Steerable Pyramid Decomposition Research Articles

Unsupervised texture classification of 3D X-ray Micro-computed Tomography images

Characterizing rock proprieties is crucial in the oilfield to evaluate hydrocarbon reserves. Several studies showed a high correlation between rock properties and textures. Therefore, we propose integrating texture information in the images to identify precisely the most representative textures in highly heterogeneous rocks to estimate their properties. First, we implemented a steerable pyramid decomposition to extract the texture features. Then, those parameters were used as input for the Self-organizing map to classify the textures. Finally, by applying several models and comparing their results, we suggested the best approach to implement for texture classification.

Fusion of Gabor filter and steerable pyramid to improve iris recognition system

<span>Iris recognition system is a technique of identifying people using their distinctive features. Generally, this technique is used in security, because it offers a good reliability. Different researchers have proposed new methods for iris recognition system to increase its effectiveness. In this paper, we propose a new method for iris recognition based on Gabor filter and steerable pyramid decomposition. It’s an efficient and accurate linear multi-scale, multi-orientation image decomposition to capture texture details of an image. At first, the iris image is segmented, normalized and decomposed by Gabor filter and steerable pyramid method. Multiple sub-band are generated by applying steerable pyramid on the input image. High frequency sub-band is ignored to eliminate noise and increase the accuracy. The method was validated using CASIA-v4 (Chinese Academy of Sciences Institute of Automation), IITD (</span><span>Indian Institute of Technology Delhi) and UPOL (University of Phoenix Online) databases. The performance of the proposed method is better than the most methods in the literature. The proposed algorithm provides accuracy of 99.99%. False acceptance rate (FAR), equal error rate (EER) and genuine acceptance rate (GAR) have also been improved.</span>

Research on Coal and Rock Type Recognition Based on Mechanical Vision

In order to identify different kinds of coal, rock, and gangue, the FPV integrated image transmission camera is used to collect images of 6 types of coal, 8 types of rocks, and 2 types of coal gangue, and the images are processed based on the two-dimensional discrete wavelet transform (2D-DWT) based on the steerable pyramid decomposition (SPD). The maximum likelihood estimation method is used to estimate the parameters, and, the coal and rock types are judged by comparing the similarity of each image. The results show the following: (1) in the eight kinds of rocks, the recognition accuracy of shale and limestone is 90%, that of anorthosite is 95%, and those of other rocks are 100%; (2) the accuracy of comprehensive identification of coal, rock, and gangue is 93%, the comprehensive of coal and gangue is 78%, and the rock classification is 97%; (3) the identification time of 6 types of coal samples, 8 types of rock samples, and 2 types of coal gangue samples are in the range of 2 s∼3 s, which is far less than 10 s, which can meet the requirements of coal and rock identification in terms of recognition speed; and (4) according to 20 groups of data, the range, variance, and standard deviation of the same coal gangue sample meet the accuracy requirements of coal and rock identification. The identification method provides an effective method to improve the efficiency of coal separation, effectively determine the distribution of coal and rock, and timely adjust the cutting height of shearer drum and the operation parameters of various fully mechanized mining equipment, so as to improve the recovery rate of coal resources.

3D steerable pyramid decomposition and its application in seismic data processing and interpretation

The application of 3D multi-scale geometric analysis in seismic data processing and interpretation is still in the preliminary stage. The principle of 3D Steerable Pyramid decomposition and reconstruction in frequency domain is analyzed in detail. Spherical low- pass filters and steerable filters are adopted to realize multi-scale and multi-directional decomposition of 3D Steerable Pyramid, and applied to the actual 3D seismic data for random noise attenuation, detection of faults, channels and sand bodies by selecting weighting function in the process of reconstruction. The application of actual 3D seismic data shows that: 1) When the weights are all equal to 1, perfect reconstruction is achieved, the random noise can be removed by threshold method in the decomposition domain of 3D Steerable Pyramid, the denoising results are clean, and the continuity of the event, the characteristics of the reflected wave group and the breakpoint are clearer; 2) Weighting reconstruction can enhance some features. Compared with amplitude and coherent attribute analysis, the data weighting reconstructed by 3D Steerable Pyramid decomposition not only shows faults and channels completely and meticulously, but also presents an even more impressive picture of sand body’s boundary, thus achieving the optimal application effect.

