Completed Local Binary Pattern Research Articles

Noise-tolerant texture feature extraction through directional thresholded local binary pattern

Local binary pattern (LBP) is a multi-applicable texture descriptor applied in machine vision. Despite its outstanding abilities in revealing textural properties of image, it is sensitive to noise, due to its thresholding mechanism. To make LBP robust against noise, a directional thresholded LBP (DTLBP) is developed in this article which applies the directional neighboring pixels average values for thresholding. Applying this type of thresholding in addition to reducing noise, due to using the information of neighboring pixels with bigger radii, increases efficiency in extracting features. The DTLBP is able to be combined with other descriptors like completed LBP (CLBP) and local ternary pattern (LTP) which improves their functionality against noise. To evaluate the functionality of DTLBP, four known datasets including Outex (TC10), CUReT, UIUC and UMD are tested. Numerous and extensive experiments on these datasets with different kinds of noises indicate this newly developed descriptor’s efficiency, with or without incremental white Gaussian and Gaussian blur noises. The proposed descriptor is compared with its available state of the art counterparts. The results show that the combination of DTLBP with CLBP descriptors provide the best classification accuracy in the experiments, which confirms the efficiency and robustness of the proposed descriptor when extracting features from noisy and raw images.

Smoke Vehicle Detection Based on Spatiotemporal Bag-Of-Features and Professional Convolutional Neural Network

Existing smoke vehicle detection methods are vulnerable to false alarms. To solve this issue, this paper presents two automatic smoke vehicle detection methods based on spatiotemporal bag-of-features (S-BoF) and professional convolutional neural network (P-CNN). In the first method, we propose the S-BoF model to characterize the key regions detected by the visual background extractor (ViBe) algorithm. The S-BoF model contains three groups of features, including color moments on three orthogonal planes (CM-TOP), completed robust local binary pattern on three orthogonal planes (CRLBP-TOP), and histogram of oriented gradient on three orthogonal planes (HOG-TOP). The extracted features are fed to the support vector machine (SVM) and classify the key regions to smoke regions or non-smoke regions to further detect smoke vehicles. In the second method, we propose the P-CNN model to extract more robust and complementary spatiotemporal features by designing three professional models to analyze different kinds of features in the key region sequence on three orthogonal planes. The three professional models, including color CNN (CCNN), texture CNN (TCNN), and gradient CNN (GCNN), are based on three independent CNN128 models with different inputs. The experimental results show that the proposed methods achieve higher detection rates and lower false alarm rates than existing smoke detection methods.

Human action recognition from RGB-D data using complete local binary pattern

Human action recognition is an active research domain in Computer Vision and Pattern Recognition due to the challenges such as inter and intra class variation, background clutter, partial occlusion and changes in scale, viewpoint, lighting, appearance etc. Human action recognition aims at determining the activities of a person or a group of persons, as well as on knowledge about the context within which the observed activities take place. As RGB cameras responds easily to illumination changes and surrounding clutters, the worthwhile RGB Depth (RGB-D) camera sensors (e.g. Kinect) is used to improve the action recognition. This paper aims at classifying Human Actions by integrating salient motion features from both RGB and Depth Camera. The methodology includes Salient Information Map generation from both RGB and depth action sequences signposting the motion significant region of the corresponding action sequence. From the Salient Information Map, Sign, Magnitude and Center descriptors representing Complete Local Binary Pattern was extracted. Then the fusion of features from depth and RGB is carried out by Canonical Correlation Analysis accompanied by dimensionality reduction. Multiclass SVM classifier is used for classifying the features in to various action categories. The experimental analysis of the proposed algorithm was carried with MSR Daily Activity 3D Dataset and UTD-MHAD Action Dataset and the recognition rate of 98.75% and 84.12% was obtained.

