Narrow Results

Compressed images are frequently used to accomplish computer vision tasks. There is an extensive use of traditional image compression standards including JPEG 2000. However, they would not consider the present solution. We determined a new image compression model that was inspired by the existing research on the medical image compression model. Here, the images are filtered at the preprocessing step to eradicate the noises that exist. The images are then decomposed using discrete wavelet transform (DWT). The outcome is then vectored quantized. In this step, we employ optimisation-assisted fuzzy $c$-means clustering for vector quantisation (VQ) with codebook generation. Considering this as an optimisation issue, a new hybrid optimisation algorithm called Bald Eagle Updated Pelican Optimization with Geometric Mean weightage (BUPOGM) is introduced to solve it. The algorithm is a combination of pelican optimisation and bald eagle optimisation, respectively. Quantised coefficients are finally encoded via the Huffman encoding process, and the compressed image is represented by the resultant bits. The outcome of the proposed work is satisfactory as it performs better than the other state-of-the-art methods.

Epilepsy is a chronic neurological disorder characterized by sudden and apparently unpredictable seizures. A system capable of forecasting the occurrence of seizures is crucial and could open new therapeutic possibilities for human health. This paper addresses an algorithm for seizure prediction using a novel feature — diffusion distance (DD) in intracranial Electroencephalograph (iEEG) recordings. Wavelet decomposition is conducted on segmented electroencephalograph (EEG) epochs and subband signals at scales 3, 4 and 5 are utilized to extract the diffusion distance. The features of all channels composing a feature vector are then fed into a Bayesian Linear Discriminant Analysis (BLDA) classifier. Finally, postprocessing procedure is applied to reduce false prediction alarms. The prediction method is evaluated on the public intracranial EEG dataset, which consists of 577.67h of intracranial EEG recordings from 21 patients with 87 seizures. We achieved a sensitivity of 85.11% for a seizure occurrence period of 30min and a sensitivity of 93.62% for a seizure occurrence period of 50min, both with the seizure prediction horizon of 10s. Our false prediction rate was 0.08/h. The proposed method yields a high sensitivity as well as a low false prediction rate, which demonstrates its potential for real-time prediction of seizures.

In order to improve the performance of mass segmentation on mammograms, an intelligent algorithm is proposed in this paper. It establishes two mass models to characterize the various masses, and the ones in the denser tissue are represented with Model I, while the ones in the fatty tissue are represented with Model II. Then, it uses iterative thresholding to extract the suspicious area, as well as the rough regions of those masses matching Model II, and applies a DWT-based technique to locate those masses matching Model I, which are hidden in the high gray-level intensity and contrast area. A region growing process restricted by Canny edge detection is subsequently used to segment the rough regions of those masses matching Model I, and finally snakes are carried out to find all the mass regions roughly extracted above. Thirty patient cases with 60 mammograms and 107 masses were used for evaluation, and the experimental result has demonstrated the algorithm's better performance over the conventional methods.

Image watermarking techniques have been widely used for copyright protection, broadcast monitoring, and data authentication. In this paper, we present a novel watermarking scheme which allows automatic selection of multiple regions-of-interest (ROIs) with robustness against geometric distortion. The fidelity of watermarked images is ensured by preserving salient foreground objects. The proposed scheme achieves watermarking robustness by geometric rectification, which is based on matching feature points between the salient foreground objects of a host image and its distorted stego-image. Experimental results show that the proposed technique can successfully obtain high fidelity and high robustness on an image dataset of multiple salient foreground objects.

To remove image noise without considering the noise model, a dual-tree wavelet thresholding method (CDOA-DTDWT) is proposed through noise variance optimization. Instead of building a noise model, the proposed approach using the improved chaotic drosophila optimization algorithm (CDOA), to estimate the noise variance, and the estimated noise variance is utilized to modify wavelet coefficients in shrinkage function. To verify the optimization ability of the improved CDOA, the comparisons with basic DOA, GA, PSO and VCS are performed as well. The proposed method is tested to remove addictive noise and multiplicative noise, and denoising results are compared with other representative methods, e.g. Wiener filter, median filter, discrete wavelet transform-based thresholding (DWT), and nonoptimized dual-tree wavelet transform-based thresholding (DTDWT). Moreover, CDOA-DTDWT is applied as pre-processing utilization for tracking roller of mining machine as well. The experiment and application results prove the effectiveness and superiority of the proposed method.

