Perceptual Hashing Research Articles

Perceptual Vibration Hashing by Sub-Band Coding: An Edge Computing Method for Condition Monitoring

High data throughput during real-time vibration monitoring can easily lead to network congestion, insufficient data storage space, heavy computing burden, and high communication costs. As a new computing paradigm, edge computing is deemed to be a good solution to these problems. In this paper, perceptual hashing is proposed as an edge computing form, aiming not only to reduce the data dimensionality but also to extract and represent the machine condition information. A sub-band coding method based on wavelet packet transform, two-dimensional discrete cosine transform, and symbolic aggregate approximation is developed for perceptual vibration hashing. When the sub-band coding method is implemented on a monitoring terminal, the acquired kilobyte-long vibration signal can be transformed into a machine condition hash occupying only a few bytes. Therefore, the efficiency of condition monitoring can benefit from the compactness of the machine condition hash, while comparable diagnostic and prognostic results can still be achieved. The effectiveness of the developed method is verified with two benchmark bearing datasets. Considerations on practical condition monitoring applications are also presented.

Image perception hash and structural similarity fusion model for parking lot status recognition

In order to improve the recognition accuracy of parking space change, a new fusion model is proposed. The image-aware hash technique and image structure similarity algorithm are combined to constru...

Scale-adaptive tracking based on perceptual hash and correlation filter

In the research on computer vision, object tracking has encountered various challenges, such as occlusion and scale variation. In recent years, tracking-by-detection methods have performed competitively. Some of these methods have focused on solving the problem of scale variation. Regardless, these algorithms perform poorly in real time. Recently, correlation filters have been widely used in object tracking because of their high efficiency; however, conventional correlation filter-based trackers cannot handle scale variation. Most correlation filter-based trackers update the template for each frame, and tracking offsets occur when a tracking error is present. To overcome these problems, we propose a novel scale-adaptive tracking algorithm that uses perceptual hash and correlation filter on the basis of tracking-by-detection methods. We employ kernel ridge regression to minimize the mean square error between the training image and the regression object, and construct a robust filter template to track the target center location. By tracking the 4 sub-blocks of the target image, the length and width expansion coefficients are calculated separately to update the target scale. We finally use the adaptive update strategy based on perceptual hash to effectively prevent the tracking offset caused by the template update error. Owing to the insensitivity to the scale variation and high efficiency of the perceptual hash, tracking becomes more robust in real time. Both quantitative and qualitative evaluations on Object Tracking Benchmark (OTB) indicate that the proposed tracking method performs more favorably compared with other state-of-the-art methods.

Perceptual hashing for SAR image segmentation

ABSTRACTImage segmentation is an important step in the implementation of the interpretation of synthetic aperture radar (SAR) image due to speckle. This article proposes a SAR image segmentation method based on perceptual hashing. The new algorithm is divided into two phases. The first phase is to obtain initial regions with multi-thresholding based on histogram after reducing the speckle noise. The initial regions are used as input data. And the next phase is to merge regions according to the similarity between regions. In this phase, to segment SAR image effectively, the proposed hashing algorithm is used to obtain hash value and similarity between regions, which preserve the texture features of SAR images. In addition, we can obtain a smooth segmentation result by reducing the redundant information with principal component analysis. Furthermore, morphological methods are used to eliminate the uneven background in the segmentation results. These improvements make our algorithm more effective to segment the images with high speed. The experimental results of four real and one synthetic SAR images verify the efficiency of our algorithm.

Image Hashing for Tamper Detection with Multiview Embedding and Perceptual Saliency

Perceptual hashing technique for tamper detection has been intensively investigated owing to the speed and memory efficiency. Recent researches have shown that leveraging supervised information could lead to learn a high-quality hashing code. However, most existing methods generate hashing code by treating each region equally while ignoring the different perceptual saliency relating to the semantic information. We argue that the integrity for salient objects is more critical and important to be verified, since the semantic content is highly connected to them. In this paper, we propose a Multi-View Semi-supervised Hashing algorithm with Perceptual Saliency (MV-SHPS), which explores supervised information and multiple features into hashing learning simultaneously. Our method calculates the image hashing distance by taking into account the perceptual saliency rather than directly considering the distance value between total images. Extensive experiments on benchmark datasets have validated the effectiveness of our proposed method.