Generalized Completed Local Binary Patterns for Time-Efficient Steel Surface Defect Classification

Efficient defect classification is one of the most important preconditions to achieve online quality inspection for hot-rolled strip steels. It is extremely challenging owing to various defect appearances, large intraclass variation, ambiguous interclass distance, and unstable gray values. In this paper, a generalized completed local binary patterns (GCLBP) framework is proposed. Two variants of improved completed local binary patterns (ICLBP) and improved completed noise-invariant local-structure patterns (ICNLP) under the GCLBP framework are developed for steel surface defect classification. Different from conventional local binary patterns variants, descriptive information hidden in nonuniform patterns is innovatively excavated for the better defect representation. This paper focuses on the following aspects. First, a lightweight searching algorithm is established for exploiting the dominant nonuniform patterns (DNUPs). Second, a hybrid pattern code mapping mechanism is proposed to encode all the uniform patterns and DNUPs. Third, feature extraction is carried out under the GCLBP framework. Finally, histogram matching is efficiently accomplished by simple nearest-neighbor classifier. The classification accuracy and time efficiency are verified on a widely recognized texture database (Outex) and a real-world steel surface defect database [Northeastern University (NEU)]. The experimental results promise that the proposed method can be widely applied in online automatic optical inspection instruments for hot-rolled strip steel.

Ship Classification Based on Multifeature Ensemble with Convolutional Neural Network

As an important part of maritime traffic, ships play an important role in military and civilian applications. However, ships’ appearances are susceptible to some factors such as lighting, occlusion, and sea state, making ship classification more challenging. This is of great importance when exploring global and detailed information for ship classification in optical remote sensing images. In this paper, a novel method to obtain discriminative feature representation of a ship image is proposed. The proposed classification framework consists of a multifeature ensemble based on convolutional neural network (ME-CNN). Specifically, two-dimensional discrete fractional Fourier transform (2D-DFrFT) is employed to extract multi-order amplitude and phase information, which contains such important information as profiles, edges, and corners; completed local binary pattern (CLBP) is used to obtain local information about ship images; Gabor filter is used to gain the global information about ship images. Then, deep convolutional neural network (CNN) is applied to extract more abstract features based on the above information. CNN, extracting high-level features automatically, has performed well for object classification tasks. After high-feature learning, as the one of fusion strategies, decision-level fusion is investigated for the final classification result. The average accuracy of the proposed approach is 98.75% on the BCCT200-resize data, 92.50% on the original BCCT200 data, and 87.33% on the challenging VAIS data, which validates the effectiveness of the proposed method when compared to the existing state-of-art algorithms.

Texture Feature Extraction from Thyroid MR Imaging Using High-Order Derived Mean CLBP

In the field of medical imaging, the traditional local binary pattern (LBP) and its improved algorithms are often sensitive to noise. Traditional LBPs are solely based on the signal information from local differences, and the binary quantization method oversimplifies the local texture features while disregarding the imaging information from the concaveconvex regions between the high-order pixels and the neighboring sampling points. Therefore, we propose an improved Derived Mean Complete Local Binary Pattern (DM CLBP) algorithm based on high-order derivatives. In the DM CLBP method, the grey value of a single pixel is replaced by the mean grey value of the rectangular area block, and the difference between pixel values in the area is obtained using the second-order differentiation method. Based on the calculation concept of the complete local binary pattern (CLBP) algorithm, the cascade signs and magnitudes of the two components are encoded and recombined in DM CLBP using a uniform pattern. The results from the experiments showed that the proposed DM CLBP descriptors achieved a classification accuracy of 94.4%. Compared with LBP and other improved algorithms, the DM CLBP algorithm presented in this study can effectively differentiate between lesion areas and normal areas in thyroid MR (magnetic resonance) images and shows the improved accuracy of area classification.

