Face location with LBP scale transform

We investigated the feasibility of using multiresolution Local Binary Pattern (LBP) texture analysis to reduce falsepositive (FP) detection in a computerized mass detection framework. A new and novel approach for extracting LBP features is devised to differentiate masses and normal breast tissue on mammograms. In particular, to characterize the LBP texture patterns of the boundaries of masses, as well as to preserve the spatial structure pattern of the masses, two individual LBP texture patterns are then extracted from the core region and the ribbon region of pixels of the respective ROI regions, respectively. These two texture patterns are combined to produce the so-called multiresolution LBP feature of a given ROI. The proposed LBP texture analysis of the information in mass core region and its margin has clearly proven to be significant and is not sensitive to the precise location of the boundaries of masses. In this study, 89 mammograms were collected from the public MAIS database (DB). To perform a more realistic assessment of FP reduction process, the LBP texture analysis was applied directly to a total of 1,693 regions of interest (ROIs) automatically segmented by computer algorithm. Support Vector Machine (SVM) was applied for the classification of mass ROIs from ROIs containing normal tissue. Receiver Operating Characteristic (ROC) analysis was conducted to evaluate the classification accuracy and its improvement using multiresolution LBP features. With multiresolution LBP features, the classifier achieved an average area under the ROC curve, , z A of 0.956 during testing. In addition, the proposed LBP features outperform other state-of-the-arts features designed for false positive reduction.

A new approach for inner-knuckle-print (IKP) recognition is proposed. The approach is based on the local binary pattern (LBP) features. In our algorithm, straight line neighbourhood is used to calculate the LBP features, so that more distinctive IKP features can be obtained. Moreover, as the LBP feature for each IKP sample, 59 binary images are extracted, and then matched by using a cross-correlation-based algorithm, which is developed to calculate the similarity between the IKP samples. The experiments on a finger image database which includes 2,000 images from 100 different individuals show the good performance of the proposed approach.KeywordsBiometricsPersonal authenticationLocal binary pattern

In the field of quantitative microscopy, textural information plays a significant role very often in tissue characterization and diagnosis, in addition to morphology and intensity. The objective of this work is to improve the classification accuracy based on textural features for the development of a computer assisted screening of oral sub-mucous fibrosis (OSF). In fact, the approach introduced is used to grade the histopathological tissue sections into normal, OSF without dysplasia (OSFWD) and OSF with dysplasia (OSFD), which would help the oral onco-pathologists to screen the subjects rapidly. The main objective of this work is to evaluate the use of Higher Order Spectra (HOS) features and Local Binary Pattern (LBP) features extracted from the epithelial layer in classifying normal, OSFWD and OSFD. For this purpose, we extracted twenty three HOS features and nine LBP features and fed them to a Support Vector Machine (SVM) for automated diagnosis. One hundred and fifty eight images (90 normal, 42 OSFWD and 26 OSFD images) were used for analysis. LBP features provide a good sensitivity of 82.85% and specificity of 87.84%, and the HOS features provide higher values of sensitivity (94.07%) and specificity (93.33%) using SVM classifier. The proposed system, can be used as an adjunct tool by the onco-pathologists to cross-check their diagnosis.

HighlightsAbnormal grain temperature changes were detected by calculating the similarity of HSV features in cloud maps.The F-measures were higher for the improved method than for methods based on HSV and LBP feature similarity.The improved method can detect abnormal heating of grain due to mold activity or spoilage and the fluctuation in grain temperature caused by aeration.The temperature field of the grain bulk in adjacent time periods has high similarity during normal storage.Abstract. Analyses of grain temperature data are time-consuming and labor-intensive, and thorough analyses are difficult to perform. This article proposes an improved method based on the hue, saturation, and value (HSV) color feature similarity of temperature field cloud maps to detect abnormal changes in grain temperature. Historical grain temperature data are preprocessed to generate temperature field cloud maps. The improved method based on HSV feature similarity is used to calculate the similarity of temperature field cloud maps for two successive days during normal storage, and a similarity threshold is set. Five types of grain bulk temperature anomalies are then simulated. Additionally, a comparative experiment is carried out that considers traditional methods based on HSV feature similarity and local binary pattern (LBP) feature similarity. The results show that the average recall rates of the F-measures of the improved method, the traditional method based on HSV feature similarity, and the method based on LBP feature similarity are 96.2%, 89.3%, and 95.4%, respectively, and the processing speeds are 340, 300, and 690 ms per group, respectively. Finally, an abnormal grain temperature experiment is carried out. The experimental results show that the improved method can detect sudden changes in the temperature field due to mold activity or spoilage and the fluctuations in grain temperature caused by aeration. Keywords: Grain storage, HSV feature, LBP feature, Similarity, Temperature.