Research on BatSLAM Algorithm for UAV Based on Audio Perceptual Hash Closed-Loop Detection

This research is aimed at the optimization of a two-dimensional (2D) empirical graph under a certain height and dark conditions for a UAV, using the bionic sonar system to replace the visual sensor’s BatSLAM mode and audio perceptual hash closed-loop detection. The BatSLAM model uses Sum of Absolute Difference (SAD) image processing methods to update the bionic sonar template. This method only judges whether the appearance of the two cochlear images is consistent and does not have geometric processing and feature extraction. Because the cochlear images produce various noises during the acquisition and transmission, there are some differences in cochlear maps obtained at the same position, which can lead to the distortion of the constructed empirical map. In this research, an audio perceptual hash closed-loop detection algorithm is developed to extract features of cochlea. It considers both the appearance and the energy difference between adjacent bands to improve the accuracy of closed-loop detection, thus solving the distortion problem and improving the experience map. The simulation experiment shows that the improved BatSLAM model based on the audio perceptual hash closed-loop detection can improve the 2D experience map for UAV under certain height and dark conditions, through improving the accuracy of the closed-loop detection to solve the distortion problem and thus implementing the optimization of the experience graph.

Robust Visual Tracking via Multi-Scale Spatio-Temporal Context Learning

In order to tackle the incomplete and inaccurate of the samples in most tracking-by-detection algorithms, this paper presents an object tracking algorithm, termed as multi-scale spatio-temporal context (MSTC) learning tracking. MSTC collaboratively explores three different types of spatio-temporal contexts, named the long-term historical targets, the medium-term stable scene (i.e., a short continuous and stable video sequence), and the short-term overall samples to improve the tracking efficiency and reduce the drift phenomenon. Different from conventional multi-timescale tracking paradigm that chooses samples in a fixed manner, MSTC formulates a low-dimensional representation named fast perceptual hash algorithm to update long-term historical targets and the medium-term stable scene dynamically with image similarity. MSTC also differs from most tracking-by-detection algorithms that label samples as positive or negative, it investigates a fusion salient sample detection to fuse weights of the samples not only by the distance information, but also by the visual spatial attention, such as color, intensity, and texture. Numerous experimental evaluations with most state-of-the-art algorithms on the standard 50 video benchmark demonstrate the superiority of the proposed algorithm.

Perceptual Hashing Based Forensics Scheme for the Integrity Authentication of High Resolution Remote Sensing Image

High resolution remote sensing (HRRS) images are widely used in many sensitive fields, and their security should be protected thoroughly. Integrity authentication is one of their major security problems, while the traditional techniques cannot fully meet the requirements. In this paper, a perceptual hashing based forensics scheme is proposed for the integrity authentication of a HRRS image. The proposed scheme firstly partitions the HRRS image into grids and adaptively pretreats the grid cells according to the entropy. Secondly, the multi-scale edge features of the grid cells are extracted by the edge chains based on the adaptive strategy. Thirdly, principal component analysis (PCA) is applied on the extracted edge feature to get robust feature, which is then normalized and encrypted with secret key set by the user to receive the perceptual hash sequence. The integrity authentication procedure is achieved via the comparison between the recomputed perceptual hash sequence and the original one. Experimental results have shown that the proposed scheme has good robustness to normal content-preserving manipulations, has good sensitivity to detect local subtle and illegal tampering of the HRRS image, and has the ability to locate the tampering area.

