Search

A binocular camera composed of colour and depth cameras is an accurate and inexpensive tool for recognising fruit trees to plan spraying paths. For this purpose, however, the accurate visual registration of the depth and colour cameras is a problem that must be solved. This paper proposes a local feature point extraction (LFPE) algorithm for depth-colour image registration, which automatically extracts the feature points of local regions in the colour and depth images for registration. First, the binarised colour and depth images are divided into local regions after edge extraction, and the regions in which the edge features match at several pixels between images are selected. Then, these regions are again divided into smaller regions to detect local extrema of the pixels as feature points. Finally, the matching feature points are calculated based on the Euclidean distance and are used to optimise the affine transformation matrix. To verify the accuracy and effectiveness of the algorithm, it is compared with the FAST, SURF and BRISK algorithms. The experimental results show that the accuracy of the proposed LFPE algorithm is 1.6 times that of BRISK, 3.5 times that of FAST and 40.1 times that of SURF. Therefore, it is more suitable for registration between depth and colour images. • Proposed a depth-colour image registration method for orchard precision spraying. • A local feature point extraction (LFPE) algorithm is proposed to match images. • The registration accuracy of LFPE is much better than other similar algorithms. [ABSTRACT FROM AUTHOR]

• A small target detection algorithm based on feature interaction and guided learning. • A feature guided alignment module is designed to obtain more effective features. • Gaussian distribution sample allocation strategy is introduced to obtain better samples. • Feature interaction and decoupling detection enhance the detection task capability. • A new regression loss function is used to optimize the localization ability to a certain extent. At present, for the diverse target sizes, different angles, and complex environment in aerial images, how to detect small objects effectively in aerial images is still a challenge task. In order to further improve the detection accuracy and reduce the missing rate, in this paper, we proposes a small target detection algorithm based on feature interaction and guided learning. Firstly, the feature guided alignment module is designed to deal with the problem of information loss and overlap. Secondly, the misallocation of small object samples is optimized by introducing gaussian sample allocation strategy. Then the interactive parallel detection header is designed to solve the detection task conflict problem. Finally, the new regression loss function is designed to enhance the localization ability of the target. The experimental results on the Tinyperson dataset and Visdrone dataset show that this model can improve the detection accuracy and reduce the missing rate of small targets effectively. [ABSTRACT FROM AUTHOR]

The unavailability and variability of training samples are the two essential concerns in the training of deep neural network models for image classification. For automated image monitoring systems, these problems are difficult when training a model through supervised learning methods because of the time and effort required. This paper proposes an adaptive solution to this problem by applying online semi-supervised learning to an automated insect pest monitoring system. The method used includes unsupervised pseudo-labelling of insect images and the training of semi-supervised classifier models for insect image recognition. The pseudo-labelling algorithm includes three major components: image labelling, label reconfirmation, and sample cleaning. Experiments were conducted on two unlabelled 1-year insect image datasets to evaluate the efficacy of the proposed method. It was found that the pseudo-labelling algorithm could achieve accuracy up to 0.963, hence enabling automated training data collection. The temporal improvement of the insect recognition performance by including new training data to retrain the classifier model was comparable in performance to the supervised learning approach as evaluated by cluster density, silhouette score, and F 1 -score. The proposed method was also able to automatically collect quality samples and train models regardless of the complexity of the images, making it a good alternative to replace laborious supervised learning. The proposed method can prevent contamination of a training dataset when images from new locations are collected. The presented techniques may also be used in other continuous learning applications that require automated training data collection and online model update. [Display omitted] • Semi-supervised learning method for an insect pest monitoring system was proposed. • Accuracy of the pseudo-labelling algorithm can be as high as 0.963. • Characteristics and variation of training data in classifier models were assessed. • Performance of classifier models can be improved through semi-supervised learning. • Techniques can be used for automated training data collection and model update. [ABSTRACT FROM AUTHOR]