A face occlusion detection scheme which is based on both skin color ratio (SCR) and Local Binary Pattern (LBP) feature, is proposed.The proposed method mainly consists of four steps: foreground extraction, head detection, feature extraction, and occlusion detection.First, foreground is extracted by codebook background subtraction algorithm.Then, the head region is located using HOG head detector.After that, the skin-color ratio and LBP feature are extracted.Finally, SVM is trained based on LBP feature.The recognition result of SVM and the result of skin-color ratio feature are merged by weighted voting strategy, and then occluded faces are classified as three categories: concealed, partially concealed, and visible.Experimental results show that the proposed detection system can achieve desirable results in intelligent video surveillance systems.

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.

In computer vision, Local Binary Pattern (LBP) and Scale Invariant Feature Transform (SIFT) are two widely used local descriptors. In this paper, we propose to combine them effectively for scene categorization. First, LBP and SIFT features are regularly extracted from training images for constructing a LBP feature codebook and a SIFT feature codebook. Then, a two-dimensional table is created by combining the obtained codebooks. For creating a representation for an image, LBP and SIFT features extracted from the same positions of the image are encoded together based on sparse coding by using the two-dimensional table. After processing all features in the input image, we adopt spatial max pooling to determine its representation. Obtained image representations are forwarded to a Support Vector Machine classifier for categorization. In addition, in order to improve the scene categorization performance further, we propose a method to select correlated visual words from large codebooks for constructing the two-dimensional table. Finally, for evaluating the proposed method, extensive experiments are implemented on datasets Scene Categories 8, Scene Categories 15 and MIT 67 Indoor Scene. It is demonstrated that the proposed method is effective for scene categorization.

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.

The texture is an essential property of an image that tells about the arrangements of pixels of different intensities in an image matrix. Researchers have used many descriptors for texture classification of the images in computer vision and image processing. Local Binary Pattern (LBP) is one of the descriptors, which is computationally efficient and straightforward for texture classification. In recent years, researchers have made many enhancements to the basic LBP method to improve the quality of extracted features for an image. This paper presents a Local Roughness Binary Pattern (LRBP) descriptor for feature extraction of an image to increase LBP discriminative capability. This new descriptor extracts features from the local region of an image called a partial feature vector and concatenates these local features to obtain a feature vector of an image. This feature vector is used as input to a classifier to classify the class of an image. We tested the proposed descriptor for the images available on CUReT and KTHTIPS2b databases with Support Vector Machine (SVM) and k-nearest Neighbors (KNN) classifiers. We have presented the experimental results obtained from the analysis process regarding classification accuracy and confusion matrix. Finally, we have presented a performance comparison between the proposed method, basic LBP descriptor, and its variants. Results show that the proposed descriptor gives much better results than other descriptors on the KTHTIPS2b Database when we use the KNN classifier.KeywordsLBPLocal binary patternLRBPLocal roughness binary patternSVMSupport vector machineKNN K-nearest neighbors

Facial emotion recognition using modified HOG and LBP features with deep stacked autoencoders

The article discusses a texture operator called Local Binary Patterns (LBP) and its applications in image processing and object detection. We provide a description of the algorithm for computing LBP together with a rationale for using LBP as a feature for object detection and image recognition. Based on the algorithm we show that LBP features have a low computational overhead compared to more complicated image features such as the commonly used SIFT or SURF features or neural network based approaches because they exploit the use of extremely fast bitwise and integer operations of the CPU. We demonstrate that LBP is robust to changes in brightness, contrast, image rotation, image scale. We develop two enhancements for LBP that improve its resistance to camera noise and enhance the discriminative power of LBP when it is used as a feature for machine learning algorithms. We present the results on a challenging real-world object detection task. Keywords: computer vision, object detection, local binary patterns.

Face recognition is efficiently used in computer vision, pattern recognition, biometric, law enforcement, surveillance, criminal investigations, and missing person detection. However, face recognition is still a challenging task under variant illuminations, pose, expression, occlusion, and background. In this paper, we proposed a cascading of histogram of oriented gradients (HOG) and local binary pattern (LBP) feature extraction method on ORL face dataset, which can improve recognition rates while also addressing pose, scale, expression, and variant illumination issues. The facial recognition network was trained using various classifiers such as with KNN, SVM, and random forest (RF). The results have been shown that the accuracy rate of the combined LBP and HOG feature extraction method is better than individual LBP or HOG features for ORL database face recognition.

