Optimized lossless audio compression using DCT energy thresholding and machine learning technique

For image data the discrete cosine transform (DCT) has comparable energy compaction capability to Karhunen-Loeve transform (KLT) which is optimal. Hence DCT has been widely accepted in various image and video compression standard such as JPEG, MPEG-2, and MPEG-4. Recently some approximate DCT’s have been reported, which can be computed much faster than the original DCT because their coefficients are either zero or the power of 2. Although the level of energy compaction is slightly degraded, the approximate DCT’s can be utilized in real time implementation of image or visual compression applications. In this paper, an approximate 8-point DCT which contains 17 non-zero power-of-2 coefficients and high energy compaction capability comparable to DCT is proposed. Transform coding experiments with several images show that the proposed transform outperforms the published works. 키워드 : 근사 DCT, 에너지 압축, 고속 구현, 변환의 직교성 Key word : Approximate DCT, Energy compaction, High speed implementation, Orthogonality of transformsJournal of the Korea Institute of Information andCommunication Engineering

Lossless image compression based on integer Discrete Tchebichef Transform

This paper presents the effective lossy and lossless color image compression algorithm with Multilayer perceptron. The parallel structure of neural network and the concept of image compression combined to yield a better reconstructed image with constant bit rate and less computation complexity. Original color image component has been divided into 8x8 blocks. The discrete cosine transform (DCT) applied on each block for lossy compression or discrete wavelet transform (DWT) applied for lossless image compression. The output coefficient values have been normalized by using mod function. These normalized vectors have been passed to Multilayer Perceptron (MLP). This proposed method implements the Back propagation neural network (BPNN) which is suitable for compression process with less convergence time. Performance of the proposed compression work is evaluated based on three ways. First one compared the performance of lossy and lossless compression with BPNN. Second one, evaluated based on different sized hidden layers and proved that increased neurons in hidden layer has been preserved the brightness of an image. Third, the evaluation based on three different types of activation function and the result shows that each function has its own merit. Proposed algorithm has been competed with existing JPEG color compression algorithm based on PSNR measurement. Resultant value denotes that the proposed method well performed to produce the better reconstructed image with PSNR value approximately increased by 21.62%.

Image forgery is the process of manipulating digital images to obscure critical information or details for personal or business gain. Nowadays, tampering and forging digital images have become frequent and easy due to the emergence of effective photo editing software and high-definition capturing equipment. Thus, several image forgery detection techniques have been developed to guarantee the authenticity and legitimacy of the images. There are several types of image forgery techniques; among them, copy-move forgery is the most common one. The paper discusses the types of image forgery and the methods proposed to detect or localize them, including Principal Component Analysis (PCA), DCT, CNN models like Encoder-Decoder, SVGGNet, MobileNet, VGG16, Resnet50, and clustering models like BIRCH. A comparison of different detection techniques is performed, and their results are also observed. Image Forgery Detection in the Medical Field is a significant area for smart health care.KeywordsCopy-move image forgerySVGGNetMobileNet-V2Balanced iterative reducing and clustering using hierarchies (BIRCH)Support vector machines (SVM)Encoder-decoderConvolutional neural network (CNN)Convolutional neural network with error level analysis (CNN_ELA)Convolutional neural network with error level analysis and sharpening pre-processing techniques (CNN_SHARPEN_ELA)Principal component analysis (PCA)Discrete cosine transform (DCT)

Image interpolation, with its image magnifying abilities, is an image processing operation of increasing importance in the fields of biology and medicine. In this paper, we present a novel image interpolation technique that utilizes the discrete cosine transform (DCT). The DCT provides for a decrease in border effects, and improves the processing speed. The advantages of this technique over the traditional Fourier-transform-based techniques stem from basic properties of DCT that it is a non-periodic, real (non-complex) transform with excellent energy compaction in the transform domain. In fact, the DCT's energy compaction property is next only to Karhunen-Loeve transform in the mean squared sense on an ensemble of images (Jain, 1989). In addition, DCT allows interpolation of small volumes (e.g., 8/spl times/8/spl times/8) which is not easily possible with an FFT-based method. Therefore, the present technique is better suited for applications such as a real-time 3D interactive maximum intensity projection, real-time 2-D image magnifier etc. More importantly, the technique can be used for the bandlimited interpolation of any digitally acquired data to minimize partial voluming artifact.

