Kelwin Fernandes, Jaime S. Cardoso · arXiv (Cornell University) · 2017
Local Binary Pattern (LBP) is a traditional descriptor for texture analysis that gained attention in the last decade. Being robust to several properties such as invariance to illumination translation and scaling, LBPs achieved state-of-the-art results in several applications. However, LBPs are not able to capture high-level features from the image, merely encoding features with low abstraction levels. In this work, we propose Deep LBP, which borrow ideas from the deep learning community to improve LBP expressiveness. By using parametrized data-driven LBP, we enable successive applications of the LBP operators with increasing abstraction levels. We validate the relevance of the proposed idea in several datasets from a wide range of applications. Deep LBP improved the performance of traditional and multiscale LBP in all cases.
Cited by 9Open access
Tobias Lindahl · KTH Publication Database DiVA (KTH Royal Institute of Technology) · 2007
This Masters thesis studies the concept of local binary patterns, which describe the neighbourhood of a pixel in a digital image by binary derivatives. The operator is often used in texture analysis and has been successfully used in facial recognition. This thesis suggests two methods based on some basic ideas of Björn Kruse and studies of literature on the subject. The first suggested method presented is an algorithm which reproduces images from their local binary patterns by a kind of integration of the binary derivatives. This method is a way to prove the preservation of information. The second suggested method is a technique of interpolating missing pixels in a single CCD camera based on local binary patterns and machine learning. The algorithm has shown some very promising results even though in its current form it does not keep up with the best algorithms of today.
Cited by 13Open access
Marco Mora, M. Silva-Ibarra, M. Acevedo-Letelier · 2019
Speckle is a multiplicative noise that greatly deteriorates images. In this paper a model of Local Binary Patterns (LBP) adapted to images with speckle (MuLBP) is proposed. The multiplicative model is constructed by substituting the additive comparisons of the traditional LBP for multiplicative comparisons from the Bigeometric Calculus. The experiments were carried out considering the 10.824 images of the KTH-TIPS2, FMD, CASIA and UFI databases. To compare the additive and multiplicative models, the Euclidean distance between the LBP histograms of the image with noise and without noise is adopted. The results indicate that, the distance between the histograms, the image with noise with respect to the image without noise, is smaller for the multiplicative models than for the traditional additive models. The above means that, the multiplicative LBP represent in a better way the textures in images contaminated with speckle.
Cited by 1
Felix Juefei-Xu, Marios Savvides · Lecture notes in computer science · 2015
Cited by 20
Feiniu Yuan, Xue Xia, Jinting Shi · Information Sciences · 2018
Cited by 24
Alicia Aglio-Caballero, Belén Ríos‐Sánchez, Carmen Sánchez Ávila et al. · 2017
Palm vein recognition has emerged as a novelty highly invariant biometric technique that is difficult to forge due to their internal nature. In this work the texture descriptors Local Binary Patterns (LBP) and Uniform Local Binary Patterns (LBPU) are analyzed as feature extraction methods for biometric verification based on palm veins. Their performance and efficiency has been studied through a multivariate analysis including the impact of different wavelengths and the parameters of the texture descriptor number of neighboors and radio. CASIA Multi-Spectral Palmprint Image Database V1.0 has been used for the evaluation of the system.
Cited by 15
Niraj P. Doshi, Gerald Schaefer · 2013
Local binary patterns (LBP) are known as a simple yet powerful texture descriptor encoding local neighbourhood properties. LBP descriptors can be calculated at different radii, leading to a multi-resolution texture characterisation. Multi-dimensional LBP (MD-LBP) utilises this concept, while also maintaining the relationships between the different scales by building a multi-dimensional histogram of LBP features. Although this has been shown to give good discriminatory power, the resulting feature vectors are also rather large. In this paper, we show that Dominant MD-LBP (D-MD-LBP), which utilises only dominant texture bins, provides an effective texture descriptor of reduced dimensionality as our experimental results, run on three benchmark datasets of the Outex test suite, confirm.
Cited by 4
С. В. Пронин · Journal of Optical Technology · 2020
An image-classification algorithm based on an alphabet of local binary patterns is described. The efficiency of the proposed algorithm is demonstrated using a test image set of handwritten digits (MNIST). A comparison of the algorithm’s properties with similar results to those of convolutional artificial neural networks is presented.
Cited by 1
Matti Pietikäinen, Guoying Zhao · Elsevier eBooks · 2015
Cited by 68Open access
Matti Pietikäinen, Abdenour Hadid, Guoying Zhao et al. · Computational imaging and vision · 2011
Cited by 570
Balakrishna Gudla, Srinivasa Rao Chalamala, Santosh Kumar Jami · 2015
Gender classification using facial features has attracted researchers attention recently. Gender classification using texture features of faces exhibited promising improvement over other facial features. Gender classification finds applications in systems which use gender as one of the parameters. Local Binary Patterns (LBP) are known to have good texture representation properties. Through this paper we present a variant of Local Binary Patterns for gender classification which can discriminate the facial textures efficiently. In this method, we used a new neighborhood shape for obtaining LBP as its representation of texture is superior than traditional LBP. We compute the proposed LBP on each non-overlapping blocks of a face image and a histogram of these LBPs is computed. We used these histograms as facial feature vectors for gender classification as these histograms shown their robustness to compression and uniform intensity variations. The classification task has been achieved by using Support Vector Machine (SVM). We compared our method with existing gender classification methods based on LBP with classifier being the same as SVM. The proposed LBP based descriptor outperforms the traditional LBP based methods and achieved 96.17 percent recognition rate on combined frontal face datasets of FERET and FEI.