Recombination hotspots in a genome are unevenly distributed. Hotspots are regions in a genome that show higher rates of meiotic recombinations. Computational methods for recombination hotspot prediction often use sophisticated features that are derived from physico-chemical or structure based properties of nucleotides. In this paper, we propose iRSpot-SF that uses sequence based features which are computationally cheap to generate. Four feature groups are used in our method: k-mer composition, gapped k-mer composition, TF-IDF of k-mers and reverse complement k-mer composition. We have used recursive feature elimination to select 17 top features for hotspot prediction. Our analysis shows the superiority of gapped k-mer composition and reverse complement k-mer composition features over others. We have used SVM with RBF kernel as a classification algorithm. We have tested our algorithm on standard benchmark datasets. Compared to other methods iRSpot-SF is able to produce significantly better results in terms of accuracy, Mathew's Correlation Coefficient and sensitivity which are 84.58%, 0.6941 and 84.57%. We have made our method readily available to use as a python based tool and made the datasets and source codes available at: https://github.com/abdlmaruf/iRSpot-SF. An web application is developed based on iRSpot-SF and freely available to use at: http://irspot.pythonanywhere.com/server.html. • Simple sequence based feature extraction • Effective feature selection • Recombination hotspot prediction • Web application and prediction tool [ABSTRACT FROM AUTHOR]

Highlights • An improved face recognition is proposed using the fusion of global and local structures. • A combination of preprocessing techniques coupled with discriminative feature extractors. • Improved performance under poor illumination, partial occlusion and low resolution. • Our best recognition results using FRGC 2.0.4 indicated more than 28% improvement. In this paper an improved face recognition algorithm under degrading conditions is proposed. The proposed algorithm uses a combination of preprocessing techniques coupled with discriminative feature extractors to obtain the best distinctive features for classification. Preprocessing approach is the fusion of multi-scale Weber and enhanced complex wavelet transform. Combination of multiple feature extraction based on Gabor filters, block-based local phase quantization (LPQ) coupled with principal component analysis (PCA) proved to be very effective to improve correct rate of recognition. We have also used two known classifiers, extreme learning machine (ELM), and sparse classifier (SC), and fused their outputs to obtain best recognition rate. Experimental results show improved performance of proposed algorithm under poor illumination, partial occlusion and low-quality images in uncontrolled conditions. Our best recognition results using second version of face recognition grand challenge (FRGC 2.0.4) which is the most challenging database, indicated more than 28% improvement over previous works. [ABSTRACT FROM AUTHOR]

Video clipping system is very important in many intelligent applications. In order to shorten the time of video and extract the framework of the video, many methods have been proposed. But these methods just considered videos without taking sound into account. As we know, sound is also an important information for image processing. For example, many sport match videos include rich sound of audience and commentator such as NBA. In addition, human pay more attention to some video clips of interest (VCOI) such as scoring time instead of pause. So in this paper, we propose a sound-based video clipping framework toward specific sports scenes. First, we convert sound of sport videos to sonogram. For some aesthetically-pleasing images (APIM) such as slam dunk or jump shot, a set of object patches are selected using BING feature. Then, these object patches are ordered by our active object patches ranking algorithm. After that, ordered object patches and sonogram are fed into CNN respectively to obtain patch-level deep feature. In order to obtain image-level deep representation, deep feature extracted from ordered object patches are aggregated statistically into a deep representation. Finally, probabilistic model is used to select VCOI and APIM. Experiments on some NBA basketball matches have shown the effectiveness of our video clipping framework. [ABSTRACT FROM AUTHOR]

Highlights • Information about image feature extraction methods is provided. • A survey on image clustering for various applicative areas is carried out. • Research gaps and challenges in image clustering are discussed. • Image characteristics along with suitable clustering approaches are provided. A huge amount of image data is being collected in real world sectors. Image data analytics provides information about important facts and issues of a particular domain. But, it is challenging to handle voluminous, unstructured and unlabeled image collection. Clustering provides groups of homogeneous unlabeled data. Therefore, it is used quite often to access the interesting data easily and quickly. Image clustering is a process of partitioning image data into clusters on the basis of similarities. Whereas, features extracted from images are used for the computation of similarities among them. In this paper, significant feature extraction approaches and clustering methods applied on the image data from nine important applicative areas are reviewed. Medical, 3D imaging, oceanography, industrial automation, remote sensing, mobile phones, security and traffic control are considered applicative areas. Characteristics of images, suitable clustering approaches for each domain, challenges and future research directions for image clustering are discussed. [ABSTRACT FROM AUTHOR]

