Gabor Filter Bank Research Articles

서포트 벡터와 뱀형상 윤곽선을 이용한 TRUS 영상의 전립선 분할

TRUS영상에서 전립선에 대한 많은 진단과 치료 과정에서 정확한 전립선 경계의 추출이 요구된다. 여기에는 전립선 경계의 애매함, 반점, 낮은 그레이 레벨로 인하여 많은 어려움이 존재한다. 본 논문에서는 서포트 벡터와 뱀형상 윤곽선을 이용하여 TRUS영상의 자동 전립선 분할에 대한 방법을 제안한다. 이 방법은 전처리, 가버 특성 추출, 학습, 전립선 추출 단계로 구성된다. 텍스처 특성을 추출하기 위하여 가버 필터 뱅크가 사용되며, 학습 과정에서 전립선과 비전립선의 각 특성을 얻기 위하여, SVM이 사용된다. 전립선의 경계는 뱀형상 윤곽 알고리즘에 의해 추출된다. 실험 결과, 제안된 알고리즘은 인간 전문가가 추출한 경계와 비교했을 때 9.3%보다 적은 차이로 전립선 경계를 추출할 수 있었다. In many diagnostic and treatment procedures for prostate disease accurate detection of prostate boundaries in transrectal ultrasound(TRUS) images is required. This is a challenging and difficult task due to weak prostate boundaries, speckle noise and the short range of gray levels. In this paper a method for automatic prostate segmentation inTRUS images using support vectors and snake-like contour is presented. This method involves preprocessing, extracting Gabor feature, training, and prostate segmentation. Gabor filter bank for extracting the texture features has been implemented. A support vector machine(SVM) for training step has been used to get each feature of prostate and nonprostate. The boundary of prostate is extracted by the snake-like contour algorithm. The results showed that this new algorithm extracted the prostate boundary with less than 9.3% relative to boundary provided manually by experts.

Detecting natural occlusion boundaries using local cues

Occlusion boundaries and junctions provide important cues for inferring three-dimensional scene organization from two-dimensional images. Although several investigators in machine vision have developed algorithms for detecting occlusions and other edges in natural images, relatively few psychophysics or neurophysiology studies have investigated what features are used by the visual system to detect natural occlusions. In this study, we addressed this question using a psychophysical experiment where subjects discriminated image patches containing occlusions from patches containing surfaces. Image patches were drawn from a novel occlusion database containing labeled occlusion boundaries and textured surfaces in a variety of natural scenes. Consistent with related previous work, we found that relatively large image patches were needed to attain reliable performance, suggesting that human subjects integrate complex information over a large spatial region to detect natural occlusions. By defining machine observers using a set of previously studied features measured from natural occlusions and surfaces, we demonstrate that simple features defined at the spatial scale of the image patch are insufficient to account for human performance in the task. To define machine observers using a more biologically plausible multiscale feature set, we trained standard linear and neural network classifiers on the rectified outputs of a Gabor filter bank applied to the image patches. We found that simple linear classifiers could not match human performance, while a neural network classifier combining filter information across location and spatial scale compared well. These results demonstrate the importance of combining a variety of cues defined at multiple spatial scales for detecting natural occlusions.

A methodology for estimating the shape of biconcave red blood cells using multicolor scattering images

In this paper, a novel methodology for estimating the shape of human biconcave red blood cells (RBCs), using color scattering images, is presented. The information retrieval process includes, image normalization, features extraction using two-dimensional discrete transforms, such as angular radial transform (ART), Zernike moments and Gabor filters bank and features dimension reduction using both independent component analysis (ICA) and principal component analysis (PCA). A radial basis neural network (RBF-NN) estimates the RBC geometrical properties. The proposed method is evaluated in both regression and identification tasks by processing images of a simulated device used to acquire scattering phenomena of moving RBCs. The simulated device consists of a tricolor light source (light emitting diode – LED) and moving RBCs in a thin glass. The evaluation database includes 23,625 scattering images, obtained by means of the boundary element method. The regression and identification accuracy of the actual RBC shape is estimated using three feature sets in the presence of additive white Gaussian noise from 60 to 10dB SNR and systematic distortion, giving a mean error rate less than 1% of the actual RBC shape, and more than 99% mean identification rate.