Cited by 7
Оптический журнал · 2020
© 2020 ГЈ. Г‘. Г‚. ÏðîГГЁГГ€ГГ±ГІГЁГІГіГІ ôèçèîëîãèè ГЁГ¬. Г€.ГЏ. Ïà âëîâà ÐÀÍ, Ñà ГГЄГІ-Ïåòåðáóðã E-mail: pronins@sbor.netÓÄÊ 004.93'12Ïîñòóïèëà â ðåäà êöèþ 01.08.2020DOI:10.17586/1023-5086-2020-87-
Cited by 0
Matti Pietikäinen, Abdenour Hadid, Guoying Zhao et al. · Computational imaging and vision · 2011
Cited by 448
Janis Fehr, H. Bürkhardt · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · 2008
We present a novel method for the fast computation of rotation invariant ¿local binary patterns¿ (LBP) on 3D volume data. Unlike a previous publication on 3D LBP, this new approach is not limited to ¿uniform patterns¿, providing a real 3D extension of the standard and rotation invariant LBP. We evaluate our methods in the context of 3D texture analysis of biological data.
Cited by 84
Subrahmanyam Murala, Q. M. Jonathan Wu · IEEE Journal of Biomedical and Health Informatics · 2014
In this paper, a new image indexing and retrieval algorithm using local mesh patterns are proposed for biomedical image retrieval application. The standard local binary pattern encodes the relationship between the referenced pixel and its surrounding neighbors, whereas the proposed method encodes the relationship among the surrounding neighbors for a given referenced pixel in an image. The possible relationships among the surrounding neighbors are depending on the number of neighbors, P. In addition, the effectiveness of our algorithm is confirmed by combining it with the Gabor transform. To prove the effectiveness of our algorithm, three experiments have been carried out on three different biomedical image databases. Out of which two are meant for computer tomography (CT) and one for magnetic resonance (MR) image retrieval. It is further mentioned that the database considered for three experiments are OASIS-MRI database, NEMA-CT database, and VIA/I-ELCAP database which includes region of interest CT images. The results after being investigated show a significant improvement in terms of their evaluation measures as compared to LBP, LBP with Gabor transform, and other spatial and transform domain methods.
Cited by 215
G. P. Cheng, Jiaxing Chen · 2016
This paper presents a local feature descriptor based on Local Binary Patterns (LBP). This descriptor uses binary bit string to represent the local region of images and the integral image to mean filter that makes descriptor building faster. Compared to Scale-invariant feature transform (SIFT)that the calculation is large and the process is time consuming in the description of the characteristics, the descriptor based on LBP speeds about 1 orders of magnitude. In the matching effect for blurred image, illumination changes, and different JPEG compression ratio, the matching results are better than descriptors based on SIFT.
Cited by 1
Le Ngu Nguyen, Thi-Thu-Hong Phan · 2024
To maintain the economic value of pistachio nuts, which is vital in the agricultural economy, efficient post-harvest industrial processes are essential. Different pistachio species cater to distinct markets, increasing the need for accurate classification methods. This study introduces an alternative feature extraction approach using Local Binary Pattern (LBP) to enhance the classification of pistachio species. We apply this method to a dataset comprising 2,148 images of two pistachio species, Kirmizi and Siirt, each with unique market-relevant characteristics. Various machine learning models are evaluated, with Multilayer Perceptron (MLP) emerging as the most effective, achieving a classification accuracy of 96.74%. The findings demonstrate that machine learning methods, combined with LBP, significantly improve the performance and efficiency of pistachio variety classification. These results hold promising applications in precise pistachio selection and intelligent farming techniques.
Cited by 1
Linlin Shen, Jinwen He · Lecture notes in computer science · 2011
Cited by 5
Lei Chen, Yunhong Wang, Yiding Wang et al. · 2009
In this work, we present a novel algorithm for face recognition named statistical local binary patterns (sLBP). This is a further development of original local binary pattern algorithm. Our method is applied for face recognition under visual light environment dealing with dramatically illumination varying on faces After a statistical analysis on the distribution probability of the gray-level difference values between neighbor pixels, a mapping function is proposed to encode a wide range of these values into three binary bits. Three extension LBP layers are then generated Finally the uniform pattern histograms of all these layers in every divided region are concatenated as an enhanced local feature vector of the face image. Experimental results on FERET face database show considerable effectiveness and robustness of our proposed method.
Cited by 20
Ning Jiang, Jiu Xu, Satoshi Goto · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences · 2012
In recent years, local pattern based features have attracted increasing interest in object detection and recognition systems. Local Binary Pattern (LBP) feature is widely used in texture classification and face detection. But the original definition of LBP is not suitable for human detection. In this paper, we propose a novel feature named gradient local binary patterns (GLBP) for human detection. In this feature, original 256 local binary patterns are reduced to 56 patterns. These 56 patterns named uniform patterns are used for generating a 56-bin histogram. And gradient value of each pixel is set as the weight which is always same in LBP based features in histogram calculation to computing the values in 56 bins for histogram. Experiments are performed on INRIA dataset, which shows the proposal GLBP feature is discriminative than histogram of orientated gradient (HOG), Semantic Local Binary Patterns (S-LBP) and histogram of template (HOT). In our experiments, the window size is fixed. That means the performance can be improved by boosting methods. And the computation of GLBP feature is parallel, which make it easy for hardware acceleration. These factors make GLBP feature possible for real-time pedestrian detection.
Cited by 7