Motion-compensated temporal filtering (MCTF) based lifting implementations of various discrete wavelet transforms have recently gained a lot of interest due to their good performance in energy compaction and their ability to provide various scalability features. Although all the existing MCTF schemes are based on the wavelet transform, in this paper, we propose a temporal filter framework based on the discrete cosine transform (DCT) which is an extension of our motion compensated DCT temporal filter (MCDCT-TF). In the current work, in addition to the two-band and three-band temporal decomposition structures employed in the MCDCT-TF technique, a longer tap filter (5/3 DCT) is utilized to improve the compression gain further. Simulation results show that a three-dimensional hybrid 3D subband/DCT codec with longer tap DCT filters yields a significant improvement over our earlier 3/2 MCDCT-TF, Haar, and 5/3 wavelet filters.

This paper proposes simple and novel image compression method using transforms. Discrete cosine Transform (DCT) and Discrete Kekre Transform (DKT) are applied on image individually. Wavelet transform of DCT and DKT is generated using Kekre's algorithm of wavelet generation. Wavelet transform gives better energy compaction than individual transform. It is reflected in reconstructed image quality of wavelet transforms. Further hybridization of two transform is used and hybrid wavelet transform using DKT and DCT is generated and applied on images. It combines properties of both, Kekre transform and DCT. Hybrid wavelet transform gives lesser error than wavelet transform and individual orthogonal transform.

In this paper highly-compacted DCT coefficients (HDCT) are presented. This compactness is achieved by sorting in ascending order the data first, then by applying the Discrete Cosine transform (DCT) to the ordered data. Images are highly correlated. DCT exhibits excellent energy compaction. It will be shown that HDCT has much better energy compactness than the DCT. This has the effect of representing every ordered image with very small number of HDCT coefficients (dimensionality reduction). The compression capabilities of the HDCT are presented. HDCT is also applied to face recognition problem. Simulation results on different databases showed high average success rate of this algorithm compared to other algorithms.

This paper presents technique for classification of nail fold capillary images based on Discrete Wavelet Transform (DWT) and Discrete Cosine Transform (DCT). An approach for image enhancement and feature extraction using wavelet transform using its property of multilevel decomposition in pattern recognition application has been proposed. The main idea is to achieve better accuracy in classification by extracting more relevant features after dimensional reduction. Data compression and energy compaction is the main feature of DCT and therefore in the proposed method, DCT was applied on LL sub band image obtained from decomposition of the nail fold capillary image using DWT. A subset of the most significant coefficients was retained as the feature vector and using K Nearest Neighbor classifier, nail fold image was classified as healthy, normal and others. In this paper, classification rate of 73.3% using 500 coefficients of DCT and 70% using 5000 coefficients of DWT as feature vector has been achieved.

Recent success in discrete cosine transform (DCT) image coding is mainly attributed to recognition of the importance of data organization and representation. Currently, there are several competitive DCT-based coders such as Xiong et al.’s DCT-based embedded image coding (EZDCT), Davis and Chawla’s significance tree quantization (STQ), and Zhao et al.’s embedded zerotree image coder based on hierarchical DCT (EZHDCT). In the wavelet context, morphological representation of wavelet data has achieved the best compression performance for still image coding. The representatives are Servetto et al.’s morphological representation of wavelet data (MRWD) and Chai et al.’s significancelinked connected component analysis (SLCCA). In this paper, we first point out that the block-based DCT by proper reorganization and representation of its coefficients can have the similar characteristics to wavelet transform, such as energy compaction, crosssubband similarity, decay of magnitude across subband, etc. This finding will widen DCT applications relevant to image compression, image retrieving, image recognition and so on. We then present a novel image coder utilizing these characteristics by morphological representation of DCT coefficients (MRDCT). The experiments show that MRDCT is among the state-of-art DCT-based image coders reported in the literature. For example, for the Lena image at 0.25 bpp, MRDCT outperforms JPEG, STQ, EZDCT and EZHDCT by 1.0 dB, 1.0 dB, 0.3 dB and 0.1 dB in PSNR, respectively. This outstanding performance is achieved without using any optimal bit allocation procedure. Thus both the encoding and decoding procedure are fast. PERFORMANCE COMPARISION (PSNR [dB]) ON LENA IMAGE