Image forgery detection using image similarity

Ideally, sophisticated image forgery methods leave no perceptible evidence of tampering. In response to such stringent context, researchers have proposed digital methods to detect such indiscernible tampering. In this paper, we present a blind image forgery detection method that uses a steerable pyramid decomposition technique and copulas ensemble. This method can accurately detect forgery in regions as small as 16 pixels, which is the smallest size reported in the literature with perfect accuracy. The proposed method is innovative in that: (i) it works on both grey scale images as well as colored images; (ii) the copula functions are used to calculate image similarity (or dissimilarity) which represents image forgery; (iii) the precision of the copula results on the image steerable pyramid bands motivated the idea of selecting the band with minimum number of elements to represent the block(s) in the image, which is 16 elements, in our case. The idea of using smallest number of elements to represent the blocks can significantly speed up the method as the testing is done on such small number of pixels; finally (iv) this method can be applied to more than one kind of image forgery with similar results. To verify the performance of the proposed method, we tested it on the well-known Copy Move Forgery Detection database (CoMoFoD) using 5123 image variations of the database. Also, we compared our results with five previously published algorithms and found that the proposed method outperformed those algorithms even when the forged images were subjected to postprocessing manipulations and transformations.

Statistical Goodness Factor ‘ᴦ’ for Image Fusion Algorithm Based on UGGD Parameters

In this paper we propose a novel pyramid decomposition based Image fusion metric, Gamma Factor or Goodness of Fit ‘ᴦ’ which describes the statistically amount of information fused by the image fusion algorithm. We first apply steerable pyramid decomposition and then a fitting model for Univariate Generalised Gaussian Distribution (UGGD) parameter estimation. From the UGGD; P and S fitting model coefficients are computed. To estimate the optimum weights for computation a huge data set of complimentary images are used. Using these weights, amount of information contributed by each image to form a fused image can be estimated. Experimental results show the tremendous matching with the quantise information

A Full-Reference Image Quality Assessment for Multiply Distorted Image based on Visual Mutual Information

Abstract A full-reference image quality assessment (FR-IQA) method for multi-distortion based on visual mutual information (MD-IQA) is proposed to solve the problem that the existing FR-IQA methods are mostly applicable to single-distorted images, but the assessment result for multiply distorted images is not ideal. First, the reference image and the distorted image are preprocessed by steerable pyramid decomposition and contrast sensitivity function (CSF). Next, a Gaussian scale mixture (GSM) model and an image distorted model are respectively constructed for the reference images and the distorted images. Then, visual distorted models are constructed both for the reference images and the distorted images. Finally, the mutual information between the processed reference image and the distorted image is calculated to obtain the full-reference quality assessment index for multiply distorted images. The experimental results show that the proposed method has higher accuracy and better performance for multiply distorted images.

Assessment of cardiac-driven liver movements with filtered harmonic phase image representation, optical flow quantification, and motion amplification.

To characterize cardiac-driven liver movements using a harmonic phase image representation (HARP) with an optical flow quantification and motion amplification method. The method was applied to define the cardiac trigger delay providing minimal signal losses in liver DWI images. The 16-s breath-hold balanced-SSFP time resolved 20 images/s were acquired at 3T in coronal and sagittal orientations. A peripheral pulse unit signal was recorded. Cardiac-triggered DWI images were acquired after different peripheral pulse unit delays. A steerable pyramid decomposition with multiple orientations and spatial frequencies was applied. The liver motion field-map was derived from temporal variations of the HARP representation filtered around the cardiac frequency. Liver displacements were quantified with an optical flow method; moreover the right liver motion was amplified. The largest displacements were observed in the left liver (feet-head:3.70 ± 1.06 mm; anterior-posterior: 2.35 ± 0.51 mm). Displacements were statistically significantly weaker in the middle right liver (0.47 ± 0.11 mm; P = 0.0156). The average error was 0.013 ± 0.022 mm (coronal plane) and 0.021 ± 0.041 mm (sagittal plane). The velocity field demonstrated opposing movements of the right liver extremities during the cardiac cycle. DWI signal loss was minimized in regions and instants of smallest amplitude of both velocity and velocity gradient. Cardiac-driven liver movements were quantified with combined cardiac frequency-filtered HARP and optical flow methods. A motion phase opposition between right liver extremities was demonstrated. Displacement amplitude and velocity were larger in the left liver especially along the vertical direction. Motion amplification visually emphasized cardiac-driven right liver displacements. The optimal cardiac timing minimizing signal loss in liver DWI images was derived.