This paper proposes a novel face recognition method that improves Huang’s linear discriminant regression classification (LDRC) algorithm. The original work finds a discriminant subspace by maximizing the between-class reconstruction error and minimizing the within-class reconstruction error simultaneously, where the reconstruction error is obtained using Linear Regression Classification (LRC). However, the maximization of the overall between-class reconstruction error is easily dominated by some large class-specific between-class reconstruction errors, which makes the following LRC erroneous. This paper adopts a better between-class reconstruction error measurement which is obtained using the collaborative representation instead of class-specific representation and can be regarded as the lower bound of all the class-specific between-class reconstruction errors. Therefore, the maximization of the collaborative between-class reconstruction error maximizes each class-specific between-class reconstruction and emphasizes the small class-specific between-class reconstruction errors, which is beneficial for the following LRC. Extensive experiments are conducted and the effectiveness of the proposed method is verified. [ABSTRACT FROM AUTHOR]

Abstract: Localized faults in gearboxes tend to result in periodic shocks and thus arouse periodic responses in vibration signals. Feature extraction has always been a key problem for localized fault diagnosis. This paper proposes a new fault feature extraction technique for gearboxes by using sparsity-enabled signal decomposition method. The sparsity-enabled signal decomposition method separates signals based on the oscillatory behavior of the signal rather than the frequency or scale. Thus, the fault feature can be nonlinearly extracted from vibration signals. During the implementation of the proposed method, tunable Q-factor wavelet transform, for which the Q-factor can be easily specified, is adopted to represent vibration signals in a sparse way, and then morphological component analysis (MCA) is employed to estimate and separate the distinct components. The corresponding optimization problem of MCA is solved by the split augmented Lagrangian shrinkage algorithm (SALSA). With the proposed method, vibration signals of the faulty gearbox can be nonlinearly decomposed into high-oscillatory component and low-oscillatory component which is the fault feature of gearboxes. To evaluate the performance of the proposed method, this paper investigates the effect of two parameters pertinent to MCA and SALSA: the Lagrange multiplier and the penalty parameter. The effectiveness of the proposed method is verified by both the simulated and practical gearbox vibration signals. Results show the proposed method outperforms empirical mode decomposition and spectral kurtosis in extracting fault features of gearboxes. [Copyright &y& Elsevier]

A Schatten p -norm-based two-dimensional principal component analysis (2DPCA-SP) method was proposed for image feature extraction in our previous work. As an unsupervised method, 2DPCA-SP ignores the label information of training samples, which is essential to classification tasks. In this paper, we propose a novel Schatten p -norm-based two-dimensional discriminant analysis (2DDA-SP) method for image feature extraction, which learns an optimal projection matrix by maximizing the difference of Schatten p -norm-based between-class dispersion and Schatten p -norm-based within-class dispersion in low-dimensional feature space. By using both the Schatten p -norm metric and the label information of training samples, 2DDA-SP not only can efficiently extract discriminative features, but is also robust to outliers. We also propose an efficient iterative algorithm to solve the optimization problem of 2DDA-SP with 0 < p < 1 . Experimental results on several image databases show that 2DDA-SP with 0 < p < 1 is effective and robust for image feature extraction. [ABSTRACT FROM AUTHOR]

Abstract: In this paper, we study the problem of feature extraction for pattern classification applications. RELIEF is considered as one of the best-performed algorithms for assessing the quality of features for pattern classification. Its extension, local feature extraction (LFE), was proposed recently and was shown to outperform RELIEF. In this paper, we extend LFE to the nonlinear case, and develop a new algorithm called kernel LFE (KLFE). Compared with other feature extraction algorithms, KLFE enjoys nice properties such as low computational complexity, and high probability of identifying relevant features; this is because KLFE is a nonlinear wrapper feature extraction method and consists of solving a simple convex optimization problem. The experimental results have shown the superiority of KLFE over the existing algorithms. [Copyright &y& Elsevier]

