Gabor Filter Parameters Research Articles

Novel MobileNet based Multipath Convolutional Neural Network for defect detection in fabrics

Automatic fabric defect detection and classification is the most important process in the textile industry to ensure the fabric quality. In the existing systems, a learning based method is used for detecting defects in plain weave fabrics. In this paper, a novel MobileNet based Multipath Convolutional Neural Network (MMPCNN) architecture is proposed for detection and classification of simple and complex patterned fabric defects. In the proposed MMPCNN architecture, MobileNet model is used in the first path. In this, Gabor filter bank is used instead of conventional filters in the first convolution layer. A simple convolutional neural network architecture with Gray Level Co-occurrence Matrix (GLCM) features as an input is used in the second path of the MMPCNN architecture. Gabor filters are more useful for analyzing the texture with different orientations and scales. Each Gabor filter parameter has its own impact on analyzing the texture and extracting the information from the texture. Therefore, in this paper, the use of Gabor filter parameters in MMPCNN architecture is analyzed. The proposed model is experimented on the TILDA textile image database and it is able to achieve 100% accuracy with reduced trainable parameters for fabric defect detection and classification.

Artificial Bee Colony Based Gabor Parameters Optimizer (ABC-GPO) for Modulation Classification.

Modulation classification is one of the essential requirements in the various cognitive radio applications where prior information about the incoming signal is unknown. The modulation classification using a pattern recognition approach can be achieved in 2 modules: first, parameters are extracted from the noisy signal, and then feature selection is carried out using a Gabor filter network (GFN). In the second module, features are exploited for classification purposes. The modulation formats considered for the purpose of classification are BPSK, QPSK, 8PSK, 16PSK, 64PSK, 4FSK, 8FSK, 16FSK, QAM, 8QAM, 16QAM, 32QAM, and 64QAM. The Gabor filter parameters and weights of the adaptive filter are attuned using the Delta rule and recursive least square (RLS) algorithm until the cost function is minimized. In the end, the artificial bee colony (ABC) algorithm is used to optimize the Gabor parameters as well as the classifier's performance. The simulation results show the supremacy of the proposed classifier structure.

Phase-based displacement measurement on a straight edge using an optimal complex Gabor filter

In recent years, a number of phase-based motion processing techniques have been developed, and these allow for motion signals to be extracted from the local phase. The phase is generated by applying a pair of even- and odd-symmetric filters, and it is more robust to the intensity change. However, the phase can be unstable in certain areas where it is not linearly correlated with motion. This paper proposes an accurate and robust displacement measurement technique using an optimal complex Gabor filter and phase-based optical flow (POF) to measure the vibration response of a straight edge with the generated linear phase. The causes of nonlinear phase are discussed, and the nonlinearity of phase is used as an indicator of the measurement accuracy. Three types of nonlinear phase caused by noise background and inappropriate filter parameters for a straight edge are presented, along with solutions that optimize the parameters of the complex Gabor filter to obtain the phase with low nonlinearity. A numerical experiment is conducted on artificially created patterns to demonstrate the correlation between the proposed phase nonlinearity and the measurement accuracy. The validation experiments are carried out on a 5-story structure using a Laser Doppler Vibrometer (LDV) and a camera to demonstrate the accuracy and robustness of the proposed technique using the phase with low nonlinearity. The results show that the proposed technique can measure the vibration at 0.01-pixel scale. In addition, the robustness of the proposed technique is validated by performing experiments under different illumination conditions. The vibration responses of the 5-story structure with noisy background are measured using both accelerometers and a camera to perform the output-only modal identification. The results confirm that the proposed method can accurately identify modal frequencies, damping ratios, and high-resolution operational deflection shapes (ODS) requiring no pure background.