Thyroid Nodule Classification Using Steerable Pyramid–Based Features From Ultrasound Images

The most common endocrine cancer is thyroid cancer. The incidental rate of thyroid cancer has significantly increased during the past few decades. Timely identification and suitable treatment are essential for better outcome. High-resolution ultrasound is the preferred modality for the detection of thyroid nodules as it has the capability of locating tiny nodules. This article proposes a feature extraction method by integrating steerable pyramid decomposition and cooccurrence matrix features for the characterization of the thyroid nodule. Steerable pyramid decomposition is carried out both in time domain and frequency domain. Textural features are obtained from the pyramid at different levels and with different filters. ReliefF method is used for feature selection. Support vector machine is used to classify the thyroid nodule as benign or malignant, and its performance is evaluated using accuracy, sensitivity, specificity, positive predictive value, negative predictive value, false alarm rate, and F1_score. The proposed approaches are tested on a dataset containing 110 thyroid ultrasound images (benign, malignant, and borderline cases). A very high overall accuracy of 99.08% with 100% sensitivity (malignant nodule detected as malignant) and 98.16% specificity (benign nodule detected as benign) is obtained for features extracted from steerable pyramid coefficients through convolution using sp1 filter at level 3. Experimental results clearly indicate that steerable pyramid–based cooccurrence matrix features can effectively describe the distinctive nature of the thyroid nodule in ultrasound image.

Regularization in parallel magnetic resonance imaging

AbstractSPIRiT (iterative self‐consistent parallel imaging reconstruction) can be solved efficiently for data acquired on arbitrary k‐space trajectories, and its sparsity regularized variant L1‐SPIRiT accelerates reconstruction. In this paper, we propose a regularized SPIRiT reconstruction based on steerable pyramid decomposition. The directionally filter banks lead to a better separation of signal and noise compared to a discrete wavelet transform (DWT). In vivo datasets and eight‐channel Shepp‐Logan phantom studies demonstrate efficient reconstructions. We compared our work with five state‐of‐the‐art parallel imaging techniques; our method yields better reconstruction results.

Spatiotemporal Colorization of Video Using 3D Steerable Pyramids

We propose a new technique for video colorization based on spatiotemporal color propagation in the 3D video volume, utilizing the dominant orientation response obtained from the steerable pyramid decomposition of the video. The volumetric color diffusion from the sources that are marked by scribbles occurs across spatiotemporally smooth regions, and the prevention of leakage is facilitated by the spatiotemporal discontinuities in the output of steerable filters, representing the object boundaries and motion boundaries. Unlike most existing methods, our approach dispenses with the need of motion vectors for interframe color transfer and provides a general framework for image and video colorization. The experimental results establish the effectiveness of the proposed approach in colorizing videos having different types of motion and visual content even in the presence of occlusion, in terms of accuracy and computational requirements.

High-resolution light field reconstruction using a hybrid imaging system.

Recently, light field cameras have drawn much attraction for their innovative performance in photographic and scientific applications. However, narrow baselines and constrained spatial resolution of current light field cameras impose restrictions on their usability. Therefore, we design a hybrid imaging system containing a light field camera and a high-resolution digital single lens reflex camera, and these two kinds of cameras share the same optical path with a beam splitter so as to achieve the reconstruction of high-resolution light fields. The high-resolution 4D light fields are reconstructed with a phase-based perspective variation strategy. First, we apply complex steerable pyramid decomposition on the high-resolution image from the digital single lens reflex camera. Then, we perform phase-based perspective-shift processing with the disparity value, which is extracted from the upsampled light field depth map, to create high-resolution synthetic light field images. High-resolution digital refocused images and high-resolution depth maps can be generated in this way. Furthermore, controlling the magnitude of the perspective shift enables us to change the depth of field rendering in the digital refocused images. We show several experimental results to demonstrate the effectiveness of our approach.

