Steerable Filters Research Articles

Global Minimum for a Finsler Elastica Minimal Path Approach

In this paper, we propose a novel curvature-penalized minimal path model via an orientation-lifted Finsler metric and the Euler elastica curve. The original minimal path model computes the globally minimal geodesic by solving an Eikonal partial differential equation (PDE). Essentially, this first-order model is unable to penalize curvature which is related to the path rigidity property in the classical active contour models. To solve this problem, we present an Eikonal PDE-based Finsler elastica minimal path approach to address the curvature-penalized geodesic energy minimization problem. We were successful at adding the curvature penalization to the classical geodesic energy. The basic idea of this work is to interpret the Euler elastica bending energy via a novel Finsler elastica metric that embeds a curvature penalty. This metric is non-Riemannian, anisotropic and asymmetric, and is defined over an orientation-lifted space by adding to the image domain the orientation as an extra space dimension. Based on this orientation lifting, the proposed minimal path model can benefit from both the curvature and orientation of the paths. Thanks to the fast marching method, the global minimum of the curvature-penalized geodesic energy can be computed efficiently. We introduce two anisotropic image data-driven speed functions that are computed by steerable filters. Based on these orientation-dependent speed functions, we can apply the proposed Finsler elastica minimal path model to the applications of closed contour detection, perceptual grouping and tubular structure extraction. Numerical experiments on both synthetic and real images show that these applications of the proposed model indeed obtain promising results.

Multi‐lane detection based on omnidirectional camera using anisotropic steerable filters

Automated lane detection is a vital part of driver assistance systems in intelligent vehicles. In this study, a multi-lane detection method based on omnidirectional images is presented to conquer the difficulties stemming from the limited view field of the rectilinear cameras. The contributions of this study are twofold. First, to extract the features of the lane markings under various illumination and road-surface scenarios, a feature extractor based on anisotropic steerable filter is proposed. Second, a parabola lane model is used to fit the straight as well as curved lanes. According to the parabola lane model, the straight lines and curves of feature maps can be represented as straight lines in a linear space coordinate system. Then lane modelling can be treated as an optimisation question in linear space and the parameters of lanes can be estimated by minimising the objection function. The method has been tested on publicly available data sets and the real car experiments. Experimental results show that the proposed method outperforms state-of-the-arts approaches and obtains a detection accuracy of 99% in real world scenes.

Automated Measurement of Cobblestone Morphology for Characterizing Stem Cell Derived Retinal Pigment Epithelial Cell Cultures.

Assessing the morphologic properties of cells in microscopy images is an important task to evaluate cell health, identity, and purity. Typically, subjective visual assessments are accomplished by an experienced researcher. This subjective human step makes transfer of the evaluation process from the laboratory to the cell manufacturing facility difficult and time consuming. Automated image analysis can provide rapid, objective measurements of cultured cells, greatly aiding manufacturing, regulatory, and research goals. Automated algorithms for classifying images based on appearance characteristics typically either extract features from the image and use those features for classification or use the images directly as input to the classification algorithm. In this study we have developed both feature and nonfeature extraction methods for automatically measuring "cobblestone" structure in human retinal pigment epithelial (RPE) cell cultures. A new approach using image compression combined with a Kolmogorov complexity-based distance metric enables robust classification of microscopy images of RPE cell cultures. The automated measurements corroborate determinations made by experienced cell biologists. We have also developed an approach for using steerable wavelet filters for extracting features to characterize the individual cellular junctions. Two image analysis techniques enable robust and accurate characterization of the cobblestone morphology that is indicative of viable RPE cultures for therapeutic applications.