Multi-View Face Detection in Open Environments using Gabor Features and Neural Networks

Multi-view face detection in open environments is a challenging task, due to the wide variations in illumination, face appearances and occlusion. In this paper, a robust method for multi-view face detection in open environments, using a combination of Gabor features and neural networks, is presented. Firstly, the effect of changing the Gabor filter parameters (orientation, frequency, standard deviation, aspect ratio and phase offset) for an image is analysed, secondly, the range of Gabor filter parameter values is determined and finally, the best values for these parameters are specified. A multilayer feedforward neural network with a back-propagation algorithm is used as a classifier. The input vector is obtained by convolving the input image and a Gabor filter, with both the angle and frequency values equal to π/2. The proposed algorithm is tested on 1,484 image samples with simple and complex backgrounds. The experimental results show that the proposed detector achieves great detection accuracy, by comparing it with several popular face-detection algorithms, such as OpenCV’s Viola-Jones detector.

Fabric defect detection using a hybrid particle swarm optimization-gravitational search algorithm and a Gabor filter.

Recently, fabric defect inspection techniques have received attention in textile production procedures, since demands for various textile fabrics are growing. However, visual inspection for fabric defect detection is a very difficult problem because of the complexity of the fabric pattern and various defects. In this paper, we propose a method to detect the defects in fabric surfaces using the hybrid Particle Swarm Optimization-Gravitational Search Algorithm (PSO-GSA) and ellipse Gabor filter (EGF). In the proposed method, the hybrid PSO-GSA been employed to optimize the parameters of the EGF. Gabor filter parameters for the texture of the nondefective fabric images adjusted via the hybrid PSO-GSA with good convergence and solution characteristics. The defective fabric image is convoluted with the selected optimal Gabor filter, and we generate binary images by thresholding processing. The proposed method uses only one optimal filter, so fabric defect inspection is faster and more cost effective. Experimental results show that the proposed method is robust and achieves accurate detection of fabric defects.

RETRACTED ARTICLE: Investigation of rotated local Gabor features in face recognition using fusion techniques

One of the major challenges related to face recognition is the effective face representation. In this paper, a new rotation algorithm is proposed to make the slanting face to upright position. Gabor features have been identified to be effective for face recognition. To investigate the prospective of Gabor phase and its combination with magnitude for face recognition, Rotated Local Gabor XOR patterns (RLGXP), which encodes the Rotated Gabor phase by using the local XOR pattern (LXP) operator is first proposed, which increases the effectiveness of face representation. Then, Cell-based Fishers linear discriminant (CFLD) to reduce the dimensionality of the proposed descriptor is introduced. Finally, by using CFLD, local patterns of Rotated Gabor magnitude and phase for face recognition are combined. This proposed approach is evaluated on MIT, GTAVE, PIE, CMU and Home databases. Moreover, to enhance the effectiveness of face representation through feature design (RLGXP), the Gabor filter parameters like mask size, scale and orientation are very important. The effectiveness of the rotating local Gabor model + CFLD method was verified for upslopes and uprights of different data sets. The analysis of face feature representation using the RLGXP + CFLD method basically depends on the phase range, the appropriate choice of the number of sub-cells per pattern map and size of neasret region. Here, the sensitivity analysis used for the above three parameters is best selected and executed. This paper also investigates the effect of different Gabor filter parameters on face recognition accuracy. Parameter Selection Investigation result proves that Gabor wavelets comprising 5 scales and 8 orientations have been chosen to extract Facial Feature Points (FFP). The final result shows that Rotated Local Gabor Features provides the best face recognition accuracy.

Fuzzified Circular Gabor Filter for Circular and Near-Circular Object Detection

This paper presents a new algorithm for filtering and detecting circular and deformed circular objects. The resulting procedure is based on fuzzifying the parameters of a circular Gabor filter to optimize the response of the circular Gabor filter and achieve additional selectivity of the filter. Circular and deformed circular objects of interest were efficiently extracted, and considerable resistance to noise and image degradation was achieved.

