Robust audio fingerprinting plays a crucial role in applications such as audio authentication and copyright protection. However, existing fingerprinting techniques often rely heavily on hand-crafted features and struggle to maintain robustness and generalization, particularly when dealing with long-duration audios and facing complex distortions. To address these challenges, we propose a deep learning framework for robust audio fingerprinting with multi-feature enhancement. First, origin audio is transformed into Log-Mel spectrum, and time-frequency features are extracted by a convolutional neural network (CNN). Then, we apply a dual-domain attention module with a dimension reduction component to dynamically capture salient regions in both time and frequency domains. Finally, we use metric learning to optimize the fingerprint space, ensuring better separation between positive and negative samples. Experimental results show that our method achieves an AUC of 0.99 on ROC curves, outperforming typical methods by up to 5.3%, with particularly strong robustness under distortions including background noise, time scaling and sampling rate changes.

In today’s intelligent transportation systems, the effectiveness of image-based analysis relies heavily on image quality. To enhance images while preserving reversibility, this article proposes a histogram matching-based reversible data hiding (HMRDH) method. The proposed approach ensures high-embedding capacity by incorporating histogram shifting from reversible data hiding with contrast enhancement (RDHCE). Unlike traditional RDHCE methods that are limited to achieving histogram equalization, our method constrains the sequence of bin adjustments to achieve flexible histogram matching. The algorithm first evaluates bin heights to assign roles, then iteratively selects and adjusts corresponding bins while embedding information. To prevent deviation from the target histogram, this method calculates the root mean square error after each iteration to ensure that the adjustment is retained only if it improves the matching accuracy. When necessary, the original image and embedded information can be fully recovered. Extensive experiments demonstrate the superiority of the proposed method in visual quality, embedding capacity, and adaptability.

Cooperative localization offers a potential solution to the limitation of anchor-deployment in range-based localization system. However, there is a huge risk of location leakage in the cooperative process. Several privacy-preserving schemes have been proposed to address this problem. Unfortunately, the inter-anchor communication makes these schemes unable to provide strong privacy guarantees. To tackle this issue, a secure and lightweight scheme based on partially homomorphic encryption is presented in this letter. Specifically, the least-squares estimation algorithm is decomposed into a form matching the additive homomorphism, so that each participated anchor can individually perform the encryption of its respective location-related information without interacting with others. During the entire localization process, private information of all entities involved remains secret, which could motivate users who have just done the positioning to participate in the localization, acting as pseudo-anchors for cooperative localization to solve the problem of dense anchor deployment. Experimental results and theoretical analysis have shown the proposed scheme meets the desired properties for a more pervasive use of indoor localization.

This paper proposes an end-to-end two-branch network for a document image perceptual hashing scheme, where the two branches focus on image visual features and text features, respectively. Existing perceptual hashing schemes cannot solve the problem of the tiny proportion of text tampering detection, while simple text detection is unable to solve the problem of background region-aware matching. To address these issues, we extract text information via optical character recognition (OCR) and then generate the text features using the bidirectional encoder representations from Transformers (BERT). Visual features of the image are extracted from the local and global features of the image using ResNet and Vision Transformer cascades, and then fused to generate the final hash sequence through the fully connected layer. The proposed network considers both image visual features and textual information to verify that the document image has not been tampered with. In our network, the OCR module enables accurate and intelligent text detection and recognition, particularly for dealing with text tampering that has only been conducted in tiny portions. It also provides more efficient and robust text recognition services. Experimental results show that the proposed hashing scheme is robust and discriminative in document images.