SUPPRESSION OF SEISMIC RANDOM NOISE BASED ON STEERABLE FILTERS

AbstractFor seismic random noise suppression, this work designs a steerable filter by taking advantage of elongated Hermite‐Gauss functions. According to the different directional responses between valid signal and random noise, we can reconstruct signal by the local characteristics of selected data. With the added directional selectivity, the filtering process can match different direction axes, which makes sure that noise is suppressed without reducing the signal fidelity. The property of directional steerability makes computation more efficient and requires less storage space. Simulation results show that we can get better signal amplitude and denoising effects than traditional wavelet transform and Curvelet transform algorithm by using this method. At –5 db SNR, this method can ensure that the average amplitude reaches 92.99% and SNR enhances 221.774%, which can significantly suppress noise as well as keep the useful signal in processing of real seismic signals.

Anisotropic Diffusion Descriptors

AbstractSpectral methods have recently gained popularity in many domains of computer graphics and geometry processing, especially shape processing, computation of shape descriptors, distances, and correspondence. Spectral geometric structures are intrinsic and thus invariant to isometric deformations, are efficiently computed, and can be constructed on shapes in different representations. A notable drawback of these constructions, however, is that they areisotropic, i.e., insensitive to direction. In this paper, we show how to construct direction‐sensitive spectral feature descriptors usinganisotropic diffusionon meshes and point clouds. The core of our construction are directed local kernels acting similarly to steerable filters, which are learned in a task‐specific manner. Remarkably, while being intrinsic, our descriptors allow to disambiguate reflection symmetries. We show the application of anisotropic descriptors for problems of shape correspondence on meshes and point clouds, achieving results significantly better than state‐of‐the‐art methods.

Driver head pose estimation using efficient descriptor fusion

A great interest is focused on driver assistance systems using the head pose as an indicator of the visual focus of attention and the mental state. In fact, the head pose estimation is a technique allowing to deduce head orientation relatively to a view of camera and could be performed by model-based or appearance-based approaches. Model-based approaches use a face geometrical model usually obtained from facial features, whereas appearance-based techniques use the whole face image characterized by a descriptor and generally consider the pose estimation as a classification problem. Appearance-based methods are faster and more adapted to discrete pose estimation. However, their performance depends strongly on the head descriptor, which should be well chosen in order to reduce the information about identity and lighting contained in the face appearance. In this paper, we propose an appearance-based discrete head pose estimation aiming to determine the driver attention level from monocular visible spectrum images, even if the facial features are not visible. Explicitly, we first propose a novel descriptor resulting from the fusion of four most relevant orientation-based head descriptors, namely the steerable filters, the histogram of oriented gradients (HOG), the Haar features, and an adapted version of speeded up robust feature (SURF) descriptor. Second, in order to derive a compact, relevant, and consistent subset of descriptor’s features, a comparative study is conducted on some well-known feature selection algorithms. Finally, the obtained subset is subject to the classification process, performed by the support vector machine (SVM), to learn head pose variations. As we show in experiments with the public database (Pointing’04) as well as with our real-world sequence, our approach describes the head with a high accuracy and provides robust estimation of the head pose, compared to state-of-the-art methods.

Transforms and Operators for Directional Bioimage Analysis: A Survey.

We give a methodology-oriented perspective on directional image analysis and rotation-invariant processing. We review the state of the art in the field and make connections with recent mathematical developments in functional analysis and wavelet theory. We unify our perspective within a common framework using operators. The intent is to provide image-processing methods that can be deployed in algorithms that analyze biomedical images with improved rotation invariance and high directional sensitivity. We start our survey with classical methods such as directional-gradient and the structure tensor. Then, we discuss how these methods can be improved with respect to robustness, invariance to geometric transformations (with a particular interest in scaling), and computation cost. To address robustness against noise, we move forward to higher degrees of directional selectivity and discuss Hessian-based detection schemes. To present multiscale approaches, we explain the differences between Fourier filters, directional wavelets, curvelets, and shearlets. To reduce the computational cost, we address the problem of matching directional patterns by proposing steerable filters, where one might perform arbitrary rotations and optimizations without discretizing the orientation. We define the property of steerability and give an introduction to the design of steerable filters. We cover the spectrum from simple steerable filters through pyramid schemes up to steerable wavelets. We also present illustrations on the design of steerable wavelets and their application to pattern recognition.