Long Range Cross-Spectral Face Recognition: Matching SWIR Against Visible Light Images

Short wave infrared (SWIR) is an emerging imaging modality in surveillance applications. It is able to capture clear long range images of a subject in harsh atmospheric conditions and at night time. However, matching SWIR images against a gallery of color images is a very challenging task. The photometric properties of images in these two spectral bands are highly distinct. This work presents a novel cross-spectral face recognition scheme that encodes images filtered with a bank of Gabor filters followed by three local operators: Simplified Weber Local Descriptor, Local Binary Pattern, and Generalized Local Binary Pattern. Both magnitude and phase of filtered images are encoded. Matching encoded face images is performed by using a symmetric I-divergence. We quantify the verification and identification performance of the cross-spectral matcher on two multispectral face datasets. In the first dataset (PRE-TINDERS), both SWIR and visible gallery images are captured at a close distance (about 2 meters). In the second dataset (TINDERS), the probe SWIR images are collected at longer ranges (50 and 106 meters). The results on PRE-TINDERS dataset form a baseline for matching long range data. We also demonstrate the capability of the proposed approach by comparing its performance with the performance of Faceit G8, a commercial face recognition engine distributed by L1. The results show that the designed method outperforms Faceit G8 in terms of verification and identification rates on both datasets.

Automatic detection of vascular bifurcations in segmented retinal images using trainable COSFIRE filters

Background: The vascular tree observed in a retinal fundus image can provide clues for cardiovascular diseases. Its analysis requires the identification of vessel bifurcations and crossovers.Methods: We use a set of trainable keypoint detectors that we call Combination Of Shifted FIlter REsponses or COSFIRE filters to automatically detect vascular bifurcations in segmented retinal images. We configure a set of COSFIRE filters that are selective for a number of prototype bifurcations and demonstrate that such filters can be effectively used to detect bifurcations that are similar to the prototypical ones. The automatic configuration of such a filter selects given channels of a bank of Gabor filters and determines certain blur and shift parameters. The response of a COSFIRE filter is computed as the weighted geometric mean of the blurred and shifted responses of the selected Gabor filters. The COSFIRE approach is inspired by the function of a specific type of shape-selective neuron in area V4 of visual cortex.Results: We ran experiments on three data sets and achieved the following results: (a) a recall of 97.88% at precision of 96.94% on 40 manually segmented images provided in the DRIVE data set, (b) a recall of 97.32% at precision of 96.04% on 20 manually segmented images provided in the STARE data set, and (c) a recall of 97.02% at precision of 96.53% on a set of 10 automatically segmented images obtained from images in the DRIVE data set.Conclusions: The COSFIRE filters that we use are conceptually simple and easy to implement: the filter output is computed as the weighted geometric mean of blurred and shifted Gabor filter responses. They are versatile keypoint detectors as they can be configured with any given local contour pattern and are subsequently able to detect the same and similar patterns.

Human detection based on pyramidal statistics of oriented filtering and online learned scene geometrical model

We study the problem of robust human detection. In this paper, a new descriptor, Pyramidal Statistics of Oriented Filtering (PSOF), is proposed for human shape representation. Unlike traditional one-scale gradient-based methods, the PSOF descriptor utilizes a Gabor filter bank to obtain multi-scale pixel-level orientation information and makes use of locally normalized pyramidal statistics of these Gabor responses to represent object shape, which shows great robustness to image noise and blur. Besides, to exclude detection outliers that violate perspective projection in image sequence, a geometrical model is learned online to describe the relationship between object's average height and the foot-point coordinate. Experimental results on both static images and video sequences show that PSOF detector performs much better than one of the state-of-the-art detectors.

Detecting rock glacier flow structures using Gabor filters and IKONOS imagery

While ridges and furrows on the surface of rock glaciers are probably the most characteristic morphological features of this expression of creeping mountain permafrost, this is the first study that examines the utility of texture filters in detecting rock glacier flow structures. Texture features were derived from a Gabor filterbank applied to two panchromatic IKONOS orthoimages from the Chilean Andes, and terrain attributes were obtained in order to narrow down the area of interest and as additional predictor variables. Four classification methods of different complexity (generalized linear model, GLM; generalized additive model, GAM; support vector machine, SVM; Bundling) were applied to three sets of predictor variables (texture attributes, terrain attributes, and the combination of both), and predictive performances were estimated using two spatial cross-validation strategies in terms of the median area under the ROC (receiver operating characteristics) curve (AUROC). Overall, classifiers utilizing texture attributes alone or, usually even better, in combination with terrain attributes outperformed terrain attributes alone, and Bundling (in most cases followed by SVM) showed the overall best performance as a classification method. Cross-validated median AUROC values were mostly between 0.70 and 0.80, or “fair,” in this focused pilot study, but much better results are to be expected at the landscape scale. Permutation-based spatial variable importance measures indicate that Gabor features corresponding to texture wavelengths between 10 and 30m are the most important predictors, which is consistent with typical ridge spacing on rock glaciers. Confounding occurred mostly in areas with linear erosion features and ridges or scarps in morainic and thermokarst terrain. We suggest that texture filters and the chosen methodological approach are relevant not only for rock glacier mapping but also for delineating debris-covered glaciers and characterizing glacier surfaces, as well as for other geomorphological and cryospheric applications.