Perceptual Hash Based Detection Algorithm for Image Copy-Paste Tampering

One of the most common modes of image attacking is copy-paste tampering. To overcome the disadvantages of slow speed and fragility in most existing regional tamper detection algorithms, a detection algorithm based on Perceptual Hash Algorithm (PHA) is proposed in this paper. In the aspect of feature extraction, the algorithm firstly carries out Discrete Wavelet Transform (DWT) on the test image and then selects the approximate sub-band to overlapping. Finally, the PHA is used to extract sub-block features and generate the feature matrix. In the patch matching phase, the first step is to find out the similar patches whose statistical displacement is larger than the threshold, and then obtains the main shift vector which satisfies the frequency of occurrence. Finally, the feature matching is performed according to the Hamming distance of similar patches. The experimental results demonstrated that the proposed algorithm can accurately detect the tampered region while ensuring fast computing speed and is robust to some common post-processing operations such as JPEG compression, Gaussian noise and Gaussian blur.

A review on robust video copy detection

The unprecedented escalation and proliferation of digital multimedia and Internet technology have triggered the enormous copyright infringement issues and tampering of digital content. Detection or localization of copy–paste forgery of digital content and distinguishing between original and manipulated video have become a weighty challenge at the present era of multimedia technology. Several distortions such as rotation, scaling and gamma correction are applied into an original video by an adversary to manipulate the original video for copyright infringement. Due to the emergence of ubiquitous digital videos on the Internet and to surpass the challenges, various copy detection schemes have been introduced by several researchers. Many real-time applications such as detection of duplicate Web videos and monitoring of real-time TV commercial media content over multi-broadcast channels require the robust copy detection approach for high security purpose. The other applications include the rapid advancement of video navigation and editing technology such as finding the opening sequence of a TV show and combining or editing similar versions of the same video for copyright infringement. This paper depicts a comprehensive overview of robust visual hashing to identify similar video contents for digital piracy detection, which overcomes the demerits of conventional cryptographic hash functions and watermarking. The paramount goal of this scheme is to generate the perceptual hash code of fixed size of length from video segments which are robust against distinct distortions or attacks such as scaling, rotation, compression, frame rate change, frame dropping, contrast enhancement, etc., made by an adversary. Besides, in this paper, distinct state-of-the-art schemes used for copy detection have been studied thoroughly and classified based on the methodology they have implemented.

Dynamic Hand Gesture Tracking Method Based on Key Frame and Video Perceptual Hashing

Aiming at the common problems such as low tracking accuracy, robustness and poor real-time ability for the traditional tracking algorithm, a novel dynamic hand gesture tracking method based on key frame and video perceptual hashing has been proposed in this paper. Firstly, the proposed method is used to frame the video sequence and extract the key frames, in order to obtain a sequence of key frames. Secondly, the video perceptual hashing is used to extract the perceptual feature of the key frame and target template, thus the hash sequence is generated. Finally, the hamming distance is used to compare the similarities between the key frame and target template, therefore, the real-time tracking is carried out by using an online adaptive template update method to ensure the continuity of the hand gesture tracking. Experimental results show that the proposed method can realize the accurate and real-time tracking of the dynamic deformation gestures, and effectively reduce the time complexity of the algorithm, as well as ensure the stability and continuity of the moving target tracking.

A Novel Liver Image Classification Method Using Perceptual Hash-Based Convolutional Neural Network

Classification of liver masses plays an important role in early diagnosis of patients. This paper proposes a method to reduce the liver computed tomography (CT) images classification time and maintain the classification performance above an acceptable threshold by using convolutional neural network (CNN). A hybrid model called fused perceptual hash-based CNN (F-PH-CNN) is proposed by using a perceptual hash function together with the CNN. The proposed method has been designed for differential diagnosis between benign and malignant masses using CT images. The most important feature of the perceptual hash functions is to obtain the salient features of images. In the proposed F-PH-CNN method, DWT–SVD-based perceptual hash functions are used. The study uses CT images of 41 benign and 34 malign samples obtained from Elazig Education and Research Hospital. These samples were augmented up to 112 samples. The experimental results show that the CNN features achieved a better classification performance in which the ANN simulation results validate that the all output data with 98.2% success. The proposed method might also address the clinical computer-aided diagnosis of liver masses.

