The Impact of Image Processing on Perceptual Hash Values

This paper proposes a perceptual hash algorithm based on the combination of Scale-invariant feature transform (SIFT) and cluster analysis (K-means). SIFT is used for extracting local stabilized feature points of images. K-means is used for compressing feature data and obtain image perceptual hash. Assess the similarity between video frame and frame by means of Hamming distance among perceptual hash value. Through the analysis of experimental data, the results show that the algorithm has good robustness and success rate.

In our previous study, we found three requirements for digital watermarking. The first is that to prevent watermark information of an image from being diverted to other images, this information must be generated based on the original image. The second is that after the original image is modified/edited, it should still be able to be used the same as the original image. The third is that multiple digital watermarks should be stored and managed without relying on trusted third parties. To meet these requirements, we proposed a digital-copyright-management system based on perceptual hashing and blockchain. However, because we used conventional perceptual hashing in that study, we could not draw sufficient conclusions about the first and second requirements. In this current study, to obtain a stable message digest, we propose a method of improving perceptual hashing based on machine learning. With this method, an image is first modified/edited using various methods to generate an image set. This image set is then input into a convolutional neural network (CNN) to calculate the features of the images, and the data of the CNN intermediate layer are output as machine learning data. Finally, through machine learning, latent stochastic variables are determined that can be used to calculate latent image features, and the perceptual hash value of this image set is calculated using these image features for the blockchain and digital watermarking. The method also records these latent stochastic variables on the blockchain to ensure copyright security by ensuring that these variables cannot be used by those other than the original author.

Perceptual audio hashing has been applied in audio content identification, retrieval and indexing for its accuracy and perceptual robustness. Security issue becomes important when perceptual hashing is applied in audio content authentication. A key-dependent compressed domain perceptual audio hashing algorithm for audio content authentication is proposed. A randomization scheme controlled by a random seed is applied in hash generation for random feature selection and post randomization. The hash function is key-dependent and collision free. Meanwhile, the randomization has little effect on robustness. The hash value is invariant to content preserving operations.

The purpose of the work is to create a unified structure for perceptual media hashing. The main goal is to consider fundamental ideas in perceptual hashing of an image. To increase the efficiency of information processing in automated control systems and image processing, there is a need to develop methods for reliable hashing and identification of graphic images. Improving the efficiency will significantly expand the scope of application software in control systems and information processing. This approach will be useful for identifying images in databases, in which it is possible to make various changes to the image, such as compression and format changes, general signal processing algorithms, scanning, or creating watermarks. Developed basic clustering, allows clusters not to bear any losses. Based on the study, two main goals of perceptual image hashing have been identified: resistance to unintentional or perceptually minor image modifications – perceptual hash persistence; the ability to withstand deliberate attacks (caused by a malicious opponent) is a hash of security. The hash of the security properties is closely related to the randomization scheme that is used when creating the hash algorithm. Another extremely important question that needs to be answered is what hash length is required to successfully obtain the desired level of stability. The theoretical analysis of randomized media hashing algorithms and the quantitative relation of randomized parameters with hash security has not yet been addressed in the literature. In the article the approaches for calculation of statistical values of graphic representations which will grasp the main features of the image are considered and remain as a matter of fact not changed through comprehensible transformations. The offered methods are flexible and can be used for the decision of other problems.

Analysis of Perceptual Hashing Algorithms in Image Manipulation Detection

We propose a robust video hash function for broadcast monitoring and database search applications. The method consists of binarized low-frequency components of the 3D-DCT transform of video sequences. Simulation experiments show that the perceptual hash function is unique for different video content, but that it remains invariant under selected signal processing attacks.

This paper proposes a blind authentication scheme to identify duplicated regions for copy-move forgery based on perceptual hashing and package clustering algorithms. For all fixed-size image blocks in suspicious images, discrete cosine transform (DCT) is used to obtain their DCT coefficient matrixes. Their perceptual hash matrixes and perceptual hash feature vectors are orderly addressed. Moreover, a package clustering algorithm is proposed to replace traditional lexicographic order algorithms for improving the detection precision. Similar blocks can be identified by matching the perceptual hash feature vectors in each package and its adjacent package. The experimental results show that the proposed scheme can locate irregular tampered regions and multiple duplicated regions in suspicious images although they are distorted by some hybrid trace hiding operations, such as adding white Gaussian noise and Gaussian blurring, adjusting contrast ratio, luminance, and hue, and their hybrid operations.

Currently, the medical information system is meeting many difficulties when conveying information via the network, such as leaking out the patients’ information, falsifying medical records, and destroying the structure of medical images etc. For these questions, the new algorithm with ultra-strong robustness is proposed, its innovation lies in perfectly combining digital watermarking technology, which is the domain technology in information security area, the emerging perceptual Hash technology, the classical threedimensional reconstruction technology, information encryption technology, and “the third party” certification together. Firstly, it is important to preprocess the original watermarking by means of Arnold scrambling; secondly, to obtain the needed information by 3D-DFT, we utilize perceptual Hash function to stratify and reduce the dimensions, as well as compress the medical volume data into 8  8, then the visual feature vector will be gained after reconstructing the three-dimensional image, which is the result of 3D-IDFT; ultimately, employing the bit operation of Hash function between the encrypted watermarking and visual feature vector, we can realize the embedding process. The experiments indicate that the approach is suitable for medical application because of its robustness. KeywordsPerceptual Hash; 3D reconstruction; Visual feature vector; Arnold scrambling;3D-DFT

