Discrete Cosine Transform Domain Research Articles

Robust Image Hashing via CP Decomposition and DCT for Copy Detection

Copy detection is a key task of image copyright protection. This article proposes a robust image hashing algorithm by CP decomposition and discrete cosine transform (DCT) for copy detection. The first contribution is the third-order tensor construction with low-frequency coefficients in the DCT domain. Since the low-frequency DCT coefficients contain most of the image energy, they can reflect the basic visual content of the image and are less disturbed by noise. Hence, the third-order tensor construction with the low-frequency DCT coefficients can ensure robustness of our algorithm. Another contribution is the application of the CP decomposition to the third-order tensor for learning a short binary hash. As the factor matrices learned from the CP decomposition can preserve the topology of the original tensor, the binary hash derived from the factor matrices can reach good discrimination. Lots of experiments and comparisons are done to validate effectiveness and advantage of our algorithm. The results demonstrate that our algorithm has superior classification and copy detection performances than several baseline algorithms. In addition, our algorithm is also better than some baseline algorithms with regard to hash length and computational time.

JPEG Quantized Coefficient Recovery via DCT Domain Spatial-Frequential Transformer.

JPEG compression adopts the quantization of Discrete Cosine Transform (DCT) coefficients for effective bit-rate reduction, whilst the quantization could lead to a significant loss of important image details. Recovering compressed JPEG images in the frequency domain has recently garnered increasing interest, complementing the multitude of restoration techniques established in the pixel domain. However, existing DCT domain methods typically suffer from limited effectiveness in handling a wide range of compression quality factors or fall short in recovering sparse quantized coefficients and the components across different colorspaces. To address these challenges, we propose a DCT domain spatial-frequential Transformer, namely DCTransformer, for JPEG quantized coefficient recovery. Specifically, a dual-branch architecture is designed to capture both spatial and frequential correlations within the collocated DCT coefficients. Moreover, we incorporate the operation of quantization matrix embedding, which effectively allows our single model to handle a wide range of quality factors, and a luminance-chrominance alignment head that produces a unified feature map to align different-sized luminance and chrominance components. Our proposed DCTransformer outperforms the current state-of-the-art JPEG artifact removal techniques, as demonstrated by our extensive experiments.

An ensemble learning approach for resampling forgery detection using Markov process

Resampling is an extremely well-known technique performed for Image forgery detection. It includes the changes in the content of a picture in terms of rotation, stretching/zooming, and shrinking, to frame a forged picture that is a localized forgery in comparison to the original picture. With the wrong intention, resampling forgery has been increased day by day, and its negative impact has been increased in criminology, law enforcement, forensics, research etc. Accordingly, the interest in the algorithm of image resampling forgery detection is significantly developed in image forensics. In this paper, a novel image resampling forgery detection technique has been proposed. In the proposed technique, two types of Markov feature with spatial and Discrete Cosine Transform domains have been extracted to recognize the resampling operation. The spatial domain gives the information for the distribution of the pixels and DCT gives the edge information. Further, these Markov features are consolidated. Due to high dimensionality hard thresholding technique is used for reducing the dimensionality. Then, these Markov features are applied to the set of models of different classifiers. With the utilization of classifiers, weighted majority voting values have been calculated during the ensemble classification. Unlike the other techniques, these weighted voting boundaries have been consequently balanced during the training process until the best accuracy has been obtained. However, it is very difficult to get best accuracy so for getting best accuracy this research needs to do lots of iterations and trained the dataset. For the comparative study very few research has been found for this resampling forgery technique with different interpolation techniques and classifier. Still, comparison has been done with some latest research work. The comparative analysis shows that the proposed ensemble learning-based algorithm provides the best outcomes with the accuracy of 99.12% for bicubic, 98.89% for bilinear, and 98.23% for lanczos3 kernel with considerably less complexity and high speed in comparison to prior techniques which are using single support vector machine for classification. Moreover, the proposed algorithm also detects a very low probability of error of 0.44% and detects the type of interpolation kernel, size of the forgery, and the type of resampling, whether it is up sampling and down sampling, using Graphical User Interface which has not been detected previously with multiple forgery detection.