Particle swarm optimization-based optimal real Gabor filter for surface inspection

PurposeThe traditional methods have difficulty to inspection various types of copper strips defects as inclusions, pits and delamination defects under uneven illumination. Therefore, this paper aims to propose an optimal real Gabor filter model for inspection; however, improper selection of Gabor parameters will cause the boundary between the defect and the background image to be not very clear. This will make the defect and the background cannot be completely separated.Design/methodology/approachThe authors proposed an optimal Real Gabor filter model for inspection of copper surface defects under uneven illumination. This proposed method only requires a single filter by calculating the specific convolution energy of the Gabor filter with the image. The Real Gabor filter’s parameter is optimized by particle swarm optimization (PSO), which objective fitness function is maximization of the Gabor filter’s energy average divided by the energy standard deviation, the objective makes a distinction between the defect and normal area.FindingsThe authors have verified the effect with different iterations of parameter optimization using PSO, the effects with different control constant of energy and neighborhood window size of real Gabor filter, the experimental results on a number of metal surface have shown the proposed method achieved a well performance in defect recognition of metal surface.Originality/valueThe authors propose a defect detection method based on particle swarm optimization for single Gabor filter parameters optimization. This proposed method only requires a single filter and finds the best parameters of the Gabor filter. By calculating the specific convolution energy of the Gabor filter and the image, to obtain the best Gabor filter parameters and to highlight the defects, the particle swarm optimization algorithm’s fitness objective function is maximize the Gabor filter's average energy divided by the energy standard deviation.

Adaptive Learning Gabor Filter for Finger-Vein Recognition

Presently, finger-vein recognition is a new research direction in the field of biometric recognition. The Gabor filter has been extensively used for finger-vein recognition; however, its parameters are difficult to adjust. To solve this problem, an adaptive-learning Gabor filter is presented herein. We combine convolutional neural networks with a Gabor filter to calculate the gradient of the Gabor-filter parameters, based on the objective function, and to then optimize its parameters via back-propagation. The parameter θ of Gabor filter can be trained to the same angle as the vein texture of finger vein image. The parameter σ of Gabor filter has a certain relation with λ, and the parameter λ of Gabor filter can converge to the optimal value well. Using this method, we not only select appropriate and effective Gabor filter parameters to design the filter banks, we also consider the relationship between those parameters. Finally, we perform experiments on four public finger-vein datasets. Experimental results demonstrate that our method outperforms state-of-the-art methods in finger-vein classification.

Direction navigability analysis of geomagnetic field based on Gabor filter

Direction navigability analysis is a supplement to the navigability analysis theory, in which extraction of the direction suitable-matching features (DSMFs) determines the evaluation performance. A method based on the Gabor filter is proposed to estimate the direction navigability of the geomagnetic field. First, the DSMFs are extracted based on the Gabor filter's responses. Second, in the view of pattern recognition, the classification accuracy in fault diagnosis is introduced as the objective function of the hybrid particle swarm optimization (HPSO) algorithm to optimize the Gabor filter's parameters. With its guidance, the DSMFs are extracted. Finally, a direction navigability analysis model is established with the support vector machine (SVM), and the performances of the models under different objective functions are discussed. Simulation results show the parameters of the Gabor filter have a significant influence on the DSMFs, which, in turn, affects the analysis results of direction navigability. Moreover, the risk of misclassification can be effectively reduced by using the analysis model with optimal Gabor filter parameters. The proposed method is not restricted in geomagnetic navigation, and it also can be used in other fields such as terrain matching and gravity navigation.

Research on filter’s parameter selection based on PROMETHEE method

The selection of filter’s parameters in target recognition was studied in this paper. The PROMETHEE method was applied to the optimization problem of Gabor filter parameters decision, the correspondence model of the elemental relation between two methods was established. The author took the identification of military target as an example, problem about the filter’s parameter decision was simulated and calculated by PROMETHEE. The result showed that using PROMETHEE method for the selection of filter’s parameters was more scientific. The human disturbance caused by the experts method and empirical method could be avoided by this way. The method can provide reference for the parameter configuration scheme decision of the filter.