Although screen-camera resilient watermarking addresses issues such as privacy leakage and copyright infringement in digital images to some extent during screen-camera communication. However, in screen-camera scenarios, uncontrolled shooting environments, various display devices, and different lens types introduce more complex noise into the watermarked images. Because some noise generated during the screen-camera process cannot be quantitatively analyzed, the integrity of the embedded watermark is compromised, making copyright verification and information acquisition still difficult. To solve this problem, we establish a large-scale screen-camera image dataset (SCISet) and propose a noise simulation network (NoS-Net). Specifically, we obtain 36,000 screen-camera images under various shooting environments with multiple types of screens and cameras. Then, we use SCISet to train the proposed NoS-Net based on the U-Net architecture, which can learn multi-level and complementary feature information of screen-camera images, enhancing its ability to simulate complex noise. Experimental results show that integrating the proposed NoS-Net into mainstream screen-camera resilient watermarking methods significantly improves their ability to resist screen-camera noise attacks. Furthermore, the diversity of SCISet plays an important role in advancing robust watermarking research.

Perceptual hashing is a cutting-edge technique in the field of digital multimedia security, which maps the perceptual content of multimedia information to a fixed-length hash sequence to achieve content authentication. This survey provides a systematic overview of the definition, basic steps, main characters, and application scenarios of perceptual hashing. According to the different authentication objects, representative schemes of perceptual image hashing, perceptual video hashing, and perceptual hashing for neural network models are introduced, respectively. Both perceptual image hashing and perceptual video hashing can be divided into classical methods-based schemes and learning-based schemes, where learning-based schemes can be subdivided into supervised and unsupervised. Classical methods-based image hashing schemes can be divided into four categories: local feature-based, transformation-based, statistical feature-based, and dimensionality reduction-based. Classical methods-based video hashing schemes are mainly categorized into spatial feature-based schemes and spatial-temporal feature-based schemes. Additionally, we introduce the dataset composition and hash distance metric strategies for perceptual hashing and analyze the performance of some representative schemes. Finally, we summarize the existing schemes and offer prospects for future research directions and development trends.

A robust reversible watermarking (RRW) algorithm enables the extraction of the watermark and the restoration of the cover image without attacks while ensuring the watermark’s extraction when the image is under attack. Existing RRW methods mainly focused on achieving robustness against geometric attacks such as rotation and scaling by embedding watermarks within the global inscribed circle of an image. However, the geometric transformations targeted by the existing methods cannot cope with combined attacks that include cropping, which is a real application scenario for geometric attacks. To extend the robustness of the watermarking algorithm, this paper proposes a local Zernike moments (ZMs) embedding strategy based on feature point extraction and selection. For each local circular domain, the same watermark is embedded in the magnitude of the ZMs. After embedding, all the compensation information used to recover the robust embedded regions is embedded outside these local circular domains in a reversible way. When attacks occur, especially combined attacks involving cropping, by using side information, the local watermarked regions in the image can be localized to extract the robust watermark. Experimental results show the superiority of the proposed method under various combined attacks that include cropping operations.

Face information in public images is vulnerable to tampering. Some studies have used pre-embedded watermarks to detect tampering but cannot recover the original face. To address this, we propose a proactive face hiding network that conceals face information in the background region for the first time. Our framework includes three U-Net-based modules: a preparation network, an encoder, and a recovery network. Special loss functions are designed to achieve our objective of recovering the original face from a protected image attacked by face swapping. In addition, we develop a neural network-based JPEG simulator and a differentiable simulator, offering a fresh perspective on addressing the robustness problem associated with JPEG compression. Our method generates protected images with a peak signal-to-noise ratio (PSNR) of 40.947 dB in experiments. Even after different face attacks, the recovered images maintain PSNR between 28.368 and 33.847 dB. After the attack of JPEG compression, the PSNR of the recovered image decreases by a maximum of 2.142 dB. Our scheme effectively generates high-quality protected images that resist face swapping and JPEG compression attacks, enabling recovery of the original faces.

Reversible data hiding (RDH) has been investigated for over two decades. Depending on the application scenario, it can be divided into RDH and reversible data hiding in encrypted images (RDHEI). Interestingly, almost all studies on RDH/RDHEI have been conducted on gray-scale images, and relatively few studies have been conducted on color images compared to those on gray-scale images. Moreover, very few studies have been undertaken on palette images as a widely used image format. For palette images in which pixels are not gray-scale levels but color table indexes, it is difficult to apply traditional RDH/RDHEI methods directly. Therefore, we propose a new framework for RDH/RDHEI specifically for palette images. This framework adds a route selection algorithm before the conventional RDH/RDHEI approach. To be specific, we propose a method named the shortest route with correlation and frequency selection to reorder the color table, followed by a correlation reconstruction of the remapped index image according to this color table. The experimental results show the improvement brought by our proposed route selection to the existing RDH/RDHEI methods in palette images.