This paper addresses the detection of periodic transients in vibration signals so as to detect faults in rotating machines. For this purpose, we present a method to estimate periodic-group-sparse signals in noise. The method is based on the formulation of a convex optimization problem. A fast iterative algorithm is given for its solution. A simulated signal is formulated to verify the performance of the proposed approach for periodic feature extraction. The detection performance of comparative methods is compared with that of the proposed approach via RMSE values and receiver operating characteristic (ROC) curves. Finally, the proposed approach is applied to single fault diagnosis of a locomotive bearing and compound faults diagnosis of motor bearings. The processed results show that the proposed approach can effectively detect and extract the useful features of bearing outer race and inner race defect. [ABSTRACT FROM AUTHOR]

Multisensory data fusion-based online welding quality monitoring has gained increasing attention in intelligent welding process. This paper mainly focuses on the automatic detection of typical welding defect for Al alloy in gas tungsten arc welding (GTAW) by means of analzing arc spectrum, sound and voltage signal. Based on the developed algorithms in time and frequency domain, 41 feature parameters were successively extracted from these signals to characterize the welding process and seam quality. Then, the proposed feature selection approach, i.e., hybrid fisher-based filter and wrapper was successfully utilized to evaluate the sensitivity of each feature and reduce the feature dimensions. Finally, the optimal feature subset with 19 features was selected to obtain the highest accuracy, i.e., 94.72% using established classification model. This study provides a guideline for feature extraction, selection and dynamic modeling based on heterogeneous multisensory data to achieve a reliable online defect detection system in arc welding. [ABSTRACT FROM AUTHOR]

Canonical correlation analysis (CCA) is an efficient method for dimensionality reduction on two-view data. However, as an unsupervised learning method, CCA cannot utilize partly given label information in multi-view semi-supervised scenarios. In this paper, we propose a novel two-view semi-supervised learning method, called semi-supervised canonical correlation analysis based on label propagation (LPbSCCA). LPbSCCA incorporates a new sparse representation based label propagation algorithm to infer label information for unlabeled data. Specifically, it firstly constructs dictionaries consisting of all labeled samples; and then obtains reconstruction coefficients of unlabeled samples using sparse representation technique; at last, by combining given labels of labeled samples, estimates label information for unlabeled ones. After that, it constructs soft label matrices of all samples and probabilistic within-class scatter matrices in each view. Finally, in order to enhance discriminative power of features, it is formulated to maximize the correlations between samples of the same class from cross views, while minimizing within-class variations in the low-dimensional feature space of each view simultaneously. Furthermore, we also extend a general model called LPbSMCCA to handle data from multiple (more than two) views. Extensive experimental results from several well-known datasets demonstrate that the proposed methods can achieve better recognition performances and robustness than existing related methods. [ABSTRACT FROM AUTHOR]

• Proposal of a methodology for estimating the period of faulty impulses. • Development of an APMESR algorithm for extracting incipient bearing fault features. • Selection of MODWPT as the linear transformation for APMESR. • Evaluation and comparison of period estimation methodologies and transformations. • Verification of APMESR's effectiveness through several simulations and experiments. Bearing incipient fault feature extraction is crucial and challenging throughout its life cycle. In this paper, an adaptive period matching enhanced sparse representation (APMESR) algorithm is developed to address this issue. First, a novel methodology for estimating the period of faulty impulses is proposed from the perspective of mining the periodicity-related numerical patterns. Second, the period estimation methodology is embedded in a sparse representation model to implement adaptive period matching to form APMESR, which is capable of achieving periodic sparsity. Third, maximal overlap discrete wavelet packet transform is selected as the linear transformation of APMESR for improving its ability to reduce noise and highlight periodic impulse signatures. Furthermore, evaluations and comparisons are conducted using simulations to demonstrate the validity and performance of the proposed period estimation methodology, linear transformation, and APMESR. Experimental results indicate that APMESR can effectively extract incipient bearing fault features and outperforms other well-advanced methods. [ABSTRACT FROM AUTHOR]