Density Weighted Connectivity of Grass Pixels in image frames for biomass estimation

Accurate estimation of the biomass of roadside grasses plays a significant role in applications such as fire-prone region identification. Current solutions heavily depend on field surveys, remote sensing measurements and image processing using reference markers, which often demand big investments of time, effort and cost. This paper proposes Density Weighted Connectivity of Grass Pixels (DWCGP) to automatically estimate grass biomass from roadside image data. The DWCGP calculates the length of continuously connected grass pixels along a vertical orientation in each image column, and then weights the length by the grass density in a surrounding region of the column. Grass pixels are classified using feedforward artificial neural networks and the dominant texture orientation at every pixel is computed using multi-orientation Gabor wavelet filter vote. Evaluations on a field survey dataset show that the DWCGP reduces Root-Mean-Square Error from 5.84 to 5.52 by additionally considering grass density on top of grass height. The DWCGP shows robustness to non-vertical grass stems and to changes of both Gabor filter parameters and surrounding region widths. It also has performance close to human observation and higher than eight baseline approaches, as well as promising results for classifying low vs. high fire risk and identifying fire-prone road regions.

An evolutionary single Gabor kernel based filter approach to face recognition

For the past few decades, Gabor filter banks have been used for extracting features in face recognition. The state-of-the-art approach for the design and selection of Gabor filter banks is based on a trial and error. This results in more computational complexity and higher response time. To overcome this problem, an attempt is made to design a single optimized Gabor filter instead of a filter bank for feature extraction. This approach improves the filter performance by significantly reducing the computational complexity and response time. The hybrid particle swarm optimization-gravitational search algorithm (PSO-GSA) is used for optimizing the parameters of the single Gabor filter. In this context, an evolutionary single Gabor kernel (ESGK) based filter approach is proposed for face recognition. The proposed method is used to extract Gabor energy feature vectors from face images. We also propose a new eigenvalue based classification approach for face recognition. This approach is derived from sparse based representation methods. The novelty in our paper is measurement of sparsity of the weighting coefficients of each training sample. The main contribution of the paper is two-fold. Firstly, investigation of ESGK approach, which is not found in the literature. Secondly, introducing a new eigen value based classifier. FERET, ORL, UMIST, GT and LFW databases are used to measure the efficiency of our proposed method. The results are compared with a holistic Gabor filter bank based recognition methods. It is witnessed that our proposed method outperforms the state-of-the-art methods.

Unsupervised Method for Building Detection using Gabor Filters

Automatic methods are a convenient solution to extract buildings from remote sensing images. In this paper, we propose an unsupervised method to extract buildings by means of the Gabor filters and morphological operators. Our proposed method starts from a set of the Gabor filter parameters which is selected empirically to generate a two-dimensional impulse response. The convolution of the impulse response with the image of interest enhances the buildings and attenuates the background. Moreover, morphological operators are applied to further refine the resulting class of interest. The developed algorithm is applied on many remotely sensed images; the obtained results are highly satisfactory and promising.

Automation of Optimized Gabor Filter Parameter Selection for Road Cracks Detection

Automated systems for road crack detection are extremely important in road maintenance for vehicle safety and traveler’s comfort. Emerging cracks in roads need to be detected and accordingly repaired as early as possible to avoid further damage thus reducing rehabilitation cost. In this paper, a robust method for Gabor filter parameters optimization for automatic road crack detection is discussed. Gabor filter has been used in previous literature for similar applications. However, there is a need for automatic selection of optimized Gabor filter parameters due to variation in texture of roads and cracks. The problem of change of background, which in fact is road texture, is addressed through a learning process by using synthetic road crack generation for Gabor filter parameter tuning. Tuned parameters are then tested on real cracks and a thorough quantitative analysis is performed for performance evaluation.

Study on Woven Fabric Texture Based on Fourier Transform and Gabor Transform

Woven fabric texture was periodic and complex, the woven fabric texture analysis method was based on Fourier transform and Gabor transform. Firstly the frequency range of woven fabric texture was obtained by using the Fourier Transform method, and the influence on fabric frequency of image resolution and fabric density was analyzed. Then the main parameters of Gabor filter was confirmed by the woven fabric texture frequency, and the sub-images which contain different texture information were obtained after the woven fabric images were decomposed and fused in different scales and directions using the Gabor filters. Finally the main texture enhancement method, the main texture elimination method, the direntional texture analysis method and extraessential texture enhancement method were discussed. The experiment proved that this method would be a powerful tool in the application of texture analysis.