Two Approaches Based on Genetic Algorithm to Generate Short Iris Codes

This paper has the following contributions in iris recognition compass: first, novel parameters selection for Gabor filters to extract the iris features. Second, due to iris textures randomness and assigning the Gabor parameters by pre-knowledgeable values, traditionally, a large Gabor filter bank has been used to prevent losing the discriminative information. It leads to perform extracting and matching the features heavily and on the other hand, the generated feature vectors are lengthened as required for extra storage space. We have proposed and compared two different approaches based on Genetic Algorithm to reduce the system complexity: optimizing the Gabor parameters and feature selection. Third, proposing a novel encoding strategy based on the texture variations to generate compact iris codes. The experimental results show that generated iris codes by optimizing the Gabor parameters approach is more distinctive and compact than ones based on feature selection approach.

Measures of angular spread and entropy for the detection of architectural distortion in prior mammograms

Architectural distortion is an important sign of early breast cancer. We present methods for computer-aided detection of architectural distortion in mammograms acquired prior to the diagnosis of breast cancer in the interval between scheduled screening sessions. Potential sites of architectural distortion were detected using node maps obtained through the application of a bank of Gabor filters and linear phase portrait modeling. A total of 4,224 regions of interest (ROIs) were automatically obtained from 106 prior mammograms of 56 interval-cancer cases, including 301 true-positive ROIs, and from 52 mammograms of 13 normal cases. Each ROI was represented by three types of entropy measures of angular histograms composed with the Gabor magnitude response, angle, coherence, orientation strength, and the angular spread of power in the Fourier spectrum, including Shannon's entropy, Tsallis entropy for nonextensive systems, and Rényi entropy for extensive systems. Using the entropy measures with stepwise logistic regression and the leave-one-patient-out method for feature selection and cross-validation, an artificial neural network resulted in an area under the receiver operating characteristic curve of 0.75. Free-response receiver operating characteristics indicated a sensitivity of 0.80at 5.2 false positives (FPs) per patient. The proposed methods can detect architectural distortion in prior mammograms taken 15months (on the average) before clinical diagnosis of breast cancer, with a high sensitivity and a moderate number of FPs per patient. The results are promising and may be improved with additional features to characterize subtle abnormalities and larger databases including prior mammograms.

Validation of continuously tagged MRI for the measurement of dynamic 3D skeletal muscle tissue deformation

Typically spatial modulation of the magnetization (SPAMM) tagged magnetic resonance imaging (MRI) requires many repeated motion cycles limiting the applicability to highly repeatable tissue motions only. This paper describes the validation of a novel SPAMM tagged MRI and post-processing framework for the measurement of complex and dynamic 3D soft tissue deformation following just three motion cycles. Techniques are applied to indentation induced deformation measurement of the upper arm and a silicone gel phantom. A SPAMM tagged MRI methodology is presented allowing continuous (3.3-3.6 Hz) sampling of 3D dynamic soft tissue deformation using non segmented 3D acquisitions. The 3D deformation is reconstructed by the combination of three mutually orthogonal tagging directions, thus requiring only three repeated motion cycles. In addition a fully automatic post-processing framework is presented employing Gabor scale-space and filter-bank analysis for tag extrema segmentation and triangulated surface fitting aided by Gabor filter bank derived surface normals. Deformation is derived following tracking of tag surface triplet triangle intersections. The dynamic deformation measurements were validated using indentation tests (∼20 mm deep at 12 mm/s) on a silicone gel soft tissue phantom containing contrasting markers which provide a reference measure of deformation. In addition, the techniques were evaluated in vivo for dynamic skeletal muscle tissue deformation measurement during indentation of the biceps region of the upper arm in a volunteer. For the phantom and volunteer tag point location precision were 44 and 92 μm, respectively resulting in individual displacements precisions of 61 and 91 μm, respectively. For both the phantom and volunteer data cumulative displacement measurement accuracy could be evaluated and the difference between initial and final locations showed a mean and standard deviation of 0.44 and 0.59 mm for the phantom and 0.40 and 0.73 mm for the human data. Finally accuracy of (cumulative) displacement was evaluated using marker tracking in the silicone gel phantom. Differences between true and predicted marker locations showed a mean of 0.35 mm and a standard deviation of 0.63 mm. A novel SPAMM tagged MRI and fully automatic post-processing framework for the measurement of complex 3D dynamic soft tissue deformation following just three repeated motion cycles was presented. The techniques demonstrate dynamic measurement of complex 3D soft tissue deformation at subvoxel accuracy and precision and were validated for 3.3-3.6 Hz sampling of deformation speeds up to 12 mm/s.