Robust Image Steganography: Hiding Messages in Frequency Coefficients

Steganography is a technique that hides secret messages into a public multimedia object without raising suspicion from third parties. However, most existing works cannot provide good robustness against lossy JPEG compression while maintaining a relatively large embedding capacity. This paper presents an end-to-end robust steganography system based on the invertible neural network (INN). Instead of hiding in the spatial domain, our method directly hides secret messages into the discrete cosine transform (DCT) coefficients of the cover image, which significantly improves the robustness and anti-steganalysis security. A mutual information loss is first proposed to constrain the flow of information in INN. Besides, a two-way fusion module (TWFM) is implemented, utilizing spatial and DCT domain features as auxiliary information to facilitate message extraction. These two designs aid in recovering secret messages from the DCT coefficients losslessly. Experimental results demonstrate that our method yields significantly lower error rates than other existing hiding methods. For example, our method achieves reliable extraction with 0 error rate for 1 bit per pixel (bpp) embedding payload; and under the JPEG compression with quality factor QF=10, the error rate of our method is about 22% lower than the state-of-the-art robust image hiding methods, which demonstrates remarkable robustness against JPEG compression.

DRRU-Net: DCT-Coefficient-Learning RRU-Net for Detecting an Image-Splicing Forgery

In this paper, we propose a lightweight deep learning network (DRRU-Net) for image-splicing forgery detection. DRRU-Net is an architecture that combines RRU-Net for learning the visual content of images and image acquisition artifacts, and a JPEG artifact learning module for learning compression artifacts in the discrete cosine transform (DCT) domain. The backbone model of a network based on pre-training, such as CAT-Net, a representative network for image forgery detection, has a relatively large number of parameters, resulting in overfitting in a small dataset, which hinders generalization performance. Therefore, in this paper, the learning module is designed to learn the characteristics according to the DCT domain in real time without pre-training. In the experiments, the proposed network architecture and training method of DRRU-Net show that the network parameters are smaller than CAT-Net, the forgery detection performance is better than that of RRU-Net, and the generalization performance for various datasets can be improved.

Decoding Algorithms and HW Strategies to Mitigate Uncertainties in a PCM-Based Analog Encoder for Compressed Sensing

Analog In-Memory computing (AIMC) is a novel paradigm looking for solutions to prevent the unnecessary transfer of data by distributing computation within memory elements. One such operation is matrix-vector multiplication (MVM), a workhorse of many fields ranging from linear regression to Deep Learning. The same concept can be readily applied to the encoding stage in Compressed Sensing (CS) systems, where an MVM operation maps input signals into compressed measurements. With a focus on an encoder built on top of a Phase-Change Memory (PCM) AIMC platform, the effects of device non-idealities, namely programming spread and drift over time, are observed in terms of the reconstruction quality obtained for synthetic signals, sparse in the Discrete Cosine Transform (DCT) domain. PCM devices are simulated using statistical models summarizing the properties experimentally observed in an AIMC prototype, designed in a 90 nm STMicroelectronics technology. Different families of decoders are tested, and tradeoffs in terms of encoding energy are analyzed. Furthermore, the benefits of a hardware drift compensation strategy are also observed, highlighting its necessity to prevent the need for a complete reprogramming of the entire analog array. The results show >30 dB average reconstruction quality for mid-range conductances and a suitably selected decoder right after programming. Additionally, the hardware drift compensation strategy enables robust performance even when different drift conditions are tested.

Log-Spectral Amplitude and Spectral Polarity Estimation in Short-Time Discrete Cosine Transform Domain

Single-channel speech enhancement based on short-time spectral amplitude (STSA) estimation often uses the unmodified phase spectrum for speech re-synthesis, thereby introducing undesired artifacts to the enhanced speech. Using discrete Cosine transform (DCT) instead of discrete Fourier transform (DFT) reduces the effects of such issues because the consequences of using noisy DCT polarities for speech re-synthesis are less severe than using the noisy DFT phases. Although DFT-based STSA estimators have been adequately studied in the past, such estimators have not sufficiently been developed for the DCT domain. This study aims to demonstrate the superiority of DCT representation in STSA estimation-based speech enhancement. To achieve this, we first derive the DCT-based STSA estimator which minimizes the mean squared error (MSE) of the log-spectral amplitudes (LSA). We then propose a novel DCT polarity estimator to be used in combination with the STSA estimator. The clean speech DCT coefficients are modeled by a Gaussian or a Laplace density and the noise DCT coefficients are modeled by a Gaussian density. To assess the enhanced speech, objective and subjective quality measures are employed. Results show that the new estimators performed better and are widely preferred by listeners over the corresponding DFT-based estimators. Moreover, the proposed STSA estimators can be expressed in the closed-form, whereas the DFT-based estimator with super-Gaussian speech prior has no closed-form solutions.