Robustness-Driven Hybrid Descriptor for Noise-Deterrent Texture Classification

A robustness-driven hybrid descriptor for noise-deterrent texture classification is presented in this paper. This work offers the ability to categorize a variety of textures under challenging image acquisition conditions. An image is initially resolved into its low-frequency components by applying wavelet decomposition. The resulting low-frequency components are further processed for feature extraction using completed joint-scale local binary patterns (CJLBP). Moreover, a second feature set is obtained by computing the low order derivatives of the original sample. The evaluated feature sets are integrated to obtain a final feature vector representation. The texture-discriminating performance of the hybrid descriptor is analysed using renowned datasets: Outex original, Outex extended and KTH-TIPS. Experimental results demonstrate a stable and robust performance of the descriptor under a variety of noisy conditions. An accuracy of 95.86%, 32.52% and 88.74% at noise variance of 0.025 is achieved for the given datasets, respectively. A comparison between performance parameters of the proposed work with its parent descriptors and recently published work is also demonstrated.

A Noninvasive System for the Automatic Detection of Gliomas Based on Hybrid Features and PSO-KSVM

Due to their location, malignant brain tumors are one of humanity's greatest killers, among these tumors, gliomas are the most common. The early detection of gliomas can contribute to the design of proper treatment schemes and, thus, improve the survival rate of patients. However, it is a challenging task to detect the gliomas within the complex structure of the brain. The conventional artificial diagnosis is time-consuming and relies on the clinical experience of radiologists. To detect gliomas more efficiently, this paper proposes a noninvasive automatic diagnosis system for gliomas based on the machine learning methods. First, image standardization, including size normalization and background removal, is applied to produce standard images; then, the modified dynamic histogram equalization is implemented to enhance the low-contrast standard brain images, and skull removal based on outlier detection is presented. Furthermore, hybrid features, including gray-level co-occurrence matrix, pyramid histogram of the oriented gradient, modified completed local binary pattern, and intensity-based features are extracted together from the enhanced images, and their dimensions are reduced by principal component analysis. Kernel support vector machine (KSVM) combined with the particle swarm optimization is eventually adopted to train classifiers; in this paper, brain magnetic resonance imaging images are labeled with normal, glioma, and other. The experimental results show that the accuracy, sensitivity, and specificity of the proposed method can reach 98.36%, 99.17%, and 97.83%, respectively, which indicates that the proposed method performs better than many current systems.

Spectrotemporal Analysis Using Local Binary Pattern Variants for Acoustic Scene Classification

In this paper, we present an approach for acoustic scene classification, which aggregates spectral and temporal features. We do this by proposing the first use of the variable-Q transform (VQT) to generate the time–frequency representation for acoustic scene classification. The VQT provides finer control over the resolution compared to the constant-Q transform (CQT) or short time fourier transform and can be tuned to better capture acoustic scene information. We then adopt a variant of the local binary pattern (LBP), the adjacent evaluation completed LBP (AECLBP), which is better suited to extracting features from acoustic time–frequency images. Our results yield a 5.2% improvement on the DCASE 2016 dataset compared to the application of standard CQT with LBP. Fusing our proposed AECLBP with HOG features, we achieve a classification accuracy of 85.5%, which outperforms one of the top performing systems.

Circular regional mean completed local binary pattern for texture classification

The local binary pattern (LBP) is a simple yet efficient texture operator, and the completed local binary pattern (CLBP) is a completed modeling for LBP that has been adopted in many texture classification methods. However, existing CLBP operators are sensitive to noise and they cannot extract the regional structure information efficiently. To overcome these disadvantages, we propose a circular regional mean completed local binary pattern (CRMCLBP) by introducing a circular regional mean operator to modify the traditional CLBP. We also present two encoding schemes for CRMCLBP. The proposed CRMCLBP not only achieves rotation invariance and completed representation capability but also has high robustness to image noise. In order to evaluate the performance, we compare the CRMCLBP with recent state-of-the-art methods by extensive experiments on two popular texture databases including Outex database and Columbia-Utrecht reflection and texture database. Excellent experimental results demonstrate that the proposed CRMCLBP is comparable with recent state-of-the-art texture descriptors and superior to other approaches for robustness.