Digital image rotation angle estimation is an essential research branch of resampling detection, and many methods have been proposed for the resampling detection problem. However, the angle factor estimation for small-angle image rotation has not been adequately studied. This paper proposes a digital image rotation angle estimation algorithm based on a convolutional neural network (CNN). The angle range of small-angle rotations is defined as an integer interval from 1° to 9°. Thus, the problem of estimating the rotation angle of a digital image is converted into a multiclassification problem. The rotation image is first preprocessed with a high-pass filter, and the resampling trace of the image is enhanced. The two-dimensional cyclic spectrum of the filtered image is then calculated. As an input to the network model, the two-dimensional spectrum map suppresses the effect of image content on rotation angle estimation. Next, a series of convolution layers are used to automatically extract the resampling features caused by rotation from the two-dimensional cyclic spectrum. Finally, the rotation angle of the image is estimated in the output layer. Experimental results show the superiority of the proposed method in small-angle rotation image estimation.

Secret sharing is a useful method which divides a secret message into several shares for security. During the recovery procedure, only when sufficient shares are obtained, the secret message can be recovered. This paper proposes two novel reversible data hiding schemes in encrypted image via secret sharing over Galois fields${{GF}}{({p})}$and${{GF}}{(}{{2}^{{8}}}{)}$. The content owner first applies a specific encryption method through block and pixel permutation and Shamir’s secret sharing. Then, the theoretical demonstration is introduced to explain that the generated shares are suitable for data embedding over${{GF}}{({p})}$and${{GF}}{(}{{2}^{{8}}}{)}$. Finally, two embedding algorithms over${{GF}}{({p})}$and${{GF}}{(}{{2}^{{8}}}{)}$are presented, and on the receiver side, with different keys, additional data can be extracted correctly and original image can be recovered losslessly. Experimental results show that our schemes can achieve better rate-distortion performance than some state-of-the-art schemes.

Reversible data hiding in encrypted images (RDHEI), an essential branch of reversible data hiding (RDH), has been in development for more than a decade. For most existing stream-cipher-based RDHEI algorithms, encryption schemes are often not the same; thus, these schemes have different effects on the encrypted images. As a result, it is not reasonable to compare the embedding rates (ERs) of RDHEI algorithms directly as we do for plaintext RDH algorithms. However, to our knowledge, many studies focus on the performance of embedding but neglect the influence of the encryption. To compare the performance of stream-cipher-based RDHEI algorithms more reasonably, this paper proposes a novel comprehensive measure to evaluate state-of-the-art RDHEI algorithms. First, the characteristics of the stream-cipher-based RDHEI algorithms are divided into two categories according to the encryption and embedding processes. Next, we use correlation and redundancy to evaluate the influence of encryption schemes and also use ER, computation complexity, visual quality, and algorithm stability to evaluate the embedding schemes. In the end, in order to combine all six indexes into the final evaluation measure, we standardize each index before applying the radar chart. The experimental results show the evaluation results of the recent RDHEI algorithms via a comprehensive analysis and demonstrate the guiding significance of the proposed method for the current RDHEI algorithm selection.

Most computer vision algorithms require parameter adjustment according to the image noise level. Conventionally, the additive white Gaussian noise (AWGN) model is widely used in most noise estimation algorithms; however, this assumption does not hold in the real world where the noise from cameras is more complex, and it is more appropriate to assume the signal-dependent noise (SDN) model. In this paper, we focus on the SDN model while considering the nonlinear radiometric calibration inside an actual camera, and propose an algorithm to efficiently estimate the noise level function (NLF), which is defined as the noise standard deviation with respect to image intensity. First, the input image is divided into overlapping patches, and noise samples are estimated in the linear transform domain. The confidence levels of the noise samples and the prior of the camera response function are then employed as constraints for the recovery of the NLF. Finally, the noise samples and constraints are represented in a convex optimization problem. The experimental results using both real and synthetic noisy images demonstrate the superiority of the proposed method. In addition, the estimated NLFs are incorporated into two well-known denoising schemes, non-local means and BM3D, and shows significant improvements in denoising SDN-polluted images.