Action recognition based on discrete cosine transform by optical pixel-wise encoding

The framework provides a novel pipeline for action recognition. The action recognition task classifies the action label of the scene. High-speed cameras are commonly used to generate high frame-rate videos for capturing sufficient motion information. However, the data volume would be the bottleneck of the system. With the insight that the discrete cosine transform (DCT) of video signals reveals the motion information remarkably, instead of obtaining video data as with traditional cameras, the proposed method directly captures a DCT spectrum of video in a single shot through optical pixel-wise encoding. Considering that video signals are sparsely distributed in the DCT domain, a learning-based frequency selector is designed for pruning the trivial frequency channels of the spectrum. An opto-electronic neural network is designed for action recognition from a single coded spectrum. The optical encoder generates the DCT spectrum, and the rest of the network jointly optimizes the frequency selector and classification model simultaneously. Compared to conventional video-based action recognition methods, the proposed method achieves higher accuracy with less data, less communication bandwidth, and less computational burden. Both simulations and experiments demonstrate that the proposed method has superior action recognition performance. To the best of our knowledge, this is the first work investigating action recognition in the DCT domain.

Deep-Learning-Based Gas Leak Source Localization From Sparse Sensor Data

In this article, we address the problem of estimating the location of gas leak sources using sparse unreliable spatio-temporal chemical sensor data. We pose the task of estimating the underlying gas signal and predicting the source location as an inverse problem. For this purpose, we develop a novel deep-learning projection-based framework. We incorporate traditional projection-onto-convex-sets (POCS) iteration in the structure of the deep model to obtain a regularized solution that conforms to our prior knowledge of the spatio-temporal structure of the gas concentration distribution. We use discrete cosine transform (DCT) layers to model the smooth nature of the gas plume signal. In the DCT domain, we project the feature maps onto a low-pass region, whose boundary is determined during training using the backpropagation algorithm. This operation is equivalent to projecting onto a convex set. Furthermore, these projection operations are embedded in the nonlinear structure of a convolutional neural network. We address two different types of data: methane–propane leak from industrial plants and isopropyl alcohol (isopropanol) vapor leak in an indoor environment. Experimental results are presented. Our results show that we can obtain a smooth estimate of the underlying gas signal while obtaining a good source location prediction with high accuracy.

A Dual-Adaptive Approach Based on Discrete Cosine Transform for Removal of ECG Baseline Wander

Removal of baseline wander (BW) is an important preprocessing step before manually or automatically interpreting electrocardiogram (ECG) records. It is a challenging issue to fully remove BW while preserving original clinical information because BW is usually mingled with low-frequency ECG components. A dual-adaptive approach based on discrete cosine transform (DCT) is presented in this study. Firstly, the cardiac fundamental frequency (CFF) of ECGs is accurately calculated through DCT domain analysis. Secondly, DCT coefficients of ECGs, whose frequencies are below CFF, are used to construct an amplitude vector in which the optimal cut-point between BW and ECGs is distinctly reflected. Finally, a new filtering technique based on DCT is exploited to suppress BW with its cutoff frequency adjusted to the optimal cut-point. The proposed method is applied to both real ECG records and simulated ECGs with its results compared to those of three previous methods published in the literature. The experimental results show that substantial improvements in performance can be achieved when adopting this dual-adaptive approach.

Envelope Detection by Shannon Energy Calculation in DCT Domain and DFS-Based Notch Filter for Interference Mitigation in GNSS Receivers

A new pre-correlation technique to enhance the Global Navigation Satellite Systems (GNSS) receivers, against the continuous wave interferences (CWI), is presented. Accordingly, the detection and the localisation procedure are constituted of many steps. First, the discrete cosine transform (DCT) is applied on the contaminated signal. Next, the Shannon-energy envelope detector, in the DCT-domain, is accomplished. Then, all envelope magnitudes above a predefined threshold, representing the interference components, are localized in the frequency domain. The following step consists in the use of the discrete Fourier series (DFS) technique to calculate the corresponding contributing harmonics of the CW interferences. Finally, the interference is reduced efficiently by a subtraction of its approximated version from the original contaminated signal. The results provided from the simulation prove that the DFS-based notch filter in terms of signal quality restoration, for both single-tone and multi-tone, is of superior performance compared to the classical notch filtering.