• A novel adaptive signal decomposition method named RVME is proposed. • Simulated and experimental cases validate the effectiveness of the proposed method. • RVME has higher computational efficiency than VMD. The variational mode extraction (VME) developed on the similar basis of variational mode decomposition (VMD) can effectively separate a specific mode by knowing an approximate center frequency from the multi-component signal. Compared with VMD, VME has made certain progress in improving the extraction accuracy and reducing the computational cost when the aim is to separate a specific mode. As the fault feature signal of rolling bearing is usually a band-limited signal which is compact around the excited resonant frequency, VME becomes a potentially effective tool for extracting fault characteristics of rolling bearing. However, how to adaptively determine the center frequency and the penalty factor are two difficult problems when using VME to separate the desired component. Accordingly, this paper presents the recursive variational mode extraction (RVME), an iterative VME-based signal decomposition algorithm. At each iteration of RVME, the initial center frequency and penalty factor for the reconstruction of a specific sub-component can be adaptively determined according to the dominant frequency of the residual signal of the previous iterative decomposition, which makes RVME an adaptive signal decomposition algorithm. The presented method is applied to simulated and experimental fault signals and compared with other classical fault feature extraction approaches, such as variational mode decomposition (VMD) and spectral kurtosis (SK). The results confirm that the established method can extract the fault features as effective as VMD, but it is significantly better than VMD in terms of computational efficiency. Meanwhile, the proposed method shows a stronger capability of weak bearing fault feature extraction and compound fault feature separation compared with SK. [ABSTRACT FROM AUTHOR]

Abstract: Recent advances in technology have increased the availability of video data, creating a strong requirement for efficient systems to manage those materials. Making efficient use of video information requires that data to be accessed in a user-friendly way. Ideally, one would like to understand a video content, without having to watch it entirely. This has been the goal of a quickly evolving research area known as video summarization. In this paper, we present a novel approach for video summarization that works in the compressed domain and allows the progressive generation of a video summary. The proposed method relies on exploiting visual features extracted from the video stream and on using a simple and fast algorithm to summarize the video content. Experiments on a TRECVID 2007 dataset show that our approach presents high quality relative to the state-of-the-art solutions and in a computational time that makes it suitable for online usage. [Copyright &y& Elsevier]

Convolution neural networks based methods can derive deep features from training images. However, one challenge is that the dimension of the extracted image features increases dramatically with more network layers. To solve this problem, this paper focuses on the study of dimension reduction. After using deep learning to extract image features, the PCA algorithm is used to achieve dimension reduction. Specifically, we first leverage deep convolutional neural network to extract image features. Then, we introduce and leverage PCA algorithm to achieve dimension reduction. Aiming at the problem that it is difficult to process high-dimensional sparse big data based on PCA algorithm. This paper optimizes the PCA algorithm. After image preprocessing, the feasibility of PCA algorithm for dimension reduction of image feature extraction by deep learning is verified by simulation experiments. The efficiency of the proposed algorithm is proved by comparing the performance of PCA algorithm before and after optimization. [ABSTRACT FROM AUTHOR]

Abstract: This paper introduces an automatic feature extraction algorithm for bearing fault diagnosis using correlation filtering-based matching pursuit. This algorithm is described and investigated in theory and practice on both simulated and real bearing vibration signals. First, the vibration model for rolling bearing with fault is derived. Then, the numerical simulation signal being taken as an example, the principle of matching pursuit is mathematically explained and its drawbacks are analyzed. Afterward, to enhance the similarity of model related to the bearing faulty impulses, the model shape parameters are optimized using spectrum kurtosis and smoothing index. After that, the model with optimum shape and period parameters is taken as a template to approximate the impulses in faulty bearing signal. Finally, based on maximizing correlation principle, the optimized cycle parameter being as impuls e repetition period is matched up. The proposed method has been successfully applied in actual vibration signals of rolling element bearing with different faults. [Copyright &y& Elsevier]