Underwater image capturing is a challenging task due to attenuation of light in water. Scattering and absorption are the results of light attenuation which lead to faded colors and reduced contrast of images, respectively. To deal with these issues and to provide better visual quality image, various enhancement methods have been proposed. This paper proposes the Dual Domain-based Underwater Image Enhancement (DDUIE) method. DDUIE method provides contrast stretching in approximation band of discrete wavelet transformed image followed by intensity adjustment of different color channels in spatial domain. To further improve the color quality, the image is processed in HSV (Hue–Saturation–Value) color space. Result analysis indicates better results for DDUIE method over state-of-the-art methods. Subjective results of DDUIE method show minimization of the bluish-green effect and reduction of nonuniform illumination up to a certain extent. These lead to enhanced color and image details. Quantitative results show that the Underwater Image Quality Measure (UIQM) and Underwater Color Image Quality Evaluation (UCIQE) values between 1 and 2 and between 0 and 1 have been achieved, respectively, which significantly illustrate that images have been enhanced efficiently and also entropy values between 7 and 8 depict the effectiveness of the proposed method in terms of image details.

The watermark embedded by traditional methods is easy to be lost under some attacks. To overcome this problem, this study proposes a novel method based on DWT. It adopts a digital audio watermarking state-switching system which optimizes DWT coefficients doubly. Firstly, it combines the quantization-embedding system and the weights of DWT coefficients with SNR to obtain an optimization model for watermarking. Next, the Lagrange principle, Hessian matrix, and minimum energy play three essential roles to obtain the optimal DWT coefficients and weights. Moreover, the almost invariant feature of the optimal weights holds demonstrating resistance to amplitude scaling. Compared with similar algorithms, the experimental results verify that the embedded audio in the proposed method has higher signal-to-noise ratio (SNR) and lower bit error rate (BER). At the same time, it indicates stronger robustness against various attacks, such as re-sampling, amplitude scaling, and mp3 compression.

Dedicated hardware for “Discrete Wavelet Transform” (DWT) is at high demand for real-time imaging operations in any standalone electronic devices, as DWT is being extensively utilized for most of the transform-domain imagery applications. Various DWT algorithms exist in the literature facilitating its software implementations which are generally unsuitable for real-time imaging in any stand-alone devices due to their power intensiveness and huge computation time. In this paper, a convolutional DWT-based pipelined and tunable VLSI architecture of Daubechies 9/7 and 5/3 DWT filter is presented. Our proposed architecture, which mingles the advantages of convolutional and lifting DWT while discarding their notable disadvantages, is made area and memory efficient by exploiting “Distributed Arithmetic’ (DA) in our own ingenious way. Almost 90% reduction in the memory size than other notable architectures is reported. In our proposed architecture, both the 9/7 and 5/3 DWT filters can be realized with a selection input, “mode”. With the introduction of DA, pipelining and parallelism are easily incorporated into our proposed 1D/2D DWT architectures. The area requirement and critical path delay are reduced to almost 38.3% and 50% than that of the latest remarkable designs. The performance of the proposed VLSI architecture also excels in real-time applications.

This paper presents a one-level decomposition Haar Discrete Wavelet Transform (DWT) architecture using a 4:2 compressor and carry propagate adder. In Haar DWT architecture, coefficient multiplication is an essential operation. The Haar coefficient multiplication $((x_{\mathrm{\text{even}}}\pm x_{\mathrm{\text{odd}}})\ast 0.707106)$ is implemented with $Radix-2^r$ multiplier and the generated partial products are represented with sign power of two (SPT) terms. The addition of SPT terms is computed with a 4:2 compressor and the final sum is computed with CPA. A $Radix-2^r$ multiplier with 4:2 compressor technique is used to improve energy and delay. Compared to the previous architectures, the proposed architecture gives reduction in area, power, and delay. The proposed Haar wavelet architecture is implemented in gate-level Verilog HDL and synthesized with UMC 90-nm technology using Cadence RC compiler. When compared to the existing designs, the proposed architecture Haar DWT architecture synthesis results show reduction in latency of 32.32% and 31.46% of circuit area.

The prediction of price trends in the stock market has always been a hot research topic in the financial field. However, due to the high instability and volatility of stock prices, it is very difficult to accurately predict stock trends. How to remove the noise of stock data, extract effective features, and pursue maximum value returns has always been a challenge. This paper proposes a hybrid model (DWT-DQN) that combines discrete wavelet transform with deep reinforcement learning to improve the accuracy and return rate of stock predictions. First, the model captures price fluctuation information on different scales by performing discrete wavelet transformation on the difference between long- and short-term moving averages of stock prices, and well extracts the changing characteristics of stock price data in the time domain and frequency domain. Then the feature data are input into the built DQN network for model training. The network can select the optimal trading action based on market status and historical experience and returns. At the same time, during the data sampling process, an attention mechanism is introduced to allow the model to further learn in the direction of maximizing returns. Through testing and verification on SSEC, HSI, NDX and SPX data sets, experiments show that the hybrid model proposed in this paper has excellent performance in terms of accuracy and return rate.