A New Highly Secure Optical Image Security Technique Using Gyrator Transform for Image Security-Related Applications

New methods and apparatuses for information security have evolved as a result of the rapid expansion of optical information processing. Security is one of the major issues in digital image transmission because it can deliver very secret information to any corresponding agency such as the military, biomedical, and security agencies. Previously, various techniques are proposed to perform optical image encryption techniques using different transformation and pixel-level techniques. Each work has its advantages and disadvantages in terms of computational complexity, security level, flexibility, quality, and so on. To overcome the security issues present in the previous works, a novel optical image encryption standard is proposed in this paper. This work uses information hiding followed by image encryption using Gyrator Transform (GT) using mean gradient key-based block swapping techniques. The main advantage of this work is that the key generation is dynamic and it depends upon the pixel intensity of 8 × 8 blocks. Secret information hiding is performed in the Discrete Cosine Transform (DCT) domain to protect the data against noise attacks. To analyze the performance, various evaluation metrics are used to measure the quality of the decrypted image under various distortions such as cropping and rotation. The robustness of information hiding is analyzed using a noise attack on the received image. This work achieved 45.6 dB of Peak Signal-to-Noise Ratio (PSNR) and 0.965 of Structural Similarity Index (SSIM), which is the best when compared to the conventional image encryption standards.

Single Image Super-Resolution with Arbitrary Magnification Based on High-Frequency Attention Network

Among various developments in the field of computer vision, single image super-resolution of images is one of the most essential tasks. However, compared to the integer magnification model for super-resolution, research on arbitrary magnification has been overlooked. In addition, the importance of single image super-resolution at arbitrary magnification is emphasized for tasks such as object recognition and satellite image magnification. In this study, we propose a model that performs arbitrary magnification while retaining the advantages of integer magnification. The proposed model extends the integer magnification image to the target magnification in the discrete cosine transform (DCT) spectral domain. The broadening of the DCT spectral domain results in a lack of high-frequency components. To solve this problem, we propose a high-frequency attention network for arbitrary magnification so that high-frequency information can be restored. In addition, only high-frequency components are extracted from the image with a mask generated by a hyperparameter in the DCT domain. Therefore, the high-frequency components that have a substantial impact on image quality are recovered by this procedure. The proposed framework achieves the performance of an integer magnification and correctly retrieves the high-frequency components lost between the arbitrary magnifications. We experimentally validated our model’s superiority over state-of-the-art models.

Convolutional Neural Networks with Discrete Cosine Transform Features

The Discrete Cosine Transform (DCT) exposes features of an image that are not evident in the original image's spatial domain. This brief contribution proposes a Convolutional Neural Network architecture that combines features from the spatial domain and the DCT domain to improve image classification performance with negligible overhead.

Elastic Full-Waveform Inversion Using Both the Multiparametric Approximate Hessian and the Discrete Cosine Transform

We propose seismic elastic full-waveform inversion (EFWI) using both the multiparametric approximate Hessian and the discrete cosine transform (DCT). EFWI is a promising technology for obtaining physical parameters. EFWI using the multiparametric approximate Hessian can suppress crosstalk artifacts for each physical parameter, but the computational burden increases as the number of physical parameters considered increases. In this study, to reduce the computational burden, DCT was used to compress the model parameters and accelerate EFWI in the truncated DCT domain. EFWI using DCT is possible to increase the calculation efficiency by reducing the total number of unknown variables. We implemented EFWI using monoparametric Hessian and multiparametric Hessian, which reduced the computational burden using DCT and conducted tests through numerical experiments using each Hessian. In numerical result, despite using a small number of DCT coefficients, we confirmed that contamination due to crosstalk artifacts was suppressed when EFWI was performed using the multiparametric approximate Hessian.

A DCT Fractional Bit Replacement Based Dual Watermarking Algorithm for Image Authentication

Abstract: Watermarking is a process of embedding a message inside a digital signal like an image, video or text. It is used for several key reasons such as authenticity verification, ownership recognition and hidden communication. In this paper, we discuss about image watermarking, where secret messages are stored in images. Introduction: We propose a dual watermarking approach, which is based on Discrete Cosine Transform, Discrete Wavelet Transform and Singular Value Decomposition methods. This paper considers one watermark as robust and other water mark as fragile. Method: The robust watermark is embedded in Discrete Wavelet Transform- Singular Value Decomposition - domain and is used to transmit hidden messages. The fragile watermark is embedded in Discrete Cosine Transform domain and is used for verification of secret message of the robust watermark. The proposed algorithm is tested in the experimental results section and shows promising results against denoising, rotation, translation and cropping attacks. Result: The results show that the performance of the proposed algorithm in terms of mean squared error, structural similarity and peak signal to noise ratio is S4considerable as compared with the existing methods. Discussion: We present the comparison results with Himanshu et. al. in table 10, from which we can see that our method performs better with gaussian noise and rotational attack only lacking with Salt and Pepper noise. Fig. 7 and Fig. 8, in terms of resulting PSNR shows the variation of noise variance and degree of rotation. From the graphs it is evident that out method performs better against Gaussian and rotational attack. Conclusion: In this paper a dual watermarking method is proposed in which one watermark is fragile which is called as authentication watermark whereas the other watermark is robust and is called as the information watermark. The authentication watermark is embedded in the fractional part of DCT domain in the cover image and the information watermark is embedded in the diagonal vector of the LL sub-band.