Abstract Image hashing is an efficient technique of many multimedia systems, such as image retrieval, image authentication and image copy detection. Classification between robustness and discrimination is one of the most important performances of image hashing. In this paper, we propose a robust image hashing with singular values of quaternion singular value decomposition (QSVD). The key contribution is the innovative use of QSVD, which can extract stable and discriminative image features from CIE L*a*b* color space. In addition, image features of a block are viewed as a point in the Cartesian coordinates and compressed by calculating the Euclidean distance between its point and a reference point. As the Euclidean distance requires smaller storage than the original block features, this technique helps to make a discriminative and compact hash. Experiments with three open image databases are conducted to validate efficiency of our image hashing. The results demonstrate that our image hashing can resist many digital operations and reaches a good discrimination. Receiver operating characteristic curve comparisons illustrate that our image hashing outperforms some state-of-the-art algorithms in classification performance.

We propose a novel indoor positioning algorithm based on the received signal strength (RSS) fingerprint. The proposed algorithm can be divided into three steps, an offline phase at which an advanced clustering (AC) strategy is used, an online phase of approximate localization at which cluster matching is used, and an online phase of precise localization with kernel ridge regression. Specifically, after offline fingerprint collection and similarity measurement, we employ an AC strategy based on the K -medoids clustering algorithm using additional reference points that are geographically located at the outer cluster boundary to enrich the data of each cluster. During the approximate localization, RSS measurements are compared with the cluster radio maps to determine to which cluster the target most likely belongs. Both the Euclidean distance of the RSSs and the Hamming distance of the coverage vectors between the observations and training records are explored for cluster matching. Then, a kernel-based ridge regression method is used to obtain the ultimate positioning of the target. The performance of the proposed algorithm is evaluated in two typical indoor environments, and compared with those of state-of-the-art algorithms. The experimental results demonstrate the effectiveness and advantages of the proposed algorithm in terms of positioning accuracy and complexity.

Noise is the most common type of image distortion affecting human visual perception. In this paper, we propose a no-reference image quality assessment (IQA) method for noisy images incorporating the features of entropy, gradient, and kurtosis. Specifically, image noise estimation is conducted in the discrete cosine transform domain based on skewness invariance. In the principal component analysis domain, kurtosis feature is obtained by statistically counting the significant differences between images with and without noise. In addition, both the consistency between the entropy and kurtosis features and the subjective scores are improved by combining them with the gradient coefficient. Support vector regression is applied to map all extracted features into an integrated scoring system. The proposed method is evaluated in three mainstream databases (i.e., LIVE, TID2013, and CSIQ), and the results demonstrate the superiority of the proposed method according to the Pearson linear correlation coefficient which is the most significant indicator in IQA.

An important goal of indoor positioning systems is to improve positioning accuracy as well as reduce power consumption. In this paper, we propose an indoor positioning method based on the received signal strength (RSS) fingerprint. The proposed method used a certain criterion to select fixed access points (FPs) in an offline phase instead of an online phase for location estimation. Principal component analysis (PCA) was applied to reduce the features of the RSS measurements but retain the most information possible for establishing the positioning model. Then, a kernel‐based ridge regression method was used to obtain the nonlinear relationship between the principal components of the RSS measures and the position of the target. We thoroughly investigated the performance of the proposed method in realistic wireless local area network (WLAN) and wireless sensor network (WSN) indoor environments and made comparisons with recently developed methods. The experimental results indicated that the proposed method was less dependent on the density of the reference points and had higher positioning accuracy than the commonly used positioning methods, and it adapts to different application environments.

