Search results

An accurate detection of overhead ground wire under open surroundings with varying illumination is the premise of reliable line grasping with the off-line arm when the inspection robot cross obstacle automatically. This paper aims to propose an improved approach which is called adaptive homomorphic filter and supervised learning (AHSL) for overhead ground wire detection.

First, to decrease the influence of the varying illumination caused by the open work environment of the inspection robot, the adaptive homomorphic filter is introduced to compensation the changing illumination. Second, to represent ground wire more effectively and to extract more powerful and discriminative information for building a binary classifier, the global and local features fusion method followed by supervised learning method support vector machine is proposed.

Experiment results on two self-built testing data sets A and B which contain relative older ground wires and relative newer ground wire and on the field ground wires show that the use of the adaptive homomorphic filter and global and local feature fusion method can improve the detection accuracy of the ground wire effectively. The result of the proposed method lays a solid foundation for inspection robot grasping the ground wire by visual servo.

This method AHSL has achieved 80.8 per cent detection accuracy on data set A which contains relative older ground wires and 85.3 per cent detection accuracy on data set B which contains relative newer ground wires, and the field experiment shows that the robot can detect the ground wire accurately. The performance achieved by proposed method is the state of the art under open environment with varying illumination.

Hyperspectral imaging (HSI) systems are becoming potent technologies for computer vision tasks due to the rich information they uncover, where each substance exhibits a distinct spectral distribution. Although the high spectral dimensionality of the data empowers feature learning, the joint spatial–spectral features have not been well explored yet. Gabor convolutional networks (GCNs) incorporate Gabor filters into a deep convolutional neural network (CNN) to extract discriminative features of different orientations and frequencies. To the best if the authors’ knowledge, this paper introduces the exploitation of GCNs for hyperspectral image classification (HSI-GCN) for the first time. HSI-GCN is able to extract deep joint spatial–spectral features more rapidly and accurately despite the shortage of training samples. The authors thoroughly evaluate the effectiveness of used method on different hyperspectral data sets, where promising results and high classification accuracy have been achieved compared to the previously proposed CNN-based and Gabor-based methods.

The authors have implemented the new algorithm of Gabor convolution network on the hyperspectral images for classification purposes.

Implementing the new GCN has shown unexpectable results with an excellent classification accuracy.

To the best of the authors’ knowledge, this work is the first one that implements this approach.

Aims to develop an efficient and robust system for real‐time personal identification by automatic face recognition.

A wavelet‐based image hierarchy and a guided coarse‐to‐fine search scheme are introduced to improve the computation efficiency in the face detection task. In addition, a Gabor‐based low feature dimensional pattern is proposed to deal with the face recognition problem.

The proposal of a wavelet‐based image hierarchy and a guided coarse‐to‐fine search scheme is effective to improve the computation efficiency in the face detection task. The introduction of a low feature dimensional pattern is powerful to cope with the transformed appearance‐based face recognition problem. In addition, the use of aggregated Gabor filter responses to represent face images provides a better solution to face feature extraction.

Provides guidance in the design of automatic face recognition system for real‐time personal identification.

Biometrics recognition has been emerging as a new and effective identification technology that attains certain level of maturity. Among many body characteristics that have been used, face is one of the most commonly used characteristics and has drawn considerably large attentions. An automated system to confirm an individual's identity employing features of face is very attractive in many specialized fields.

Introduces a wavelet‐based image hierarchy and a guided coarse‐to‐fine search scheme to improve the computation efficiency in the face detection task. Introduces a Gabor‐based low feature dimensional pattern to deal with the face recognition problem.

There is a huge demand for objective on-farm techniques, which would enable identification of the ‘outliers’ of sheep for the purpose of breeding selection, reducing the fineness (or diameter) of woolgrowers’ flocks with greater confidence, and maintaining the uniform quality throughout the wool clips. In this study, the concept of texture analysis based on Gabor filtering is employed and textural features are extracted from the images of wool staples with different fineness. It is justified by the experiments that those textural features are rotation invariant and also sensitive to the fineness of wool staples and efficient in discrimination of wool staples with different fineness. Since it requires minimum manual operations, this approach has a great potential to be applied on farm or in shearing shed.

Two dimensional band-pass filters can be used to enhance the edges of the defects contained in fabric images. In this paper, we designed two types of 2D band-pass filters for the automatic detection of defects. One is the matched Gabor filter, and the other is the matched Mexican hat wavelet. Experiments show that the matched Gabor filter is more suitable for defects of higher frequency, while the matched Mexican hat wavelet is more effective for defects of lower frequency. Based on the two types of band-pass filters, an automatic fabric defect detection system was designed which boasts good accuracy and high speed.

The purpose of this paper is to propose a new algorithm chaotic pigeon-inspired optimization (CPIO), which can effectively improve the computing efficiency of the basic Itti’s model for saliency-based detection. The CPIO algorithm and relevant applications are aimed at air surveillance for target detection.

To compare the improvements of the performance on Itti’s model, three bio-inspired algorithms including particle swarm optimization (PSO), brain storm optimization (BSO) and CPIO are applied to optimize the weight coefficients of each feature map in the saliency computation.

According to the experimental results in optimized Itti’s model, CPIO outperforms PSO in terms of computing efficiency and is superior to BSO in terms of searching ability. Therefore, CPIO provides the best overall properties among the three algorithms.