Reducing reconstruction error of classified textural patches by integration of random forests and coupled dictionary nonlinear regressors: with applications to super-resolution of abdominal CT images.

Random forests and dictionary-based statistical regressions have common characteristics, including non-linear mapping and supervised learning. To reduce the reconstruction error of high-resolution images, we integrate random forests and coupled dictionary learning. Textural differences of image blocks are considered by the classification of patches using an Auto-Encoder network. The proposed algorithm partitions an input LR image by 5 × 5 blocks and classifies training patches into six categories. A single random forest regressor is then trained corresponding to each class. The output of an RF is considered as an initial estimate of the HR slice. If a slice's representation is sparse in the Discrete Cosine Transform domain, the initial reconstructed image is further improved by a coupled dictionary. In this study, we applied our method to abdominal CT scans and compared them to conventional and recent researches. We achieved an average improvement of 0.06 (2.37) using the SSIM (PSNR) index compared to the random forest + dictionary learning method. The low standard deviation of the results reveals the stability of the proposed method as well. The proposed algorithm depicts the effectiveness of classifying image patches and individual treatment of each class.

Low‐rank tensor completion with sparse regularization in a transformed domain

AbstractTensor completion is a challenging problem with various applications, especially in recovering incomplete visual data. Considering a color image or gray video as a three‐dimensional tensor, many related models based on the low‐rank prior of the tensor have been proposed. However, the low‐rank prior may not be enough to recover the original tensor from the observed incomplete tensor. In this paper, we propose a tensor completion method to recover color images and gray videos by exploiting both the low‐rank and sparse prior of the observed tensor. Specifically, the tensor completion task can be formulated as a low‐rank minimization problem with a sparse regularizer. The low‐rank property is depicted by the tensor truncated nuclear norm based on tensor singular value decomposition which is a better approximation of tensor tubal rank than tensor nuclear norm. While the sparse regularizer is imposed by a ℓ1‐norm in a discrete cosine transformation domain, which can better employ the local sparse property of the incomplete data. To solve the optimization problem, we employ an alternating direction method of multipliers in which we only need to solve several subproblems which have closed‐form solutions. Substantial experiments on real‐world images and videos show that the proposed method has better performances than the existing state‐of‐the‐art methods.

Maximizing embedding capacity for speech steganography: a segment-growing approach

It has been proven that the higher the correlation level between samples in the time-domain of a digital signal, the stronger the energy com paction property in the Discrete Cosine Transform (DCT) domain. This paper aims to investigate the limits of the DCT energy compaction property in speech signals by segmenting the cover speech signal into correlated segments and hide in each segment. The Hiding process is performed using a hiding strategy in spired by the Amplitude Modulation (AM) technique. Due to segmentation, the homogeneity is expected to increase which causes the energy of the signal to be strongly compacted in a few critical DCT coefficients, and therefore, a substantial amount of insignificant DCT coefficients can be replaced with the secret data without sacrificing the quality of the signal. Experimental results have proven the effectiveness of the proposed scheme which outperforms other speech steganography techniques recently published in the literature.

A novel audio watermarking scheme based on fuzzy inference system in DCT domain

Digital watermarking technology provides an effective potential solution to copyright protection and authentication of digital media. In this article, a new design of audio watermarking is introduced which is able to make compromise between transparency, robustness, and capacity by means of the synergy between fuzzy inference system, Singular Value Decomposition (SVD), and Fibonacci’s sequence in Discrete Cosine Transform (DCT). In the embedding phase, the proposed method, first of all, finds proper segments for inserting watermark data by helping fuzzy inference system with energy, zero-crossing rate (ZCR), and music edge features. Then, the watermark bits are embedded in the suitable segments based on collaboration of SVD technique and Fibonacci sequence in DCT domain. The proposed watermark extraction is performed in blind manner. The results on five Blues, Electronic, Classic, Jazz and Rock audio files show that the proposed method has high transparency (in average SNR = 49.80 dB) with payload of 598.34 bps. Moreover, robustness tests against Stirmark attacks show that the average of error rate is 1.3644, which means the proposed scheme has high stability in the digital signal processing attacks.