks, because these approaches use features of the entire image to map information, and these features are easy to be lost when being attacked. In order to improve the robustness against geometric attacks, we propose a coverless image steganography method based on multi-object recognition. In this scheme, we firstly use Faster RCNN to detect objects in the image data set, establish a mapping dictionary between object labels and binary sequence. Then we propose a novel mapping rule based on the filtered robust object labels for sequence generation. Therefore, an image can generate robust binary sequence through multi-objects recognition. In the transmission process, the transmitted image has not been modified, so our method can fundamentally resist steganalysis tools and avoid the attacker’s suspicions. In addition, the capacity and hiding rate of the proposed method are both considerable. Evaluations with under geometric attacks shows, on average, $3.1\times $ robustness increase over other five coverless steganography methods. Moreover, evaluations under ten noise attacks shows, on average, the robustness of our method is also excellent, which reaches 83%.

Xuyu Xiang

Papers

An Encrypted Image Retrieval Method Based on Harris Corner Optimization and LSH in Cloud Computing

Coverless steganography based on image retrieval of DenseNet features and DWT sequence mapping

A Robust Watermarking Scheme in YCbCr Color Space Based on Channel Coding

Coverless Image Steganography: A Survey

Coverless Image Steganography Based on Multi-Object Recognition