The algorithm proposed in this paper can be extensively applied for fast, accurate and multi-target detections in aerial images.

CPIO algorithm is originally proposed, which is very promising in solving complicated optimization problems.

The purpose of this paper is to focus on the design of automated fabric defect detection based on cascaded low-rank decomposition and to maintain high quality control in textile manufacturing.

This paper proposed a fabric defect detection algorithm based on cascaded low-rank decomposition. First, the constructed Gabor feature matrix is divided into a low-rank matrix and sparse matrix using low-rank decomposition technique, and the sparse matrix is used as priori matrix where higher values indicate a higher probability of abnormality. Second, we conducted the second low-rank decomposition for the constructed texton feature matrix under the guidance of the priori matrix. Finally, an improved adaptive threshold segmentation algorithm was adopted to segment the saliency map generated by the final sparse matrix to locate the defect regions.

The proposed method was evaluated on the public fabric image databases. By comparing with the ground-truth, the average detection rate of 98.26% was obtained and is superior to the state-of-the-art.

The cascaded low-rank decomposition was first proposed and applied into the fabric defect detection. The quantitative value shows the effectiveness of the detection method. Hence, the proposed method can be used for accurate defect detection and automated analysis system.

Nowadays, most methods of illusion garment evaluation are based on the subjective evaluation of experienced practitioners, which consumes time and the results are too subjective to be accurate enough. It is necessary to explore a method that can quantify professional experience into objective indicators to evaluate the sensory comfort of the optical illusion skirt quickly and accurately. The purpose of this paper is to propose a method to objectively evaluate the sensory comfort of optical illusion skirt patterns by combining texture feature extraction and prediction model construction.

Firstly, 10 optical illusion sample skirts are produced, and 10 experimental images are collected for each sample skirt. Then a Likert five-level evaluation scale is designed to obtain the sensory comfort level of each skirt through the questionnaire survey. Synchronously, the coarseness, contrast, directionality, line-likeness, regularity and roughness of the sample image are calculated based on Tamura texture feature algorithm, and the mean, contrast and entropy are extracted of the image transformed by Gabor wavelet. Both are set as objective parameters. Two final indicators T1 and T2 are refined from the objective parameters previously obtained to construct the predictive model of the subjective comfort of the visual illusion skirt. The linear regression model and the MLP neural network model are constructed.

Results show that the accuracy of the linear regression model is 92%, and prediction accuracy of the MLP neural network model is 97.9%. It is feasible to use Tamura texture features, Gabor wavelet transform and MLP neural network methods to objectively predict the sensory comfort of visual illusion skirt images.

Compared with the existing uncertain and non-reproducible subjective evaluation of optical illusion clothing based on experienced experts. The main advantage of the authors' method is that this method can objectively obtain evaluation parameters, quickly and accurately obtain evaluation grades without repeated evaluation by experienced experts. It is a method of objectively quantifying the experience of experts.

The purpose of this paper is to improve the accuracy of the facial expression recognition by using genetic algorithm (GA) with an appropriate fitness evaluation function and Pareto optimization model with two new objective functions.

To achieve facial expression recognition with high accuracy, the Haar-like features representation approach and the bilateral filter are first used to preprocess the facial image. Second, the uniform local Gabor binary patterns are used to extract the facial feature so as to reduce the feature dimension. Third, an improved GA and Pareto optimization approach are used to select the optimal significant features. Fourth, the random forest classifier is chosen to achieve the feature classification. Subsequently, some comparative experiments are implemented. Finally, the conclusion is drawn and some future research topics are pointed out.

The experiment results show that the proposed facial expression recognition algorithm outperforms ones in the existing literature in terms of both the actuary and computational time.

The GA and Pareto optimization algorithm are combined to select the optimal significant feature. To improve the accuracy of the facial expression recognition, the GA is improved by adjusting an appropriate fitness evaluation function, and a new Pareto optimization model is proposed that contains two objective functions indicating the achievements in minimizing within-class variations and in maximizing between-class variations.

Any node in a mobile ad hoc network (MANET) can act as a host or router at any time and so, the nodes in the MANET are vulnerable to many types of attacks. Sybil attack is one of the harmful attacks in the MANET, which produces fake identities similar to legitimate nodes in the network. It is a serious threat to the MANET when a malicious node uses the fake identities to enter the network illegally.

A MANET is an independent collection of mobile nodes that form a temporary or arbitrary network without any fixed infrastructure. The nodes in the MANET lack centralized administration to manage the network and change their links to other devices frequently.

So for securing a MANET, an approach based on biometric authentication can be used. The multimodal biometric technology has been providing some more potential solutions for the user to be able to devise an authentication in MANETs of high security.

The Sybil detection approach, which is based on the received signal strength indicator (RSSI) variations, permits the node to be able to verify the authenticity of communicating nodes in accordance with their localizations.

As the MANET node suffers from a low level of memory and power of computation, there is a novel technique of feature extraction that is proposed for the multimodal biometrics that makes use of palm prints that are based on a charge-coupled device and fingerprints, along with the features that are fused.

This paper proposes an RSSI-based multimodal biometric solution to detect Sybil attack in MANETs.

The results of the experiment have indicated that this method has achieved a performance which is better compared to that of the other methods.