In today's world with the increase in pollution and other lifestyle changes of people, many individuals are prone to various cancer types. Out of these many cancer types Skin Cancer is the most common. Skin cancer is of two types i.e., benign and malignant. Timely detection of the skin cancer may lead to proper treatment and thus reduce the cost of treatment and hence reduces the damage to the skin-saving patients' life. For detecting skin cancer with high accuracy and very fast compared to the traditional methods this paper proposed the method of using texture-based features descriptors such as Local Binary Pattern (LBP) and Histogram of Oriented Gradient (HOG). This research proposed the method of detecting skin cancer type from the RGB image of the target area of skin cancer. The proposed method used texture features of the image to detect skin cancer with help of LBP and HOG texture feature descriptors. Further Logistic Regression (LR) is applied for classifying whether skin cancer is benign or malignant. The results are very efficient as the accuracy achieved by utilizing LBP and HOG of RGB image data is 99.394%. A total of 3600 RGB Images have been used for such a study. The experimental analysis results obtained are compared with other techniques like Random Forest Classifier, Ada Boost Classifiers, and Logistic Regression and it is found that the proposed approach outperforms available algorithms.

In this paper, an algorithm is proposed for Trilingual Script Identification System in block wise for camera captured images. The Local Binary Pattern (LBP) features are used for Kannada, Hindi and English images for testing the performance of a proposed algorithm, a dataset of 6000 neat block images are considered. For each script a total of 2000 images are used for the proposed method. The segmentation technique is used to segment the document image in blocks. Block of sizes 128×128, 256×256, 512×512 and 1024×1024 for Kannada, Hindi and English have been considered. The LBP features are extracted in 8 neighbors, there by generating 59 features and submitted to KNN and SVM classifiers to classify the underlying image. The identification accuracy for KNN and SVM classifiers are respectively 96.60% and 98.00% for block size 128×128, 98.71% and 98.07% for block size 256×256, 99.70% and 98.00% for block size 512×512 and further 94.90% and 99.01% for block size 1024×1024 respectively. The optimal accuracy is 99.01% for SVM classifier for block size 1024×1024. The proposed method is independent of thinning.

In telemedicine, digital watermarking is critical for safeguarding patient privacy by securely embedding sensitive Electronic Patient Records (EPR) directly into medical imagery. This work proposes a high-capacity, non-blind, and semi-fragile watermarking scheme leveraging a 64-bit complex-float computational pipeline and the Discrete Orthonormal Stockwell Transform (DOST) combined with Local Binary Pattern (LBP) features. To improve security, the architecture incorporates Arnold scrambling for confusion and chaotic mapping for diffusion-based encryption. In the attack-free scenario, the proposed method significantly outperformed the recent state-of-the-art (SOTA) technique across two MRI datasets. On the TCIA MRI dataset, the proposed method achieved mean values of 79.84 dB for Peak Signal-to-Noise Ratio (PSNR) and 0.9969 for Structural Similarity Index (SSIM), representing average improvements of 111.61% and 4.35%, respectively, over the SOTA baseline (37.73 dB and 0.9553). On the BMIBTD MRI dataset, the proposed method achieved mean values of 65.62 dB for PSNR and 0.9827 for SSIM, reflecting average improvements of 77.54% in PSNR and 11.14% in SSIM compared to the SOTA values (36.96 dB and 0.8842). Furthermore, the proposed method maintained a mean Normalised Correlation Coefficient (NCC) of 1, demonstrating performance parity with the SOTA technique in terms of general robustness. Extensive robustness analysis reveals a selective, tiered sensitivity profile: the scheme exhibits high resilience to stochastic channel noise (NCC≳0.90), a characteristic semi-fragile response to Median filtering (NCC≈0.6-0.8), and high sensitivity to deterministic manipulations such as JPEG compression, Mean filtering, and geometric transformations. Rather than a limitation, this tiered behaviour serves as an inherent integrity-authentication mechanism, where the degradation or destruction of the mantissa-embedded watermark provides immediate detection of unauthorised spatial tampering or resampling post-acquisition. Computational time analysis demonstrates that the proposed method maintains an efficient total mean execution time of 0.2203 seconds, with separate mean processing times of 0.1293 seconds for embedding and 0.0910 seconds for extraction, ensuring rapid performance for real-time clinical applications. The capacity (8.00 bpp) and efficiency (η = 0.0625) of the proposed technique were analysed and found to be high compared to recent SOTA methods. Security analysis confirms the proposed framework's robustness against statistical, differential, and brute-force attacks, achieving superior performance metrics-including high NPCR and information entropy-compared to recent SOTA methods. Beyond MRI datasets, the system demonstrated comparable performance when validated on X-ray and ultrasound scans, confirming the framework's cross-modality consistency. The proposed system provides a significant advancement in balancing high-fidelity diagnostic reconstruction with robust defence against cryptanalytic threats.