Cell Boundary Detection for Quantitative Studies of the Role of Tetraspanin CD82 in Cell-cell Adhesion

Cell-cell adhesion is mediated by interaction of a number of protein complexes residing on the cell plasma membranes. Disruption of these complexes affects structural and functional integrity of tissues. It has been hypothesized that a membrane protein tetraspanin CD82, a known metastasis suppressor, may play a role in regulating cell adhesion. Two proteins of interest (PG and Dsg2) have been fluorescently tagged in cells expressing CD82 and in control cells, and imaged over the course of three hours. This paper describes a fully automatic method for quantitative analysis of PG and Dsg2 fluorescence. Cell boundaries are detected by the application of second-order steerable Gaussian filters. Cells are then segmented by closing the detected boundaries. Fluorescence levels are computed from a region lying around ± 1.5 microns from the centre-line between adjacent cells. Mean fluorescence levels obtained for thirty three cell images show that both the levels and the dynamics are different between the control and the CD82-expressing cells, which suggests that CD82 may play a role in cell-cell adhesion.

Integrated Multiple Features for Tumor Image Retrieval Using Classifier and Feedback Methods

The content based image retrieval method greatly assists in retrieving medical images close to the query image from a large database basing on their visual features. This paper presents an effective approach in which the region of the object is extracted with the help of multiple features ignoring the background of the object by employing edge following segmentation method followed by extracting texture and shape characteristics of the images. The former is extracted with the help of Steerable filter at different orientations and radial Chebyshev moments are used for extracting the later. Initially the images similar to the query image are extracted from a large group of medical images. Then the search is by accelerating the retrieval process with the help of Support Vector Machine (SVM) classifier. The performance of the retrieval system is enhanced by adapting the subjective feedback method. The experimental results show that the proposed region based multiple features and integrated with classifier and subjective feedback method yields better results than classical retrieval systems.

Shadow Detection by Local Color Constancy

This paper describe the technique of shadow detection properly, this technique can detect both the cast and selfshadow. The method exploits local color constancy properties which are cause of reflectance suppression in excess of shadowed regions. For detecting shadowed areas in a scene, the values of the backdrop image are separated by values of the current frame in the true color (RGB) space. We use all three type of colour space in our work. Illumination map is extracted using a steerable filter framework based on global, local correlations in low and high frequency bands respectively. The lighting and colour features so extracted are then input to a decision trees are designed to detect shadow edges using AdaBoost. The simulation results give us an idea about the performance of the proposed method as good with boundary marking on shadow and nonshadow region with high accuracy.

A comparison of interest point and region detectors on structured, range and texture images

This article presents an evaluation of the image retrieval and classification potential of local features. Several affine invariant region and scale invariant interest point detectors in combination with well known descriptors were evaluated. Tests on building, range and texture databases were carried out in order to understand the effects of the nature and the variability of the data on the performance of the detectors in terms of their invariance to affine deformations and scale changes. Furthermore, a novel multi-scale edge shape detector, Twin Leaf Regions (TLR) is also proposed using a graph based image decomposition. In TLR, Affine adaptation is avoided in order to reduce the offset from the edges so that pure edges shapes are captured in multiple scales. In the evaluation of building recognition, both homogeneous affine regions (such as Maximally Stable Extremal Regions (MSER)) and corner based detectors (such as Hessian and Harris with both Affine/Laplace variants, SURF with determinant of Hessian based corners and SIFT with difference of Gaussians) acquired more than 90% mean average precision, whereas on range images, homogeneous region detector did not work well. TLR offered good performance than MSER and comparable performance to Harris Affine and Harris Laplace in range image classification and texture retrieval. But its performance was low in building recognition. In general, it was observed that the affine and scale invariance becomes less effective in range and textured images. It is also shown that in a bi-channel approach, combining surface and edge regions (MSER and TLR) boosts the overall performance. Among the descriptors, SIFT and SURF generally offer higher performance but low dimensional descriptors such as Steerable Filters follow closely.