Multi-scale completed local binary patterns for ulcer detection in wireless capsule endoscopy images

This paper deals with ulcer abnormalities detection of small bowel, from wireless capsule endoscopy images (WCE). We propose a multi-scale approach based on completed local binary patterns, and laplacian pyramid (MS-CLBP). The proposed approach captures additional information about the magnitude as a robust descriptor against illuminations changes in WCE images. In addition, ulcer detection, was performed using the Green component and Cr components of RGB and YCbCr color spaces, respectively. Using the support vector machine (SVM) classifier, we conduct several experiments on two datasets. The results obtained validate the efficiency of the proposed system with an average accuracy of 95.11 and 93.88% for both datasets. Finally, a comparison with the state of the art methods shows that the proposed method is superior to the other approaches.

Improving the classification of rotated images by adding the signal and magnitude information to a local texture descriptor

Texture image classification, especially for images with substantial changes in rotation, illumination, scale and point of view, is a fundamental and challenging problem in the field of computer vision. Natural images acquired under uncontrolled environments have textures with unknown orientation angles. Therefore, it is difficult to identify the same known texture at different acquisition angles. A common solution is image rotation by means of an interpolation technique. However, texture descriptors are not effective enough when two similar textures acquired at different angles are compared. In this work, we propose a simple and efficient image descriptor, called Completed Local Mapped Pattern (CLMP), and apply it to the texture classification of rotated images. This new approach is an improvement over the previously published Local Mapped Pattern (LMP) descriptor because the new approach includes the signal and the magnitude information. This innovation is more discriminating and robust for the description of rotated textures at arbitrary angles. We used two image datasets to validate the proposed descriptor: the Kylberg Sintorn Rotation Dataset and the Brodatz Texture Rotation Dataset. We also introduced a new texture dataset, which contains rotated texture images from Brodatz’s Album. The database contains images of natural textures that have been rotated by both hardware and interpolation methods. We presented an evaluation of the influence of the interpolation method on image rotation, compared with different descriptors in the literature. The experimental results show that our proposed CLMP descriptor outperforms the widely used Completed Local Binary Pattern (CLBP) descriptor and the recently published Sampled Local Mapped Pattern Magnitude (SLMP_M) descriptor. Our results also demonstrate that the choice of interpolation method influences the descriptive capability of each descriptor.

A collaborative representation face classification on separable adaptive directional wavelet transform based completed local binary pattern features

Face recognition has emerged as the most active area of research in computer vision. A variety of face recognition methods were devised, though several challenges are imposed due to face variations such as facial expression, pose variation and illumination variation which generate great concern in developing efficient face recognition methods. It is desirable to extract robust local descriptive features to effectively represent such face variations. The essential attribute of the proposed method is to extract directional descriptive local features based on the face image characteristics. In order to extract the multi-resolution directional features as per the face variations, a 2-D interpolation-based separable adaptive directional wavelet transform (SADIWT) is proposed. For the implementation of 2-D SADIWT, a set of seven directions with an improved quadtree partitioning scheme is proposed. Completed local binary patterns (CLBP) superior to local binary patterns (LBP) in extracting local texture features are applied on top level’s 2-D SADIWT sub-bands to obtain local descriptive features. Collaborative representation classification (CRC) takes benefit of these descriptive features and leads to a very competitive classification performance. Extensive experimental results on benchmark face databases such as ORL, FERET, CMU-PIE, and LFW demonstrate high classification accuracy of the proposed method. A comparison with numerous methods which include various holistic, LBP-based descriptors and representation methods demonstrate the efficacy of the proposed method. Experiments are also conducted to exhibit the robustness and discrimination capability of the proposed method for handling single image per person (SIPP) and random block occlusion problem.

Assessing Texture Features to Classify Coastal Wetland Vegetation from High Spatial Resolution Imagery Using Completed Local Binary Patterns (CLBP)