A new fuzzy segmentation approach based on S-FCM type 2 using LBP-GCO features

Gabor filtering is a widely applied approach for texture analysis. This technique shows a strong dependence on certain number of parameters. Unfortunately, each variation of values of any parameter may affect the texture characterization performance. Moreover, Gabor filters are unable to extract micro-texture features which also have a negative effect on the clustering task. This paper, deals with a new descriptor which avoids the drawbacks mentioned above. The novel texture descriptor combines grating cell operator outputs derived from a designed Gabor filters bank, and local binary pattern features. For the clustering task, an extended version of fuzzy type 2 clustering algorithm is also proposed. The effectiveness of the proposed segmentation approach on a variety of synthetic and textured images is highlighted. Several experimental results on a set of textured images show the superiority of the proposed approach in terms of segmentation accuracy with respect to quantitative and qualitative comparisons.

Gabor filter and graph cut based texture analysis

This paper describes a method for texture based segmentation. Texture features are extracted by applying a bank of Gabor filters using two-sided convolution strategy. Probability texture model is represented by Gaussian mixture that is trained with the Expectation-maximization algorithm. Texture similarity, obtained this way, is used like the input of a Graph cut method. We show that the combination of texture analysis and the Graph cut method produce good results.

Texture Feature Extraction Inspired By Natural Vision System And Hmax Algorithm

In this paper, a new and effective method called HMAX is used for image texture. feature extraction. This method is inspired by the biological system of brain and human vision in order to create feature vectors for image recognition. A set of C2 features obtained from HMAX algorithm that are stable against changes in angle and size, are extracted from all image datasets firstly. Then using artificial neural networks and K-nearest neighbor classifiers, eight different types of natural texture images from VISTEX dataset are classified. In order to evaluate the HMAX feature extraction method, the classification results are compared with Gabor filter banks. Since HMAX model is consistent with natural vision system, it is expected to obtain a better accuracy compared to Gabor filter banks. Experimental results with artificial neural network and K-nearest neighbor classifier show that the accuracy of 90.12% and 84.50% respectively for HMAX features. They have significant improvements compared to Gabor filter banks which obtained 78.62% and 72% accuracy.

Fabric Defect Detection Scheme Based on Gabor Filter and PCA

Gabor feature is one of the features which have been used for texture classification. In this paper, we propose a novel fabric detect detection scheme based on Gabor filter and PCA. The fabric image is split into image blocks, and then different Gabor filter banks are applied into each image blocks. A feature vector is generated by concatenating all the Gabor features with different directions and scales for each image block. Principal component analysis (PCA) is adopted to reduce the dimension of the Gabor feature vector. In the end, SVM can classify each image block as non-defective and defective. Experimental results demonstrate the efficiency of our proposed algorithm. Because of its simplicity, online implementation is possible as well.

Fast Gabor Filterbank and its Application in Fingerprint Texture Analysis

Minutiae-based matching is the main method of fingerprint recognition. Anil K. Jain brought forward a method (FingerCode) which use Gabor filter to extract the texture feature of fingerprint and match it. In order to get a faster algorithm of fingerprint identification, the properties of the real part of Gabor filter are analyzed and the Gabor filter algorithm is accelerated in special conditions and is validated by experiment, which decreases the computational complexity from O(n2) to O(n).

Automated teniae coli detection and identification on computed tomographic colonography

Computed tomographic colonography (CTC) is a minimally invasive technique for colonic polyps and cancer screening. Teniae coli are three bands of longitudinal smooth muscle on the colon surface. Teniae coli are important anatomically meaningful landmarks on human colon. In this paper, the authors propose an automatic teniae coli detection method for CT colonography. The original CTC slices are first segmented and reconstructed to a 3D colon surface. Then, the 3D colon surface is unfolded using a reversible projection technique. After that the unfolded colon is projected to a 2D height map. The teniae coli are detected using the height map and then reversely projected back to the 3D colon. Since teniae are located at the junctions where the haustral folds meet, the authors apply 2D Gabor filter banks to extract features of haustral folds. The maximum response of the filter banks is then selected as the feature image. The fold centers are then identified based on local maxima and thresholding on the feature image. Connecting the fold centers yields a path of the folds. Teniae coli are extracted as lines running between the fold paths. The authors used the spatial relationship between ileocecal valve (ICV) and teniae mesocolica (TM) to identify the TM, then the teniae omentalis (TO) and the teniae libera (TL) can be identified subsequently. The authors tested the proposed method on 47 cases of 37 patients, 10 of the patients with both supine and prone CT scans. The proposed method yielded performance with an average normalized root mean square error (RMSE) ( ± standard deviation [95% confidence interval]) of 4.87% ( ± 2.93%, [4.05% 5.69%]). The proposed fully-automated teniae coli detection and identification method is accurate and promising for future clinical applications.