Automatic segmentation of lymph vessel wall using optimal surface graph cut and hidden Markov Models.

We present a novel method to segment the lymph vessel wall in confocal microscopy images using Optimal Surface Segmentation (OSS) and hidden Markov Models (HMM). OSS is used to preform a pre-segmentation on the images, to act as the initial state for the HMM. We utilize a steerable filter to determine edge based filters for both of these segmentations, and use these features to build Gaussian probability distributions for both the vessel walls and the background. From this we infer the emission probability for the HMM, and the transmission probability is learned using a Baum-Welch algorithm. We transform the segmentation problem into one of cost minimization, with each node in the graph corresponding to one state, and the weight for each node being defined using its emission probability. We define the inter-relations between neighboring nodes using the transmission probability. Having constructed the problem, it is solved using the Viterbi algorithm, allowing the vessel to be reconstructed. The optimal solution can be found in polynomial time. We present qualitative and quantitative analysis to show the performance of the proposed method.

A Statistical Method for Improved 3D Surface Detection

In this letter, we present a new 3D statistical method for surface detection which provides improvements over competitive methods both in terms of noise suppression and detection of complete surfaces. The methods are applied to both synthetically created image volumes, and MRI data. Accuracy against a ground truth is assessed using the quantitative figure of merit performance measure, with the statistical methods outperforming both a 3D implementation of the gradient Canny operator and a 3D optimal steerable filter method. The results also confirm how 3D surface detection methods avoid missing surface information by successfully locating complete boundaries irrespective of the object orientation and plane of image capture. We conclude that the statistical 3D methods are capable of producing more accurate surface maps in textured images, that reflect the 3D boundary information, improving on current 2D and 3D standards.

Suppression of near‐surface scattered body‐to‐surface waves: a steerable and nonlinear filtering approach

ABSTRACTWe present an approach based on local‐slope estimation for the separation of scattered surface waves from reflected body waves. The direct and scattered surface waves contain a significant amount of seismic energy. They present great challenges in land seismic data acquisition and processing, particularly in arid regions with complex near‐surface heterogeneities (e.g., dry river beds, wadis/large escarpments, and karst features). The near‐surface scattered body‐to‐surface waves, which have comparable amplitudes to reflections, can mask the seismic reflections. These difficulties, added to large amplitude direct and back‐scattered surface (Rayleigh) waves, create a major reduction in signal‐to‐noise ratio and degrade the final sub‐surface image quality. Removal of these waves can be difficult using conventional filtering methods, such as an filter, without distorting the reflected signal. The filtering algorithm we present is based on predicting the spatially varying slope of the noise, using steerable filters, and separating the signal and noise components by applying a directional nonlinear filter oriented toward the noise direction to predict the noise and then subtract it from the data. The slope estimation step using steerable filters is very efficient. It requires only a linear combination of a set of basis filters at fixed orientation to synthesize an image filtered at an arbitrary orientation. We apply our filtering approach to simulated data as well as to seismic data recorded in the field to suppress the scattered surface waves from reflected body waves, and we demonstrate its superiority over conventional techniques in signal preservation and noise suppression.

Steerable PCA for Rotation-Invariant Image Recognition

In this paper, we propose a continuous-domain version of principal-component analysis, with the constraint that the underlying family of templates appears at arbitrary orientations. We show that the corresponding principal components are steerable. Our method can be used for designing steerable filters so that they best approximate a given collection of reference templates. We apply this framework to the detection and classification of micrometer-sized particles that are used in a microfluidic diagnostics system. This is done in two steps. First, we decompose the particles into a small number of templates and compute their steerable principal components. Then we use these principal components to automatically estimate the orientation and the class of each particle.

Fast digital zooming system using directionally adaptive image interpolation and restoration.