Visual tracking based on improved foreground detection and perceptual hashing

Perceptual hashing is widely used to search or match similar images for digital forensics and cybercrime study. Unfortunately, the robustness of perceptual hashing algorithms is not well understood in these contexts. In this paper, we examine the robustness of perceptual hashing and its dependent security applications both experimentally and empirically. We first develop a series of attack algorithms to subvert perceptual hashing based image search. This is done by generating attack images that effectively enlarge the hash distance to the original image while introducing minimal visual changes. To make the attack practical, we design the attack algorithms under a black-box setting, augmented with novel designs (e.g., grayscale initialization) to improve the attack efficiency and transferability. We then evaluate our attack against the standard pHash as well as its robust variant using three different datasets. After confirming the attack effectiveness experimentally, we then empirically test against real-world reverse image search engines including TinEye, Google, Microsoft Bing, and Yandex. We find that our attack is highly successful on TinEye and Bing, and is moderately successful on Google and Yandex. Based on our findings, we discuss possible countermeasures and recommendations.

In this paper, we propose a perceptual image hash algorithm based on cascade algorithm, which can be applied in image authentication, retrieval, and indexing. Image perceptual hash uses for image retrieval in sense of human perception against distortions caused by compression, noise, common signal processing and geometrical modifications. The main disadvantage of perceptual hash is high time expenses. In the proposed cascade algorithm of image retrieval initializes with short hashes, and then a full hash is applied to the processed results. Computer simulation results show that the proposed hash algorithm yields a good performance in terms of robustness, discriminability, and time expenses.

Abstract. Among the immovable cultural relics such as grottoes, stone carvings of the same period usually show similar artistic styles and repetitive statues. Through the study of the similarity between cultural relics in the same period, we can have reference value for the historical significance, artistic characteristics and cultural relics restoration of cultural relics. The traditional discrimination of cultural relics similarity often depends on the subjective experience judgment of experts, which is time-consuming and inefficient. Often, different experts may issue different conclusions, the lack of convincing objective evaluation basis, can not provide effective scientific support for the protection and restoration of cultural relics. In order to provide objective criteria for evaluating the similarity of cultural relics and avoid the interference of human factors, this paper proposes the concept of similarity index of cultural relics based on perceptual Hash (pHsah) algorithm. For orthophoto images of cultural relics with similarity index within the threshold, the SIFT operator is further used to find the corresponding feature points. This paper takes the Buddha statues in Yungang Grottoes as the research object, objectively calculates the similarity index of cultural relics, combines the pHash algorithm and Sift operator, realizes the objective quantitative discrimination of cultural relics similarity, effectively avoids the subjective influence of experts on the judgment of cultural relics similarity.

This paper presents a new perceptual image hashing approach that exploits the image color information using hypercomplex (quaternionic) representations. Unlike grayscale-based techniques, the proposed approach preserves the color interaction between the image components that have a significant contribution in the generated perceptual image hash codes. Having a robust image hash function optimizes a wide range of applications including content-based retrieval, image authentication, and image watermarking. Initially, the input color image is processed in a “holistic” manner using the hypercomplex representation where the red, green and blue (RGB) components are handled as a single entity. Then, non-overlapping 8 × 8 image blocks are processed using the Quaternion Fourier transform (QFT). Binary image hash codes are generated by comparing the block mean frequency energy to the global mean frequency energy. For retrieval purposes, the Hamming distance (HD) is used as the comparison metric to retrieve perceptually similar images. The performance of the proposed perceptual hashing for color image is compared to that based on the conventional complex Fourier transform (CFT). Simulation results clearly indicate the superior retrieval performance of the proposed QFT-based perceptual hashing technique in term of HD values of intra-and inter-class image samples. Moreover, the performance improvement of the QFT-based technique is achieved at a computational complexity similar to the CFT-based scheme.

According to the characteristics of agriculture image, new image recognition scheme and image authentication scheme were designed, which based on perceptual hash algorithm. Some tomato leaf diseases pictures were used to achieve image perceptual hash feature extraction. And the experimental results show that the same diseases images have closer perceptual hash characteristics.

Image retrieval is a prominent subject of study in the fields of image processing and computer vision. With its application in various domains, such as logo search, product search or general image search in Google, Bing, etc., image retrieval has received significant attention for many years. In this work, we study and investigate a framework that leverages visual transferring fea-tures and hashing algorithms for the purpose of finding similar images in a dataset. The key idea of our solution is to find the answer to the following question: “How can we convert an image into binary code and search it more efficiently in a large-scale dataset?”. To achieve this pur-pose, we use pretrained CNN models from ImageNet for image representation and then convert them into binary code by using hashing algorithms. These images in the dataset are represented by binary codes, and the Hamming distance is used to find the images in the dataset that are in-dexed. To demonstrate the robustness of the system, we systematically tested the performance of the system based on speed with raw indexing and hashing indexing on 4 datasets: CIFAR-10, Caltech-101, Oxford-102-Flowers, and MS-COCO 2017. The experimental results show that lo-cal sensitive hashing (LSH) algorithms with 2,048 bits in binary code demonstrate the same or greater precision than raw indexing. Furthermore, the findings show that the MobileNet architec-ture consistently outperforms other architectures across these datasets, effectively balancing speed and precision.