Multi-level Local Binary Pattern Analysis for Texture Characterization

Face recognition based on curvelets and local binary pattern features via using local property preservation

With huge and ever-growing products in the factory, image retrieval can help the worker retrieve the same, or similar, existing products rapidly and accurately to guide production. In this paper, an effective method based on Fourier transform and local binary pattern is proposed to improve the retrieval efficiency of wool fabric. After capturing the fabric image, histogram equalization was implemented on the value of the Hue, Saturation, Value (HSV) mode to enhance the contrast. Subsequently, Fourier transform together with local binary pattern operator were performed to obtain the frequency spectrum and the local binary pattern, respectively. Each frequency spectrum was divided into 22 rings with the same width, and the standard deviation of the frequencies in each ring was calculated as a Fourier feature. Distinct output values of each local binary pattern were counted and normalized as local binary pattern features. Finally, Euclidean distance was adopted to measure the similarity based on the Fourier feature and local binary pattern feature. Twenty thousand wool fabric images were captured to demonstrate the efficacy of the proposed method. Experimental results indicate that the framework is effective and superior for image retrieval of wool fabric, providing referential assistance for the worker in the factory and improving retrieval efficiency.

The Local Binary Pattern (LBP) and its variants are capable of extracting image texture and have been successfully applied to classification. However, LBP has not been used to extract and describe the texture of polarized images, and simple LBP cannot characterize the polarized texture information from different polarizations of angles. In order to solve these problems, we propose a new multi-angle orthogonal difference polarization image texture descriptor (MODP_ITD) by analyzing the relationship between the difference of orthogonal difference polarization images from different angles and the pixel intensity distribution in the local neighborhood of images from different angles. The MODP_ITD consists of three patterns: multi-angle polarization orthogonal difference local binary pattern (MODP_LBP), multi-angle polarization orthogonal difference local sampling point principal component sequence pattern (MODP_LPCSP) and multi-angle orthogonal difference polarization local difference binary pattern (MODP_LDBP). The MODP_LBP extracts local corresponding texture characteristics of polarized orthogonal difference images from multiple angles. The MODP_LPCSP sorts the principal component order of each angle orthogonal difference local sampling point. The MODP LDBP extracts the local difference characteristics between different angles by constructing a new polarized image. Then, the frequency histograms of MODP_LBP, MOD_LPCSP ,and MODP_LDBP are cascaded to generate MODP_ITD, so as to distinguish local neighborhoods. By using vertical and parallel polarization and unpolarized light active illumination, combined with the measurements at three different detection zenith angles, we constructed a polarization texture image database. A substantial number of experimental results on the self-built database show that our proposed MODP_ITD can represent the detailed information of polarization images texture. In addition, compared with the existing LBP methods, The MODP_ITD has a competitive advantage in classification accuracy.

This paper proposes a novel face representation approach, local Gabor binary mapping pattern (LGBMP), for multi-view gender classification. In this approach, a face image is first represented as a series of Gabor magnitude pictures (GMP) by applying multi-scale and multi-orientation Gabor filters. Each GMP is then encoded as a LGBP image where a uniform local binary pattern (LBP) operator is used. After that, each LGBP image is divided into non-overlapping rectangular regions, from which spatial histograms are extracted. Although an LGBP feature vector can be obtained by fitting together the regional histograms, it can not be employed in pattern classification due to its high dimension. We propose that each regional LGBP feature be mapped onto a one-dimensional subspace independently before they are concatenated as a whole feature vector. This is attractive since we reduce the feature dimension and also preserve the spatial information of LGBP image. Two ways have been proposed to map the regional LGBP feature in this paper. One is so-called LGBMP-LDA using linear discriminant analysis (LDA) for dimensionality reduction while the other is to project the regional LGBP feature onto the class center connecting line, namely, LGBMP-CCL. As a result, despite several decades of Gabor filters, the final feature dimension is even less than that of the feature extracted by using LBP directly on gray-scale images. The classification tasks in our work are performed by support vector machines (SVM). The experimental results on the CAS-PEAL face database indicate that the proposed approach achieves higher accuracy than the others such as SVMs+Gray-scale pixel, SVMs+Gabor and SVMs+LBP approach, more particularly, it has the lowest dimension of feature vector.

Serving as an effective texture description operator, local binary pattern (LBP) has been applied in the visible face recognition successfully. In order to enhance the recognition performance, the technology of face recognition depending on the near infrared (NIR) image has attracted extensive attention in the recent years. Although the characteristics of LBP have been researched in optical image thoroughly, the development of these do not catch enough attention in the NIR image at all. Therefore, in our paper, we study the characteristics of LBP from the following two aspects in NIR image. On one hand, we come to the probability distribution of various patterns of LBP in the NIR facial image. On the other hand, we discuss the influence to LBP caused by the illumination change in facial image.

Based on pattern uniformity measure and the number of ones in the Local Binary Pattern (LBP) codes, this paper proposes an Improved Local Binary Pattern (ILBP) operator to describe local image texture more effectively. The ILBP operator discovers an important group of basic primitives such as lines, T-junctions, and cross-intersections, which are ignored by uniform LBP operator. Such local primitives are as crucial as those represented by uniform patterns for recognition tasks. The resulting ILBP feature is more discriminative than traditional LBP feature although they are both invariant in terms of monotonic gray-scale variation and rotation transformation.