We present the design, implementation, and application of several families of fast multiplierless approximations of the discrete cosine transform (DCT) with the lifting scheme called the binDCT. These binDCT families are derived from Chen's (1977) and Loeffler's (1989) plane rotation-based factorizations of the DCT matrix, respectively, and the design approach can also be applied to a DCT of arbitrary size. Two design approaches are presented. In the first method, an optimization program is defined, and the multiplierless transform is obtained by approximating its solution with dyadic values. In the second method, a general lifting-based scaled DCT structure is obtained, and the analytical values of all lifting parameters are derived, enabling dyadic approximations with different accuracies. Therefore, the binDCT can be tuned to cover the gap between the Walsh-Hadamard transform and the DCT. The corresponding two-dimensional (2-D) binDCT allows a 16-bit implementation, enables lossless compression, and maintains satisfactory compatibility with the floating-point DCT. The performance of the binDCT in JPEG, H.263+, and lossless compression is also demonstrated.

Image up-sampling using deep cascaded neural networks in dual domains for images down-sampled in DCT domain

In this paper, an algorithm for multiple watermarking based on discrete wavelet transforms (DWT), discrete cosine transform (DCT) and singular value decomposition (SVD) has been proposed for healthcare applications. For identity authentication purpose, the proposed method uses three watermarks in the form of medical Lump image watermark, the doctor signature/identification code and diagnostic information of the patient as the text watermarks. In order to improve the robustness performance of the image watermark, Back Propagation Neural Network (BPNN) is applied to the extracted image watermark to reduce the noise effects on the watermarked image. The security of the image watermark is also enhanced by using Arnold transform before embedding into the cover. Further, the symptom and signature text watermarks are also encoded by lossless arithmetic compression technique and Hamming error correction code respectively. The compressed and encoded text watermark is then embedded into the cover image. Experimental results are obtained by varying the gain factor, different sizes of text watermarks and the different cover image modalities. The results are provided to illustrate that the proposed method is able to withstand a different of signal processing attacks and has been found to be giving excellent performance for robustness, imperceptibility, capacity and security simultaneously. The robustness performance of the method is also compared with other reported techniques. Finally, the visual quality of the watermarked image is evaluated by the subjective method also. This shows that the visual quality of the watermarked images is acceptable for diagnosis at different gain factors. Therefore the proposed method may find potential application in prevention of patient identity theft in healthcare applications.

The process of sorting marble plates according to their surface texture is an important task in the automated marble plate production. Nowadays some inspection systems in marble industry that automate the classification tasks are too expensive and are compatible only with specific technological equipment in the plant. In this paper a new approach to the design of an Automated Marble Plate Classification System (AMPCS),based on different neural network input training sets is proposed, aiming at high classification accuracy using simple processing and application of only standard devices. It is based on training a classification MLP neural network with three different input training sets: extracted texture histograms, Discrete Cosine and Wavelet Transform over the histograms. The algorithm is implemented in a PLC for real-time operation. The performance of the system is assessed with each one of the input training sets. The experimental test results regarding classification accuracy and quick operation are represented and discussed. PLCs, because these devices are preferable and widely used in up-to-date automated production systems. In this paper, a new approach for design of an Automated Marble Plate Classification System (AMPCS) based on different neural network input training sets is proposed, aiming at high classification accuracy using simple processing and application of only standard devices and communication protocols. It is based on training a classification Multi-Layer-Perceptron Neural Network (MLP NN) with three different input training sets: extracted texture histograms, Discrete Cosine Transform (DCT) and Discrete Wavelet Transform (DWT) over the histograms. The algorithm is implemented in a PLC for real- time operation. The system performance is assessed with each one of the input training sets. The modeling technique performance is assessed with different training and test sets. The experimental test results regarding classification accuracy and quick operation are represented and discussed.

This paper proposes the development of a Numerical Command Recognition System of Speech Signal based on Neural Networks and DCT models. Thus, two configurations of neural networks, the Multilayer Perceptron and Learning Vector Quantization are evaluated by their performance in speech signal recognition, whose encoding is made by the mel-cepstral coefficients that are used to generate a two-dimensional time matrix by Discrete Cosine Transform (DCT). The selection of the best configuration of neural network for classification of the patterns was carried out by comparative analysis of performance of the MLP and LVQ networks through training, validation and test of the network topology and learning algorithms previously established. For demonstration of the performance of the proposed analysis methodology, the obtained results were compared with other methods of classification given by Gaussian Mixture Models (GMM) and Support Vector Machines (SVM).