Abstract Video hashing is a novel technique of multimedia processing and finds applications in video retrieval, video copy detection, anti-piracy search and video authentication. In this paper, we propose a robust video hashing based on discrete cosine transform (DCT) and non-negative matrix decomposition (NMF). The proposed video hashing extracts secure features from a normalized video via random partition and dominant DCT coefficients, and exploits NMF to learn a compact representation from the secure features. Experiments with 2050 videos are carried out to validate efficiency of the proposed video hashing. The results show that the proposed video hashing is robust to many digital operations and reaches good discrimination. Receiver operating characteristic (ROC) curve comparisons illustrate that the proposed video hashing outperforms some state-of-the-art algorithms in classification between robustness and discrimination.

The precise estimation of the noise level is a crucial issue in image processing. In this study, the authors propose a new method for noise standard deviation (STD) estimation from natural images based on skewness‐scale invariance in the transform domain and an adaptive noise injection strategy. The method is divided into two steps. The first step assumes that the natural clean image has the property of constancy of skewness in the transform domain. Then, a preliminary noise estimation method based on skewness invariance is designed by solving a constrained non‐linear optimisation problem. The second step involves noise rectification via noise injection. According to the phenomenon that compared with the high‐noise circumstance, the error of preliminary estimation is more serious under a low amount of noise, the noise STD is re‐estimated by injecting another noise for which the STD is known. In addition, the threshold model with respect to image complexity is established to identify whether a second estimation is needed. The experimental results demonstrate the efficacy of the proposed method and performance is superior to other state‐of‐the‐art methods.

We propose a novel perceptual image hashing based on weighted discrete wavelet transform (DWT) statistical features. This hashing converts input image into a normalized image by bi-linear interpolation and color space conversion, extracts edge image of the normalized image via Canny operator, and divides the edge image into non-overlapping blocks. For each block, a three-level 2D DWT is applied to obtain different sub-bands and the weighted sum of the DWT statistics of these sub-bands is calculated. Finally, image hash is generated by concatenating and quantizing these weighted DWT features. Similarity of image hashes is measured by Euclidean distance. The Copydays dataset and the Uncompressed Color Image Database (UCID) are both used to evaluate classification between robustness and discrimination. Receiver operating characteristics curve comparisons illustrate that our hashing is superior to some state-of-the-art algorithms in classification performance with respect to robustness and discrimination. The LIVE Image Quality Assessment Database is used to validate our application in reduced-reference image quality assessment. Experimental results show that our hashing has better performance in image quality assessment than two popular measures, i.e. peak signal-to-noise ratio and structural similarity.

A robust hashing method is developed for detecting image forgery including removal, insertion, and replacement of objects, and abnormal color modification, and for locating the forged area. Both global and local features are used in forming the hash sequence. The global features are based on Zernike moments representing luminance and chrominance characteristics of the image as a whole. The local features include position and texture information of salient regions in the image. Secret keys are introduced in feature extraction and hash construction. While being robust against content-preserving image processing, the hash is sensitive to malicious tampering and, therefore, applicable to image authentication. The hash of a test image is compared with that of a reference image. When the hash distance is greater than a threshold τ1and less than τ2, the received image is judged as a fake. By decomposing the hashes, the type of image forgery and location of forged areas can be determined. Probability of collision between hashes of different images approaches zero. Experimental results are presented to show effectiveness of the method.

In visual perception, distant objects appear smaller than those close to the observer. To insert an object into an image, properly size a foreign object is difficult, especially when there is no reference object in the same distance. To detect this type of image forgery, we present a perspective-constraint based method, with which the height ratio of two objects in an image can be determined without any knowledge of the camera parameters. Assuming that the camera is held leveled and with negligible tilt, the height ratio can be found merely by a vanishing line of the plane on which both objects of interest is situated. Once the estimated ratio exceeds a tolerable interval, a forged region is identified. Experimental results show efficacy of the method even if the images to be tested have been down-sampled or compressed with a low quality factor.