A CORRELATIVE TWO-STEP APPROACH TO HALLUCINATING FACES

Face hallucination is to synthesize high-resolution face image from the input low-resolution one. Although many two-step learning-based face hallucination approaches have been developed, they suffer from the expensive computational cost due to the separate calculation of the global and local models. To overcome this problem, we propose a correlative two-step learning-based face hallucination approach which bridges the gap between the global model and the local model. In the global phase, we build a global face hallucination framework by combining the steerable pyramid decomposition and the reconstruction. In the residue compensation phase, based on the combination weights and constituent samples obtained in the global phase, a residue face image is synthesized by the neighbor reconstruction algorithm to compensate the hallucinated global face image with subtle facial features. The ultimate hallucinated result is synthesized by adding the residue face image to the global face image. Compared with existing methods, in the global phase, our global face image is more similar to the original high-resolution face image. Furthermore, in the residue compensation phase, we use the combination weights and constituent samples obtained in the global phase to compute the residue face image, by which the computational efficiency can be greatly improved without compromising the quality of facial details. The experimental results and comparisons demonstrate that our approach can not only generate convincible high-resolution face images efficiently, but also has high computational efficiency. Furthermore, our proposed approach can be used to restore the damaged face images in image inpainting. The efficacy of our approach is validated by recovering the damaged face images with visually good results.

Using multiple steerable filters and Bayesian regularization for facial expression recognition

Facial expression recognition has recently become a challenging research area. Its applications include human–computer interfaces, human emotion analysis, and medical care and cure.In this paper, we present a new challenging method to recognize seven universal emotional expressions, which are happiness, neutral, angry, disgust, sadness, fear and surprise. In our approach, we identify the user׳s facial expressions from the input images, using statistical features extracted from the steerable pyramid decomposition, and classified with a Bayesian regularization neural network. The evaluation of the proposed approach in terms of recognition accuracy is achieved using two universal databases, the Japanese Female Facial Expression database and the Cohn–Kanade facial expression database. The overall accuracy rate reaches 93.33% for the first database and is about 98.13% for the second one. These results show the effectiveness of the steerable proposed algorithm.

A Robust Image Watermarking Scheme Using Steerable Pyramid Transform

In recent years, digital image watermarking techniques are represented as a solution to protect intellectual property rights of digital media. In this work, we propose a new watermarking scheme based on steerable pyramid decomposition transform. Trade-off between invisibility and robustness properties is considered in the proposed scheme. In which, the distortion caused by the embedding process of the watermark should be as low as possible and at the same time should be robust as high as possible against attacks. The proposed scheme embeds several copies of the watermark image in all steerable pyramid transform bands of the original image, in order to facilitate the watermark detection and to be more robust against several attacks like cropping in case we lost some parts of the watermarked image. In the experimental results, the good similarity between the watermarked and the original images demonstrates the good invisibility of the proposed scheme, and the survival of the watermark against geometric and no-geometric attacks demonstrates the robustness of the same scheme.

A no-reference image quality assessment approach based on steerable pyramid decomposition using natural scene statistics

For majorities of no-reference image quality assessment (NRIQA) algorithms, prior knowledge about image distortion types is needed. However, the source distortions in the image are actually not giv...

A robust watermarking scheme based on steerable pyramid and singular value decomposition

Most of the watermarking schemes that have been proposed until now are based on DCT, DFT, and DWT transformations. For this reason, this paper presents a new robust watermarking scheme based on Steerable Pyramid (SP) wavelet transform and singular value decomposition (SVD) for copyright protection and authenticity. SP transformation is applied to the original image with a number of scales and orientations accurately calculated. Low-pass band is selected and divided into blocks. After applying SVD on each block, watermarking process embeds the watermark by modifying coecient of S component

Learning How to Extract Rotation-Invariant and Scale-Invariant Features from Texture Images

Learning how to extract texture features from noncontrolled environments characterized by distorted images is a still-open task. By using a new rotation-invariant and scale-invariant image descriptor based on steerable pyramid decomposition, and a novel multiclass recognition method based on optimum-path forest, a new texture recognition system is proposed. By combining the discriminating power of our image descriptor and classifier, our system uses small-size feature vectors to characterize texture images without compromising overall classification rates. State-of-the-art recognition results are further presented on the Brodatz data set. High classification rates demonstrate the superiority of the proposed system.