Abstract: Gearbox fault diagnosis is very important for preventing catastrophic accidents. Vibration signals of gearboxes measured by sensors are useful and dependable as they carry key information related to the mechanical faults in gearboxes. Effective signal processing techniques are in necessary demands to extract the fault features contained in the collected gearbox vibration signals. Overcomplete rational dilation discrete wavelet transform (ORDWT) enjoys attractive properties such as better shift-invariance, adjustable time–frequency distributions and flexible wavelet atoms of tunable oscillation in comparison with classical dyadic wavelet transform (DWT). Due to these advantages, ORDWT is presented as a versatile tool that can be adapted to analysis of gearbox fault features of different types, especially in analyzing the non-stationary and transient characteristics of the signals. Aiming to extract the various types of fault features confronted in gearbox fault diagnosis, a fault feature extraction technique based on ORDWT is proposed in this paper. In the routine of the proposed technique, ORDWT is used as the pre-processing decomposition tool, and a corresponding post-processing method is combined with ORDWT to extract the fault feature of a specific type. For extracting periodical impulses in the signal, an impulse matching algorithm is presented. In this algorithm, ORDWT bases of varied time–frequency distributions and varied oscillatory natures are adopted, moreover an improved signal impulsiveness measure derived from kurtosis is developed for choosing optimal ORDWT bases that perfectly match the hidden periodical impulses. For demodulation purpose, an improved instantaneous time–frequency spectrum (ITFS), based on the combination of ORDWT and Hilbert transform, is presented. For signal denoising applications, ORDWT is enhanced by neighboring coefficient shrinkage strategy as well as subband selection step to reveal the buried transient vibration contents. The proposed fault feature extraction technique is applied in a range of engineering applications, and the processing results demonstrate that the ORDWT-based feature extraction technique successfully identifies the incipient fault features in the cases where DWT and empirical mode decomposition method are less effective. [Copyright &y& Elsevier]

Abstract: The nonlocal means (NLM) filter has distinct advantages over traditional image denoising techniques. However, in spite of its simplicity, the pixel value-based self-similarity measure used by the NLM filter is intrinsically less robust when applied to images with non-stationary contents. In this paper, we use Gabor-based texture features to measure the self-similarity, and thus propose the Gabor feature based NLM (GFNLM) filter for textured image denoising. This filter recovers noise-corrupted images by replacing each pixel value with the weighted sum of pixel values in its search window, where each weight is defined based on the Gabor-based texture similarity measure. The GFNLM filter has been compared to the classical NLM filter and four other state-of-the-art image denoising algorithms in textured images degraded by additive Gaussian noise. Our results show that the proposed GFNLM filter can denoise textured images more effectively and robustly while preserving the texture information. [Copyright &y& Elsevier]

Abstract: The assessment and diagnosis of bearing health using vibration data has been a research topic of interest for many years and includes developments in an assortment of signal processing methods and classification algorithms. This paper investigates detecting bearing degradation at different levels of damage, in that estimating the bearing health at the various stages of degradation is important for predicting failure as well as making maintenance decisions. The proposed technique does not require a measure of the rotational shaft speed or bearing cage speed, which makes it very suitable in certain applications in which it is very difficult or not cost effective to measure the rotational speed. To effectively estimate the bearing health state, a novel tachometer-less synchronously averaged envelope (TLSAE) signal processing and feature extraction technique for rolling element bearing is proposed. The Tachometer-Less Synchronous Averaged Envelope (TLSAE) method consists of first using a narrow band pass filter around a calculated bearing fault frequency of interest and using the derivative of the phase of the Hilbert Transform of this narrow band signal to generate a synthesized tachometer signal that is representative of the impact due to a bearing defect. This synthesized tachometer signal is combined with the high frequency envelope method to perform synchronous averaging on the envelope signal, resulting in a defect synchronous envelope spectrum in which the frequency content is in terms of the fault frequency orders. The proposed method is further compared and evaluated with other existing methods, in particular to the traditional Fourier Transform technique, the bearing envelope analysis technique, and the empirical mode decomposition signal processing methods on the basis of whether each method provides an enhanced level of indication that can determine the health of rolling element bearings. Data from a bearing test-rig is used to facilitate the comparison and evaluation of the signal processing methods. Vibration data was collected from the test-rig for bearings with different levels of degradation. The calculated vibration features from the tachometer-less synchronously averaged envelope (TLSAE) technique are compared to the other feature extraction techniques; with the synchronous average method providing a set of bearing vibration features that can distinguish all three levels of damage on the outer race of the rolling element bearing. Future work looks to further investigate this proposed technique for data collected during a run to failure test in order to consider its merits for early detection of incipient bearing damage and whether it provides a consistent monotonic trend from spall initiation to bearing failure. [Copyright &y& Elsevier]