The fabric defect detection based on CIE L*a*b* color space using 2-D Gabor filter

A detection algorithm based on CIE L*a*b* color space is proposed to detect various colorful fabric defects more accurately and avoid the error detection resulted from losing image information of graying. CIE L*a*b* color space is transformed from XYZ space via nonlinear transformation of RGB space. First, three features including the brightness characteristics L*, color information of a* and b* which are used to form 2-D Gabor filter in a complex number can be acquired. Genetic algorithm with the objective function in a form of energy is adopted to select optimal Gabor filter parameters. Second, filter built by flawless image is used to filter the corresponding drawbacks of image. Third, ultimate results are obtained through sliding threshold segmentation method and properly de-noising. The experiment success rate is 95.83%, which indicate that this method can detect diversiform colorful fabric defect accurately.

Differential evolution-based optimal Gabor filter model for fabric inspection

In this paper, a defect detection model using optimized Gabor filters, which is suitable for real-time operation, is proposed to tackle the woven fabric inspection problem in fashion industry. Based on the analysis of the particular characteristics of fabric defects, the proposed model utilizes composite differential evolution (CoDE) to optimize the parameters of Gabor filters, which can achieve the optimal feature extraction of fabric defects. Together with thresholding and fusion operations, the optimal Gabor filters can successfully segment the defects from the original image background. By using optimal Gabor filters instead of a Gabor filter bank, the computational cost of the detection model can be significantly reduced. The performance of the proposed defect detection model is evaluated off-line through extensive experiments based on various types of fabric. Experimental results reveal that the proposed detection model is effective and robust, and is superior than four existing models in terms of the high detection rate and low false alarm rate.

Defect Detection on Printed Fabrics Via Gabor Filter and Regular Band

Two methods are proposed in this paper to inspect printed fabrics. One method is to apply a genetic algorithm to select parameters of optimal Gabor filter. Optimal Gabor filter can reduce the noise information of printed fabrics, which can achieve defect detection of printed fabrics. The other is in utilizing distance matching function to determine the unit of printed fabrics. Extracting features on a moving unit of printed fabrics can realize defect segmentation of printed fabrics. Two approaches of defect detection have their own advantages. Detecting method with Gabor filter using genetic algorithm has perfect detection results of random printed fabrics, the other method based on statistical rule can receive better defect detection results of regular printed fabrics. Both methods can be realized in practice and detection time of proposed methods can occupy little in total detection time.

Rapid and non-invasive quantification of intramuscular fat content of intact pork cuts

Having acquired near infrared (NIR) hyperspectral images of intact pork loin samples through an NIR hyperspectral imaging system, the efficiency of a variety of image processing techniques including texture pattern analysis techniques were applied to process hyperspectral images so as to determine the intramuscular fat (IMF) content non-destructively. After the segmentation of region of interest (ROI), the raw spectral, texture-based spectral and textural characteristics of pork images were extracted by spectral averaging and pattern recognition techniques namely Gabor filter and improved gray level co-occurrence matrix (GLCM), respectively. First derivatives of the non-filtered and the Gabor filtered spectra were also investigated. Full waveband partial least squares regression (PLSR) was employed to determine the optimal parameters of Gabor filter and GLCM, and to select optimal wavelengths for IMF prediction. A stepwise procedure was applied to the optimal wavelengths to further optimize them to key wavelengths. Multiple linear regression (MLR) models were built based on the key wavelengths. Mean spectra and the Gabor filtered spectra outperformed GLCM. The best result, represented by correlation coefficients of calibration (Rc), cross validation (Rcv) and prediction (Rp) of 0.89, 0.89, and 0.86, respectively, was achieved using the first derivative of Gabor filtered spectra at 1193 and 1217 nm. To visualize the IMF content in pork, the distribution maps of IMF content in pork were drawn using a mean spectra-based MLR model. These promising results highlight the great potential of NIR hyperspectral imaging for non-destructive prediction of IMF content of intact pork.