In this paper, we present a new encryption method based on discrete wavelet transform (DWT). This method provides a number of advantages as a pseudo randomness and sensitivity due to the variation of the initial values. We start by decomposing the image with spatial reconstruction by DWT, followed by preformation by fractional chaotic cryptovirology and Henon map keys for space encryption. Bearing in mind the rapid pace of change in the fields of fractional chaotic cryptovirology, our findings suggest that the proposed method is too powerful relative to the key sensitivity, histogram, entropy and correlation coefficient.

Recently, the emotional state recognition of humans via Electroencephalogram (EEG) is one of the emerging topics that grasp the attention of researchers too. This EEG based recognition is normally an effective model for many of the real-time applications, especially for disabled people. A number of researchers are in progress to make the recognition model more effective in terms of accurate emotion recognition. However, it is not so satisfactory in the precise accurate progressing. Hence this paper intends to recognize the human emotional states or affects through EEG signals by adopting advanced features and classifier models. In the first stage of recognition procedure, this paper exploits 2501 (EMCD) and Wavelet Transformation to represent the EEG signal in low dimension as well as descriptive. By EMCD, the EEG redundancy can be neglected, and the significant information can be extracted. The classification processes using the extracted features with the aid of a classifier named Deep Belief Network (DBN). The performance of the proposed Wavelet-EMCD (WE) approach is analyzed in terms of measures such as Accuracy, Sensitivity, Specificity, Precision, False positive rate (FPR), False negative rate (FNR), Negative Predictive Value (NPV), False Discovery Rate (FDR), F1Score and Mathews correlation coefficient (MCC) and proven the superiority of proposed work in recognizing the emotions more accurately.

Most of the documents use fingerprint impression for authentication. Property related documents, bank checks, application forms, etc., are the examples of such documents. Fingerprint-based document image retrieval system aims to provide a solution for searching and browsing of such digitized documents. The major challenges in implementing fingerprint-based document image retrieval are an efficient method for fingerprint detection and an effective feature extraction method. In this work, we propose a method for automatic detection of a fingerprint from given query document image employing Discrete Wavelet Transform (DWT)-based features and SVM classifier. In this paper, we also propose and investigate two feature extraction schemes, DWT and Stationary Wavelet Transform (SWT)-based Local Binary Pattern (LBP) features for fingerprint-based document image retrieval. The standardized Euclidean distance is employed for matching and ranking of the documents. Proposed method is tested on a database of 1200 document images and is also compared with current state-of-art. The proposed scheme provided 98.87% of detection accuracy and 73.08% of Mean Average Precision (MAP) for document image retrieval.

Computer-assisted colon cancer detection on the histopathological images has become a tedious task due to its shape characteristics and other biological properties. The images acquired through the histopathological microscope may vary in magnifications for better visibility. This may change the morphological properties and hence an automated magnification independent colon cancer detection system is essential. The manual diagnosis of colon biopsy images is subjective, sluggish, laborious leading to nonconformity between histopathologists due to visual evaluation at various microscopic magnifications. Automatic detection of colon across image magnifications is challenging due to many aspects like tailored segmentation and varying features. This demands techniques that take advantage of the textural, color, and geometric properties of colon tissue. This work exhibits a segmentation approach based on the morphological features derived from the segmented region. Gabor Wavelet, Harris Corner, and DWT-LBP coefficients are extracted as it should not be dependent on the spatial domain with respect to the magnification. These features are fed to the Genetically Optimized Neural Network classifier to classify them as normal and malignant ones. Here, the genetic algorithm is used to learn the best hyper-parameters for a neural network.

This paper proposes a novel method for the image interpolation problem based on two-dimensional discrete wavelet transform (DWT) with the edge preserving approach. The purpose of this method is to consider two contrasting issues of over-smoothing and creation of spurious edges at the same time, and offer a novel solution based on statistical dependencies of image sub-bands, and noise behavior. The offered method has a multi-faceted approach for the problem; by sub-band coding, it handles each 2D-DWT image sub-band with a different solution. For LH and HL sub-bands, two algorithms work together in order to preserve regularity. Area_Check algorithm is a four-phase edge-preserving algorithm that aims to recognize and interpolate separating lines of environments and edgy regions in the best possible way. On the other hand, RLS_AVG algorithm interpolates smooth surfaces of the image by keeping the regularity of the image without over-smoothing. In this regard, the offered algorithm has a great power to counter jaggies and annoying artifacts. In the end, in order to demonstrate the capability, and performance of the proposed method, the final results in various metrics are compared with the results of the most famous and the newest image interpolation methods.