Abstract: State-of-the-art object retrieval systems are mostly based on the bag-of-visual-words representation which encodes local appearance information of an image in a feature vector. An image object search is performed by comparing query object’s feature vector with those for database images. However, a database image vector generally carries mixed information of the entire image which may contain multiple objects and background. Search quality is degraded by such noisy (or diluted) feature vectors. To tackle this problem, we propose a novel representation, pseudo-objects – a subset of proximate feature points with its own feature vector to represent a local area, to approximate candidate objects in database images. In this paper, we investigate effective methods (e.g., grid, G-means, and GMM–BIC) to estimate pseudo-objects. Additionally, we also confirm that the pseudo-objects can significantly benefit inverted-file indexing both in accuracy and efficiency. Experimenting over two consumer photo benchmarks, we demonstrate that the proposed method significantly outperforms other state-of-the-art object retrieval and indexing algorithms. [Copyright &y& Elsevier]

Abstract: In order to enhance the desired features related to some special type of machine fault, a technique based on the dual-tree complex wavelet transform (DTCWT) is proposed in this paper. It is demonstrated that DTCWT enjoys better shift invariance and reduced spectral aliasing than second-generation wavelet transform (SGWT) and empirical mode decomposition by means of numerical simulations. These advantages of the DTCWT arise from the relationship between the two dual-tree wavelet basis functions, instead of the matching of the used single wavelet basis function to the signal being analyzed. Since noise inevitably exists in the measured signals, an enhanced vibration signals denoising algorithm incorporating DTCWT with NeighCoeff shrinkage is also developed. Denoising results of vibration signals resulting from a crack gear indicate the proposed denoising method can effectively remove noise and retain the valuable information as much as possible compared to those DWT- and SGWT-based NeighCoeff shrinkage denoising methods. As is well known, excavation of comprehensive signatures embedded in the vibration signals is of practical importance to clearly clarify the roots of the fault, especially the combined faults. In the case of multiple features detection, diagnosis results of rolling element bearings with combined faults and an actual industrial equipment confirm that the proposed DTCWT-based method is a powerful and versatile tool and consistently outperforms SGWT and fast kurtogram, which are widely used recently. Moreover, it must be noted, the proposed method is completely suitable for on-line surveillance and diagnosis due to its good robustness and efficient algorithm. [Copyright &y& Elsevier]

Enhancers are regulatory elements involved in gene expression.It is a part of DNA, which can enhance the transcription rate of gene. However, the identification of enhancer by biological experimental methods is time-consuming and expensive. Therefore, there is an urgent need for more efficient methods to identify them.In this study, we propose a new feature extraction method RKPK, which combines three feature methods and uses the recursive feature elimination algorithm for feature selection, and apply deep neural network as classifier to construct the iEnhancer-RD calculation method for enhancer identification. It is a two-layer classification architecture in which the first layer(layer I) identifies enhancers from a set of DNA sequences, and the second layer(layer II) divides the identified enhancers into two subgroups, namely strong and weak enhancers. Independent dataset test indicates that the proposed method is significantly better than most existing methods, and attains the accuracy of 78.8% and 70.5% in the two layers, respectively. Our iEnhancer-RD architecture is implemented in Python and is available at https://github.com/YangHuan639/iEnhancer-RD. [Display omitted] • In this paper, we propose iEnhancer-RD, a method to identify enhancers and their strength. • We propose new feature methods KPCV and RKPK, and compare and analyze these two representations. • Deep neural network (DNN) is used as our classififier. • Optimize several feature methods and the parameters of the constructed deep neural network. • Compared with other work, this method has signifificant improvement in most performance indicators. [ABSTRACT FROM AUTHOR]