This paper presents a fast digital zooming system for mobile consumer cameras using directionally adaptive image interpolation and restoration methods. The proposed interpolation algorithm performs edge refinement along the initially estimated edge orientation using directionally steerable filters. Either the directionally weighted linear or adaptive cubic-spline interpolation filter is then selectively used according to the refined edge orientation for removing jagged artifacts in the slanted edge region. A novel image restoration algorithm is also presented for removing blurring artifacts caused by the linear or cubic-spline interpolation using the directionally adaptive truncated constrained least squares (TCLS) filter. Both proposed steerable filter-based interpolation and the TCLS-based restoration filters have a finite impulse response (FIR) structure for real time processing in an image signal processing (ISP) chain. Experimental results show that the proposed digital zooming system provides high-quality magnified images with FIR filter-based fast computational structure.

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.

Joint 3-D vessel segmentation and centerline extraction using oblique Hough forests with steerable filters.

We propose a novel framework for joint 3-D vessel segmentation and centerline extraction. The approach is based on multivariate Hough voting and oblique random forests (RFs) that we learn from noisy annotations. It relies on steerable filters for the efficient computation of local image features at different scales and orientations. We validate both the segmentation performance and the centerline accuracy of our approach both on synthetic vascular data and four 3-D imaging datasets of the rat visual cortex at 700 nm resolution. First, we evaluate the most important structural components of our approach: (1) Orthogonal subspace filtering in comparison to steerable filters that show, qualitatively, similarities to the eigenspace filters learned from local image patches. (2) Standard RF against oblique RF. Second, we compare the overall approach to different state-of-the-art methods for (1) vessel segmentation based on optimally oriented flux (OOF) and the eigenstructure of the Hessian, and (2) centerline extraction based on homotopic skeletonization and geodesic path tracing. Our experiments reveal the benefit of steerable over eigenspace filters as well as the advantage of oblique split directions over univariate orthogonal splits. We further show that the learning-based approach outperforms different state-of-the-art methods and proves highly accurate and robust with regard to both vessel segmentation and centerline extraction in spite of the high level of label noise in the training data.

Steerable local frequency based multispectral multifocus image fusion

Design of a focus measure and a fusion algorithm which will perform well across different spectra remains an extremely challenging task. In this work, the problem of multispectral multifocus image fusion is addressed using the phase information of the source image pixels at different orientations. We make the local frequency, the spatial derivative of the local phase of the pixels, steerable to obtain a good novel focus measure. Oriented analytic image based on the theory of steerable filters is constructed for that purpose. A multifocus fusion algorithm is proposed next using this focus measure. Comprehensive experimentations clearly demonstrate that our focus measure as well as the multifocus fusion algorithm yield promising results across the visual (VIS), the near-infrared (NIR) and the thermal (TH) spectra.

Action recognition by spatio-temporal oriented energies

In this paper, we present a unified representation based on the spatio-temporal steerable pyramid (STSP) for the holistic representation of human actions. A video sequence is viewed as a spatio-temporal volume preserving all the appearance and motion information of an action in it. By decomposing the spatio-temporal volumes into band-passed sub-volumes, the spatio-temporal Laplacian pyramid provides an effective technique for multi-scale analysis of video sequences, and spatio-temporal patterns with different scales could be well localized and captured. To efficiently explore the underlying local spatio-temporal orientation structures at multiple scales, a bank of three-dimensional separable steerable filters are conducted on each of the sub-volume from the Laplacian pyramid. The outputs of the quadrature pair of steerable filters are squared and summed to yield a more robust oriented energy representation. To be further invariant and compact, a spatio-temporal max pooling operation is performed between responses of the filtering at adjacent scales and over spatio-temporal neighbourhoods. In order to capture the appearance, local geometric structure and motion of an action, we apply the STSP on the intensity, 3D gradients and optical flow of video sequences, yielding a unified holistic representation of human actions.Taking advantage of multi-scale, multi-orientation analysis and feature pooling, STSP produces a compact but informative and invariant representation of human actions. We conduct extensive experiments on the KTH, UCF Sports and HMDB51 datasets, which shows the unified STSP achieves comparable results with the state-of-the-art methods.