Coastal wetland vegetation is a vital component that plays an important role in environmental protection and the maintenance of the ecological balance. As such, the efficient classification of coastal wetland vegetation types is key to the preservation of wetlands. Based on its detailed spatial information, high spatial resolution imagery constitutes an important tool for extracting suitable texture features for improving the accuracy of classification. In this paper, a texture feature, Completed Local Binary Patterns (CLBP), which is highly suitable for face recognition, is presented and applied to vegetation classification using high spatial resolution Pléiades satellite imagery in the central zone of Yancheng National Natural Reservation (YNNR) in Jiangsu, China. To demonstrate the potential of CLBP texture features, Grey Level Co-occurrence Matrix (GLCM) texture features were used to compare the classification. Using spectral data alone and spectral data combined with texture features, the image was classified using a Support Vector Machine (SVM) based on vegetation types. The results show that CLBP and GLCM texture features yielded an accuracy 6.50% higher than that gained when using only spectral information for vegetation classification. However, CLBP showed greater improvement in terms of classification accuracy than GLCM for Spartina alterniflora. Furthermore, for the CLBP features, CLBP_magnitude (CLBP_m) was more effective than CLBP_sign (CLBP_s), CLBP_center (CLBP_c), and CLBP_s/m or CLBP_s/m/c. These findings suggest that the CLBP approach offers potential for vegetation classification in high spatial resolution images.

Adaptive multiclass correlation filters and its applications in the time series recognition

The adaptive multiclass correlation filters (AMCF) method is proposed to exploit different kinds of features and information in a unified framework for recognition. Theoretical investigation into AMCF shows that it obtains a closed-form subsolution to constrain the optimization objective, simplifying the entire inference mechanism in the multiclass classification. The time series recognition problems, such as human action recognition and radar behavior recognition, are important yet challenging tasks. However, it is still time-consuming to acquire enough labeled training samples. AMCF is capable to exploit different kinds of features to solve the time series recognition problem. With this new correlation filters-based method, we extend the original signals and handle the insufficient training set effectively. Experiments are done on the depth image based action recognition and radar behavior recognition with a small number of training examples, including MSRAction3D, MSRGesture3D, UTD-MHAD, and radar behavior datasets. Particularly, we demonstrate that the proposed action recognition system is based on the completed local binary patterns and AMCF, and successfully achieves superior performances over the state-of-the-arts.

Ground-based cloud classification by learning stable local binary patterns

Feature selection and extraction is the first step in implementing pattern classification. The same is true for ground-based cloud classification. Histogram features based on local binary patterns (LBPs) are widely used to classify texture images. However, the conventional uniform LBP approach cannot capture all the dominant patterns in cloud texture images, thereby resulting in low classification performance. In this study, a robust feature extraction method by learning stable LBPs is proposed based on the averaged ranks of the occurrence frequencies of all rotation invariant patterns defined in the LBPs of cloud images. The proposed method is validated with a ground-based cloud classification database comprising five cloud types. Experimental results demonstrate that the proposed method achieves significantly higher classification accuracy than the uniform LBP, local texture patterns (LTP), dominant LBP (DLBP), completed LBP (CLTP) and salient LBP (SaLBP) methods in this cloud image database and under different noise conditions. And the performance of the proposed method is comparable with that of the popular deep convolutional neural network (DCNN) method, but with less computation complexity. Furthermore, the proposed method also achieves superior performance on an independent test data set.

A Multiresolution Gray-Scale and Rotation Invariant Descriptor for Texture Classification

Texture classification algorithms using local binary pattern (LBP) and its variants usually can achieve attractive results. However, the selected rotation invariant structural patterns in numerous LBP variants are not absolutely continuous invariant to any rotation angle. To improve the classification effectiveness on this occasion, in this paper, we introduce a robust descriptor based on the principal curvatures (PCs) and rotation invariant version of CLBP_Sign operator in completed LBP (CLBP), namely PC-LBP. Different from the original LBP and many LBP variants, PCs are employed in this paper to represent each local structure information due to their continuous rotation invariance. Simultaneously, both micro-and macro-structure texture information can also be captured through PCs, which comprise maximum and minimum curvatures. Inspired by the similar coding strategy of the CLBP_Sign operator, a new operator CLBP_PC is developed. By exploiting complementary information resulting from the two operators combination, the final PC-LBP descriptor has the properties of conspicuous rotation invariance, strong discriminativeness, gray scale invariance, needless of pretraining, and high computational efficiency. In addition, to improve the robustness of texture classification with multiresolution, a multiscale sampling approach is designed by adjusting three parameters accordingly. Experimental results demonstrate that the proposed multiresolution PC-LBP approach achieves comparable performance or outperforms a large number of state-of-the-art methods. Impressively, the classification accuracy of the proposed method performed on Outex_TC_00010 test suite is 100%.