Histogram-based perceptual hash algorithm for synthetic aperture radar image segmentation

To speed up the segmentation procedure and improve the segmentation quality of synthetic aperture radar (SAR) image, this paper presents an adaptive unsupervised SAR image segmentation method, which is integrated in the grayscale histogram and perceptual hash algorithm. The final clusters can be acquired self-adaptively without predefining. The two stages of the algorithm are discussed in details: histogram-based preprocessing and region merging. In preprocessing, histogram-based gray-level reduction is adopted to generate the set of initial segmented regions to address the problem of over-segmentation. When merging regions, the similarity of different regions can be obtained by comparing their different fingerprints calculated in the perceptual hash algorithm, which is the kernel of the whole SAR image segmentation method. The application of the perceptual hash algorithm for image segmentation can reduce the computational complexity and improve the efficiency of region merging. Experimental simulations and theoretical analysis are used to demonstrate the effectiveness of this algorithm.

A multi-channel approach through fusion of audio for detecting video inter-frame forgery

The forgery operation of digital video in the temporal domain is often accompanied by the synchronization of the audio channel operation. In this paper, we proposed a fusion of audio forensics detection methods for video inter-frame forgery. First, the audio channel of the video is extracted, and discrete wavelet packet decomposition and analysis of singularity points of audio signals are used to locate the forged singularity points. Next, features of each frame of the video are extracted with the perceptual hash and used to calculate the similarity between consecutive frames, to locate the forgery position in the video frame sequence. We fused the results of the audio channel and the video frame sequence channel. The QDCT feature is used to further fine detect the suspected forgery location. Our method can position replication source locations for copy-move forgery. Experiments show that our method has higher accuracy and better performance in comparison with similar methods, especially on the delete forgery operation.

The Speech multi features fusion perceptual hash algorithm based on tensor decomposition

With constant progress in modern speech communication technologies, the speech data is prone to be attacked by the noise or maliciously tampered. In order to make the speech perception hash algorithm has strong robustness and high efficiency, this paper put forward a speech perception hash algorithm based on the tensor decomposition and multi features is proposed. This algorithm analyses the speech perception feature acquires each speech component wavelet packet decomposition. LPCC, LSP and ISP feature of each speech component are extracted to constitute the speech feature tensor. Speech authentication is done by generating the hash values through feature matrix quantification which use mid-value. Experimental results showing that the proposed algorithm is robust for content to maintain operations compared with similar algorithms. It is able to resist the attack of the common background noise. Also, the algorithm is highly efficiency in terms of arithmetic, and is able to meet the real-time requirements of speech communication and complete the speech authentication quickly.

Perceptual hash algorithm‐based adaptive GOP selection algorithm for distributed compressive video sensing

Distributed compressive video sensing (DCVS) is a novel video coding technique that shifts sophisticated motion estimation and compensation from the encoder to the decoder and is suitable for resource-limited communication, namely wireless video sensor networks (WVSNs). In DCVS, key frames serve as the reference for subsequent non-key frames in a given group of pictures (GOP). However, in fast-motion sequences, e.g. scene-changing sequences, a fixed GOP size can cause inaccuracy in the selection of reference key frames. The difference in the peak signal-to-noise ratio between key frames and non-key frames caused by this inaccuracy appears as flicker in the decoded video, negatively affecting the quality of experience. To address this problem, the authors present a perceptual hash algorithm-based adaptive GOP selection algorithm for DCVS and a novel allocation model for the frame sampling rate. In addition, the authors define several indexes to assess the degree of flicker in decoded video. The experimental results demonstrate that the proposed algorithm reduces the degree of flicker in fast-motion sequences by 40-60% relative to the state-of-the-art architecture, while also outperforming other adaptive GOP selection strategies.

