To address the drawbacks of existing secret data hiding techniques, such as their high computational demands for training deep neural networks or their limited hiding capacity, we present a new approach. Our proposed ...
详细信息
The local binary pattern (LBP) is an effective feature, describing the size relationship between the neighboring pixels and the current pixel. While individual LBP-based methods yield good results, co-occurrence LBP-b...
详细信息
The local binary pattern (LBP) is an effective feature, describing the size relationship between the neighboring pixels and the current pixel. While individual LBP-based methods yield good results, co-occurrence LBP-based methods exhibit a better ability to extract structural information. However, most of the co-occurrence LBP-based methods excel mainly in dealing with rotated images, exhibiting limitations in preserving performance for scaled images. To address the issue, a cross-scale co-occurrence LBP (CS-CoLBP) is proposed. Initially, we construct an LBP co-occurrence space to capture robust structural features by simulating scale transformation. Subsequently, we use Cross-Scale Co-occurrence pairs (CS-Co pairs) to extract the structural features, keeping robust descriptions even in the presence of scaling. Finally, we refine these CS-Co pairs through Rotation Consistency Adjustment (RCA) to bolster their rotation invariance, thereby making the proposed CS-CoLBP as powerful as existing co-occurrence LBP-based methods for rotated image description. While keeping the desired geometric invariance, the proposed CS-CoLBP maintains a modest feature dimension. Empirical evaluations across several datasets demonstrate that CS-CoLBP outperforms the existing state-of-the-art LBP-based methods even in the presence of geometric transformations and image manipulations.
S R C Texture features play a vital role in content-based image retrieval (CBIR) applications. Most texture extraction methods have a low accuracy and high feature vector length. This paper presents a novel hexagonal ...
详细信息
S R C Texture features play a vital role in content-based image retrieval (CBIR) applications. Most texture extraction methods have a low accuracy and high feature vector length. This paper presents a novel hexagonal local binary pattern (HLBP) to extract more informative and compact features from images. To have robust patterns against rotation, rotation invariant hexagonal patterns are presented using cyclic set theory. Texture feature vector is extracted from hexagonal images based on proposed patterns and used in CBIR application. To evaluate proposed method, experiments are performed in five datasets Corel-1k, Brodatz, VisTex, Corel-10k, and STex. The proposed HLBP method outperforms square local binary pattern (SLBP) in images with noise in the terms of precision. The feature vector length of the proposed method is 64, which is much shorter than those in competitive methods and leads to high speed in retrieval phase. The best performance of the proposed method is revealed in texture datasets which achieved the highest precision among all competitive methods.
This study explores timber defect classification using features extracted from Colour Uniform local binary patterns (CULBP) for four timber species: Rubberwood, KSK, Merbau, and Meranti, evaluating eight common defect...
详细信息
The paper offers a methodology for recognizing humans by integrating the complementary features face, gait are extracted by fusion of Median local binary pattern (Median-LBP) and Gabor Scale Average (GSA)-based Princi...
详细信息
This study investigates the integration of local binary pattern (LBP) features with eager learning models for the classification of retinal abnormalities, focusing on diseases like Diabetic Retinopathy (DR) and Age-Re...
详细信息
Islanding is a significant obstacle along with excessive penetration of DG sources. The islanding could cause harm to the customers and their equipment. The IEEE 1547 DG interconnection regulations stipulate that the ...
详细信息
The work presented in this research outlines a new method for detecting bone fractures, which is based on a machine learning model. To achieve this goal, Support Vector Machine (SVM) classifiers are trained on a datas...
详细信息
One of the most hazardous diseases is cancer, which poses a significant threat to human health due to its ability to manifest in various parts of the body as abnormal, proliferative cells. In the case of oral cancer, ...
详细信息
One of the most hazardous diseases is cancer, which poses a significant threat to human health due to its ability to manifest in various parts of the body as abnormal, proliferative cells. In the case of oral cancer, diverse behavioral patterns may be observed, making early detection and accurate prognosis crucial for effective and timely treatment. Multi-Layer Visual Feature Fusion (MLVFF) is a novel feature fusion technique that is explor to develop a system to detect and predict oral cancer at its earliest, most treatable stages. MLVFF combines local binary patterns (LBP) characteristics with Convolutional Neural Network (CNN). More precisely, MLVFF may successfully improve the discriminating strength of features for Oral Cancer image recognition by combining the LBP and CNN versions, respectively. Test accuracy for the suggested model is 98.00%. In addition, we draw attention to emerging research questions in the field of cancer sickness, offering relevant data for further research that will improve cancer detection and treatments.
Human authentication is a crucial part of most computer vision automation systems. Conventional fingerprint, iris, face, or palm print-based systems cannot identify individuals when their external biometric components...
详细信息
Human authentication is a crucial part of most computer vision automation systems. Conventional fingerprint, iris, face, or palm print-based systems cannot identify individuals when their external biometric components are destroyed, such as by severe burns, rashes, or wounds. The main elements of any person authentication system are non-forgery, security, resilience, and privacy. The local texture descriptor is vital in describing hand radiographic images' texture. This paper presents the novel local triangular binarypattern based texture descriptor to provide a local texture description of the hand radiographic images. The performance of the proposed descriptor is assessed using different machine learning classifiers such as K-nearest neighbor (KNN), support vector machine (SVM), radial basis function-SVM (RBF-SVM), classification tree (CT), and random forest (RF) for authentication of the 20 users based on hand radiographs. The suggested system provides an overall accuracy of 84.17% for KNN, 90% for SVM, 91.35% for RBF-SVM, 92.50% for CT, and 96.67% for RF for the 20 users for the In-house hand radiographic dataset.
暂无评论