Jumping and Refined Local Pattern for Texture Classification

The local binary pattern (LBP) model is a simple and effective method of texture classification, but it is sensitive to rotational and noisy images. Although many variants of LBP are proposed by scholars, there are still several urgent problems, such as poor noise and rotation immunity. In this paper, we propose a robust texture descriptor, jumping and refined local pattern (JRLP) for texture classification. In particular, we first extract jumping local difference count pattern (JLDCP) consisting of second-order difference count pattern and diagonal difference count pattern to represent the jumping information in a local domain. To capture the detail information left by JLDCP, we extract a refined completed LBP (RCLBP). By concatenating the JLDCP and RCLBP, we build a JRLP-based robust texture descriptor for classification. Experimental results on four representative texture databases (Brodatz, CUReT, UIUC, and VisTex) reveal that our proposed texture classification method is effective and robust for noise, rotation, scale, and illumination variants and outperforms six representative methods.

Cross-Domain Ground-Based Cloud Classification Based on Transfer of Local Features and Discriminative Metric Learning

Cross-domain ground-based cloud classification is a challenging issue as the appearance of cloud images from different cloud databases possesses extreme variations. Two fundamental problems which are essential for cross-domain ground-based cloud classification are feature representation and similarity measurement. In this paper, we propose an effective feature representation called transfer of local features (TLF), and measurement method called discriminative metric learning (DML). The TLF is a generalized representation framework that can integrate various kinds of local features, e.g., local binary patterns (LBP), local ternary patterns (LTP) and completed LBP (CLBP). In order to handle domain shift, such as variations of illumination, image resolution, capturing location, occlusion and so on, the TLF mines the maximum response in regions to make a stable representation for domain variations. We also propose to learn a discriminant metric, simultaneously. We make use of sample pairs and the relationship among cloud classes to learn the distance metric. Furthermore, in order to improve the practicability of the proposed method, we replace the original cloud images with the convolutional activation maps which are then applied to TLF and DML. The proposed method has been validated on three cloud databases which are collected in China alone, provided by Chinese Academy of Meteorological Sciences (CAMS), Meteorological Observation Centre (MOC), and Institute of Atmospheric Physics (IAP). The classification accuracies outperform the state-of-the-art methods.

Grading of ripening stages of red banana using dielectric properties changes and image processing approach

In this research work, the dielectric properties of red banana fruit are studied at different ripening temperatures for developing a rapid and non-destructive assessment method to measure the ripening stages of red banana. A 5 volt sine wave AC power supply and a rectangular parallel plate capacitor circuit are used to measure the difference in dielectric properties caused by the introduction of a red banana in between the plates. The values of properties like capacitance and relative permittivity are increased continuously whereas impedance and admittance are decreased gradually with increase in ripening stages of red banana. In image processing approach, Noise Reductant Local Binary Pattern (NRLBP), Local Binary Pattern (LBP), Completed Local Binary Pattern (CLBP) based techniques are used for red banana’s ripening grade determination. The processing stages involved are enhancement, Binary Pattern generation and classification. The variant Binary patterns are tested on noisy as well as noiseless condition and the results are compared. A novel enhancement technique for banana ripening grade determination is proposed based on segmentation using Tsallis entropy. Also novel idea on the automation of q parameter involved in Tsallis Entropy is implemented. The threshold parameter of the Noise Reductant Local Binary Pattern (NRLBP) varied and its effect on classification rate is studied. A new modification is proposed and implemented on NRLBP to accommodate uniform background and areas with the image. Classification is done using Chi-Square distance/nearest neighbor and Fuzzy C means (FCM) clustering. The results are compared and superiority of FCM method for banana ripening grade determination is noted.