This paper presents a method that combines discrete S-transform (DST) time-frequency distribution (TFD) and local binary pattern (LBP) based image analysis technique for classifying power quality (PQ) disturbances. The purpose of this combination is to extract discriminative features by utilizing from both capability of generating the compact TFD of a non-stationary signal and the efficient image representation capability of LBP. In the proposed method, DST based TFDs of PQ disturbance signals are considered as 2-D images. LBP histograms are used to extract the features from TF images. Initially, the uniform patterns in TF images are obtained by the LBP operator. Next, the occurrence histograms of these patterns are used to produce representative feature vectors that can capture the unique and salient characteristics of each disturbance. The classification performance of the proposed method is evaluated through total 2400 disturbance signals. The experimental results have shown that the rate of correct classification is about 98 % for the different PQ disturbances.

Local binary pattern (LBP) is a powerful texture descriptor that is gray-scale and rotation invariant. In this paper, an extension of the original LBP is proposed. LBP operator is adopted in multi-layer block domain, instead of pixel domain. Meanwhile, feature dimension is effectively reduced by dual-histogram LBP (DH-LBP). Combining merits of the two, we propose the advanced LBP (ALBP) and use that in solving the practical problem of crowd estimation. Experiment results demonstrate the performance and the potential of our method.

The Local Binary Patterns (LBP) feature extraction method is a theoretically and computationally simple and efficient methodology for texture analysis. The LBP operator is used in many applications such as facial expression recognition and face recognition. The original LBP is based on hard thresholding the neighborhood of each pixel, which makes texture representation sensitive to noise. In addition, LBP cannot distinguish between a strong and a weak pattern. In order to enhance the LBP approach, Fuzzy Local Binary Patterns (FLBP) is proposed. In FLBP, any neighborhood does not represented only by one code, but, it is represented by all existing codes with different degrees. In FLBP, any fuzzy Intersection and Union operators may be used. In this study, the following operators are applied and their results are compared together: Dot-Sum, Min-Max and normalized Min-Max. Based on the extensive experiments, the fuzzy Min-Max operators are more useful and can improve the accuracy in the application of Facial Expression Recognition (FER) about 4% (i.e., form 82.98% to 86.88%).

Effective plant discrimination based on the combination of local binary pattern operators and multiclass support vector machine methods

In recent years, with the development of the image processing technology, the protection to the authenticity and integrity of digital images has always been a topic of great concern. A blind image authentication technology with high tamper detection accuracy under different common attacks is urgently needed. In this paper, an improved fragile watermarking based on local binary pattern (LBP) for blind tamper detection in images is proposed. In this method, the binary watermark is generated by LBP operator, which is often used in texture analysis and pattern recognition. In order to improve the security of the proposed method, Arnold transform and logistic map are used to scramble the watermark. Then the watermark is inserted into the least significant bit (LSB) of original pixels. Since the watermark is constructed from the image itself, no original image is needed in tamper detection. The LBP map of watermarked image is compared with the extracted watermark to determine whether it is tampered or not. Compared with other state-of-the-art algorithms, experimental results show that the proposed scheme achieves good performance in tamper detection and localization under various attacks.

The Local Binary Pattern (LBP) descriptor encodes the complementary information of the spatial patterns and intensity variations in a local image neighborhood. The richness of this multidimensional information offers many possible variations to the encoding process. Taking advantage of this, several variants of the LBP have been proposed. This work attempts to further optimize the discriminative power of the LBP specifically for the medical image classification task. It proposes an LBP variant that takes into account the salient edge features that are found particularly in chest X-ray images. In addition, it introduces a semi-global histogram to replace the commonly used global histogram which normally represents the spatial distribution of the generated codes in the LBP encoding process. The proposed LBP variant has been applied to the task of classifying X-rays of the ImageCLEFmed 2009 dataset into different chest categories. Experimental results show that while reducing the computational load the proposed LBP variant achieved an accuracy of 99.19% as compared to the best reported LBP based results of 98.73%, in classifying chest x-ray images of the ImageCLEFmed 2009 dataset.

Depression is a common mental disease characterized by significant sadness and feeling blue all the time. At present, most classifications and predictions of depression rely on different characteristics. Comparing with the previous work, we use local binary pattern (LBP) and signal singular spectrum analysis (SSA) technology to extract features from the original signal. Firstly, the LBP signal is obtained by encoding the segmented signal. Then, we use SSA to decompose and reconstruct the LBP signal to remove noise and divide the frequency band. Finally, we feed the data of each frequency band to K-nearest neighbor (KNN), decision tree (DT), support vector machine (SVM) and extreme learning machine (ELM) for classification. The experimental results show that LBP and SSA features achieve the best classification effect on SVM, and the accuracy of beta band is the highest with 99.24% accuracy, 99.34% sensitivity and 99.12% specificity respectively.

Application of local binary patterns in digital images to estimate botanical composition in mixed alfalfa–grass fields

Most image classification algorithms consist of feature extraction and image classification. Hence, feature extraction is a critical step for obtaining an accurate classification result. In this study, we perform the classification experiments based on the image features extracted using Local Binary Pattern operator (LBP), Discrete Wavelet Transforms (DWT) and Color Features (CF) for image classification. A comparison is made using the different combination of features; 1) LBP features only, 2) LBP and DWT features, and 3) LBP, DWT and CF features with a slight modification. Our goal is to determine what types of features are useful for improving the classification results. The Linear Support Vector Machine (SVM) algorithm is used to classify each pixel into a class based on the features used to obtain a classified image. Preliminary experimental results show that the hybrid of DWT, LBP, and CF gives the highest accuracy.