Face Recognition Using Gabor Filter Bank, Kernel Principle Component Analysis and Support Vector Machine

This paper presents a novel face recognition method based on the Gabor filter bank, Kernel Principle Component Analysis (KPCA) and Support Vector Machine (SVM). At first, the Gabor filter bank with 5 frequencies and 8 orientations is applied on each face image to extract robust features against local distortions caused by variance of illumination, facial expression and pose. Then, the feature reduction technique of KPCA is performed on the outputs of the filter bank to form the new low-dimensional feature vectors. Finally, SVM is used for classification of the extracted features. The proposed method is tested on the ORL face database. The experimental results reveal that the proposed method has a maximum recognition rate of 98.5% which is higher than the other related algorithms applied on the ORL database.

US Image Segmentation Based on Expectation Maximization and Gabor Filter

Segmentation of Ultrasound (US) Images is quite challenging as the images are of poor quality, contains strong speckle noise and so are not of that high quality as CT or MRI images. Both supervised and unsupervised segmentation techniques are used for segmentation. Unsupervised segmentation approaches mainly rely on subjective assessment. We propose an unsupervised segmentation technique based on conventional Expectation Maximization (EM) algorithm applied on texture features extracted by a bank of Gabor filters. The approach includes three steps: decomposition of image using Gabor filters, texture feature extraction and segmentation. The segmentation results are compared with the work done using K-means clustering. K-means being a basic technique results in over-segmentation and converges in local minima. EM technique used after texture feature extraction is tested on many US images and results were quite satisfactory.

Classification of Prostate Histopathology Images Based on Multifractal Analysis

Histopathology is a microscopic anatomical study of body tissues and widely used as a cancer diagnosing method. Generally, pathologists examine the structural deviation of cellular and sub-cellular components to diagnose the malignancy of body tissues. These judgments may often subjective to pathologists' skills and personal experiences. However, computational diagnosis tools may circumvent these limitations and improve the reliability of the diagnosis decisions. This paper proposes a prostate image classification method by extracting textural behavior using multifractal analysis. Fractal geometry is used to describe the complexity of self-similar structures as a non-integer exponent called fractal dimension. Natural complex structures (or images) are not self-similar, thus a single exponent (the fractal dimension) may not be adequate to describe the complexity of such structures. Multifractal analysis technique has been introduced to describe the complexity as a spectrum of fractal dimensions. Based on multifractal computation of digital imaging, we obtain two textural feature descriptors; i) local irregularity: α and ii) global regularity: f(α). We exploit these multifractal feature descriptors with a texton dictionary based classification model to discriminate cancer/non-cancer tissues of histopathology images of H&E stained prostate biopsy specimens. Moreover, we examine other three feature descriptors; Gabor filter bank, LM filter bank and Haralick features to benchmark the performance of the proposed method. Experiment results indicated that the performance of the proposed multifractal feature descriptor outperforms the other feature descriptors by achieving over 94% of correct classification accuracy.

Instantaneous frequency based spectral analysis of nuclear magnetic resonance spectroscopy data

Nuclear magnetic resonance spectroscopy signals are modelled as a sum of decaying complex exponentials in noise. The spectral analysis of these signals allowing for their decomposition and the estimation of the parameters of the components is crucial to the study of biochemical samples. This paper presents a novel Gabor filterbank/notch filtering instantaneous frequency (IF) estimator, that enables the extraction of weaker and shorter lived exponentials. This new approach is an iterative procedure where a Gabor filterbank is first employed to obtain a reliable estimate of the IF of the strongest component present. The estimated strongest component is then notch filtered, which un-masks weaker components, and the procedure repeated. The performance of this method was evaluated using an artificial signal and compared to the short time Fourier transform, reassigned STFT, and the original Gabor filterbank approach. The results clearly demonstrate its superiority in uncovering weaker signals and resolving components that are very close to one another in frequency. Furthermore, the new method is shown to be more robust than the ITCMP technique at low signal to noise ratios.