• A sign language recognition framework based on global-local attention, including: • A Multiple Group Random Segment Sampling algorithm to extract the key frame clips; • A global Attention-Model based ResC3D network with an improved timing conversion layer; • A local SLR algorithm based on Mask RCNN hand detection network. Video-level sign language recognition is still a challenging task due to the influence of sign language-independent factors and timing requirements. This paper constructs a sign language recognition framework based on global-local feature description, and proposes a three-dimensional residual global network model with attention layer and a local network model based on target detection. The global feature description is based on the whole video behavior for time series modeling. The improved timing conversion layer is used to explore the timing information of different periods and learn the video representations of different timings. In the local module the hand is located through the target detection network to highlight its key role in the whole sign language behavior, which strengthens the category differences, and compensates the global network. Experiments on two well-known Chinese sign language datasets (SLR_Dataset and DEVSIGN_D) show that the proposed method can obtain higher recognition accuracy (respectively 89.2%, 91%) and better generalization performance. [ABSTRACT FROM AUTHOR]

Tuberculosis and other mycobacteriosis are serious illnesses which control is based on early diagnosis. A technique commonly used consists of analyzing sputum images for detecting bacilli. However, the analysis of sputum is time consuming and requires highly trained personnel to avoid high errors. Image-processing techniques provide a good tool for improving the manual screening of samples. In this paper, a new autofocus algorithm and a new bacilli detection technique is presented with the aim to attain a high specificity rate and reduce the time consumed to analyze such sputum samples. This technique is based on the combined use of some invariant shape features together with a simple thresholding operation on the chromatic channels. Some feature descriptors have been extracted from bacilli shape using an edited dataset of samples. A -means clustering technique was applied for classification purposes and the sensitivity vs specificity results were evaluated using a standard ROC analysis procedure. [Copyright &y& Elsevier]

• We develop a detection algorithm and analyze results for different occluded sizes. • We selectively drop objects' features to enrich the occluded scenes. • We learn the implicit mapping to recover occlude noise to real feature. • We verify the effect of GC-FRCN and apply it to the in-filed Rice Panicles Counting. Detecting the object with external occlusion has always been a hot topic in computer version, while its accuracy is always limited due to the loss of original object information and increase of new occlusion noise. In this paper, we propose a occluded object detection algorithm named GC-FRCN (Generative feature completing Faster RCNN), which consists of the OSGM (Occlusion Sample Generation Module) and OSIM (Occlusion Sample Inpainting Module). Specifically, the OSGM mines and discards the feature points with high category response on the feature map to enhance the richness of occlusion scenes in the training data set. OSIM learns an implicit mapping relationship from occluded feature map to real feature map adversarially, which aims at improving feature quality by repair the noisy object feature. Extensive experiments and ablation studies have been conducted on four different datasets. All the experiments demonstrate the GC-FRCN can effectively detect objects with local external occlusion and has good robustness for occlusion at different scales. [ABSTRACT FROM AUTHOR]

With the rapid development of mobile Internet and digital technology, people are more and more keen to share pictures on social networks, and online pictures have exploded. How to retrieve similar images from large-scale images has always been a hot issue in the field of image retrieval, and the selection of image features largely affects the performance of image retrieval. The Convolutional Neural Networks (CNN), which contains more hidden layers, has more complex network structure and stronger ability of feature learning and expression compared with traditional feature extraction methods. By analyzing the disadvantage that global CNN features cannot effectively describe local details when they act on image retrieval tasks, a strategy of aggregating low-level CNN feature maps to generate local features is proposed. The high-level features of CNN model pay more attention to semantic information, but the low-level features pay more attention to local details. Using the increasingly abstract characteristics of CNN model from low to high. This paper presents a probabilistic semantic retrieval algorithm, proposes a probabilistic semantic hash retrieval method based on CNN, and designs a new end-to-end supervised learning framework, which can simultaneously learn semantic features and hash features to achieve fast image retrieval. Using convolution network, the error rate is reduced to 14.41% in this test set. In three open image libraries, namely Oxford, Holidays and ImageNet, the performance of traditional SIFT-based retrieval algorithms and other CNN-based image retrieval algorithms in tasks are compared and analyzed. The experimental results show that the proposed algorithm is superior to other contrast algorithms in terms of comprehensive retrieval effect and retrieval time. [ABSTRACT FROM AUTHOR]