In this paper, a dynamic stochastic resonance (DSR) based watermark detection technique in discrete wavelet transform (DWT) domain is presented. Pseudo random bit sequence having certain seed value is considered as a watermark. Watermark embedding is done by embedding random bits in spread-spectrum fashion to the significant DWT coefficients. Watermark detection is quantitatively characterized by the value of correlation. The performance of watermark detection is improved by DSR which is an iterative process that utilizes the internal noise present in the image or external noise which is added during attacks. Even under various noise attacks, geometrical distortions, image enhancement and compression attacks, the DSR-based random bits detection is observed to give noteworthy improvement over existing watermark detection techniques. DSR-based technique is also found to give better detection performance when compared with the suprathreshold stochastic resonance-based detection technique.

The impact of motors breakdown and failures on mobile robot motor bearing is an important concern for robot industries. For this reason, predictive motor lifetime and bearing fault classification techniques are being investigated extensively as a method of decreasing motor downtime and enhancing mobile robot reliability. With increasing attention on neural network technologies, many researchers have carried out lots of the relevant experiments and analyses, very plentiful and important conclusions are obtained. In this article, a classification method based on discrete wavelet transform (DWT) and long short-term memory network (LSTM) a proposed to find and classify fault type of mobile robot permanent magnet synchronous motor (PMSM). First, a set of mobile robot motor vibration signal were collected by the sensors. Second, the obtained vibration signal is decomposed into six frequency bands by the DWT. Haar function is selected as the mother function in the processing. The energy of every frequency band was calculated as a classification feature. Thirdly, four classification features with high classification rate are obtained. The feature vector is used as input of the neural network, and the fault type is identified by LSTM classifier with deviation unit. From the results of the experiments provided in the paper, the method can detect the fault type accurately and it is feasible and effective under different motor speed.

The Computer-Aided Diagnostic (CAD) system is an important tool that helps radiologists to provide a second opinion for the early detection of breast cancer and therefore, aids to reduce the mortality rates. In this work, we try to develop a new (CAD) system to classify mammograms into benign or malignant. The proposed system consists of three main steps. The preprocessing stage consists of noise filtering, elimination of unwanted objects and suppressing the pectoral muscle. The Seeded Region Growing (SRG) segmentation technique is applied in a triangular region that contains the pectoral muscle to localize it and extract the region of interest (ROI). The features extraction step is performed by applying the discrete wavelet transform (DWT) to each obtained ROI, and the most discriminating coefficients are selected using the discrimination power analysis (DPA) method. Finally, the classification is carried out by the support vector machine (SVM), artificial neural networks (ANN), random forest (RF) and Naive Bayes (NB) classifiers. The evaluation of the proposed system on the mini-MIAS database shows its effectiveness compared to other recently published CAD systems, and a classification accuracy of about 99.41% with the SVM classifier was obtained.

In JPEG2000 standard, the number of bit planes of wavelet coefficients to be used in encoding is dependent on the compression ratio as well as subbands. These significant wavelet bit planes can be utilized to embed bits of secret data as they are retained in the final bit stream after Tier-2 encoding. In proposed techniques, the above mentioned concept have been utilized to embed secret data bits in lowest significant bit planes of the quantized wavelet coefficients of a cover image. In first technique, secret data is converted into a series of symbols using multiple bases notational system. These bases are selected by using the degree of local variation of coefficient values of the cover image so that coefficient of a complex region can potentially carry more secret data bits as compared to coefficients of smooth region. Symbols of secret data are embedded into bit planes of significant quantized wavelet coefficients by using EMD approaches. In second technique, the secret data bits are embedded into significant quantized wavelet coefficients by using modified EMD. Experimental results show that these proposed techniques provide large embedding capacity and better visual quality stego images than existing steganography techniques applicable to JPEG2000 compressed images. It has also been shown that modified EMD-based technique is better than EMD with multiple bases notational system (MBNS)-based technique.

Dialect recognition of low resource languages is the next stage in the technological advancement in speech recognition. Traditional methods for dialects recognition such as mel frequency cesptral coefficients (MFCC) and discrete wavelet transform (DWT) work better for high resource languages, however, the performance is low when applied in low resource languages. This paper presents a new approach for Pashto dialects recognition using an adaptive filter bank with MFCC and DWT. In this approach, features are extracted using adaptive filter bank in MFCC and DWT followed by classification through hidden Markov model (HMM), support vector machines (SVM) and K-nearest neighbors (KNN). The results obtained from the proposed method are very satisfactory with an overall dialect recognition accuracy of $88\%$.