Perceptual image hash function via associative memory‐based self‐correcting

Paralleling with the revolutionary development of the Internet, there has been increasing concern about the copyright infringement of digital media. A central problem in copyright protection is to accurately and efficiently identify the illegal copies of copyrighted contents. Perceptual hash function, which summarises the perceptual characteristics of digital media to a short digest, is a low-cost solution to this problem. Owing to the easy-to-manipulate nature of digital media, a major challenge in designing perceptual hash function is to achieve the robustness against distortion. To tackle this problem, an associative memory-based hash function is introduced. The proposed work repairs the distortions on local image structures via associative memory-based de-noising, in the hope of simulating the self-correcting mechanism in human memory. The shape invariant descriptors of de-noised structures are then encoded to binary bits. Experimental results confirm that the proposed work outperforms representative algorithms, and it can achieve an equal error rate of 3.30 × 10 − 3 in content identification with only 80 bits.

A Novel Perceptual Hash Algorithm for Multispectral Image Authentication

The perceptual hash algorithm is a technique to authenticate the integrity of images. While a few scholars have worked on mono-spectral image perceptual hashing, there is limited research on multispectral image perceptual hashing. In this paper, we propose a perceptual hash algorithm for the content authentication of a multispectral remote sensing image based on the synthetic characteristics of each band: firstly, the multispectral remote sensing image is preprocessed with band clustering and grid partition; secondly, the edge feature of the band subsets is extracted by band fusion-based edge feature extraction; thirdly, the perceptual feature of the same region of the band subsets is compressed and normalized to generate the perceptual hash value. The authentication procedure is achieved via the normalized Hamming distance between the perceptual hash value of the recomputed perceptual hash value and the original hash value. The experiments indicated that our proposed algorithm is robust compared to content-preserved operations and it efficiently authenticates the integrity of multispectral remote sensing images.

A high-performance speech perceptual hashing authentication algorithm based on discrete wavelet transform and measurement matrix

Aiming at the problems of existing speech authentication algorithms, such as poor robustness and discrimination, security vulnerability, low efficiency, poor ability of tamper detection and localization, a high-performance speech perceptual hashing authentication algorithm based on Discrete Wavelet Transform (DWT) and measurement matrix is proposed in this paper. Firstly, the speech signal is conducted with DWT by applying preprocessing, and the low-frequency wavelet coefficients are regarded as the perceptual feature value. Then the measurement matrix controlled by chaos map is applied to reduce the dimension of feature value. Finally, the feature value is used to generate the perceptual hash sequence by the process of hashing structure. The measurement matrix is designed as the secret key to enhance the security of the proposed algorithm. The experimental results demonstrates the proposed algorithm has high efficiency in perceptual robustness, discrimination, time consumption and security, as well as having a high accuracy of tampering detection and localization.

A probabilistic image authentication method based on chaos

Fragile watermarking methods have been used as active image authentication methods. These methods must have capabilities like high capacity, high visual quality, high image authentication ability and image recovery capability. Many of the fragile watermarking methods suggested in the literature do not provide all of these capabilities. In this article, a new probabilistic image authentication method with high capacity, high visual quality, high image authenticity ability and image recovery capability is proposed. Chaotic pseudo random number generators, a new watermark generation network which similar to neural network, modulo based watermark embedding functions, modulo based watermark extraction functions, tamper detection algorithm and perceptual hash based image recovery algorithm are utilized for creating a new probabilistic image authentication method in this article. The proposed method is a block based authentication method and 3 × 3 size of overlapping neighborhood blocks are used in this method. The proposed watermark generation network uses symmetric pixels as inputs and weights to generate predicted pixel. In this step, modulo operator and random numbers are used for calculating embeddable value. Owing to chaotic random number generator, the proposed method gains probabilistic and nonlinear structure. To generate random number, logistic map is used as random number generator in the proposed image watermarking method. Then, a modulo based watermark embedding function is used for embedding embeddable value (generated watermark). In the watermark extraction step, modulo operator is used. If the predicted value differs from the extracted value, tamper detection is performed. Otherwise, image authentication is success. A new image recovery algorithm is proposed in this method. This algorithm provides image recovery for tampered areas with high visual quality. The proposed image watermarking method can authenticate grayscale and color images. The experimental results demonstrated that, the proposed method has high payload capacity, high visual quality and high image authentication ability.