Local binary pattern and its derivatives for face recognition

Suruliandi, A.; Meena, K.; Rose, R. Reena

doi:10.1049/iet-cvi.2011.0228

Cited by 74 publications

(30 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This work combines the statistical features proposed in the work by Heinle et al (2010) and the distribution of local texture features using LBP codes (Suruliandi et al, 2012). The statistical features represent the spectral and texture information in a global view.…”

Section: Feature Extractionmentioning

confidence: 99%

“…In addition to the above-mentioned statistical features, we enhance the texture features by applying LBPs (Suruliandi et al, 2012). The LBP P ,R code for a pixel (x c , y c ) is defined in Eq.…”

Section: Distribution Of Local Texture Featuresmentioning

confidence: 99%

“…The abilities of these descriptors are more restricted since a certain amount of information is lost in the simplification process. In addition to the simple statistical features, we extract the local texture features using local binary patterns (LBPs) (Suruliandi et al, 2012). The texture information encoded by LBP forms higher dimensional feature vectors compared to traditional statistical features.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Block-based cloud classification with statistical features and distribution of local texture features

Cheng

2015

Atmos. Meas. Tech.

View full text Add to dashboard Cite

Abstract. This work performs cloud classification on all-sky images. To deal with mixed cloud types in one image, we propose performing block division and block-based classification. In addition to classical statistical texture features, the proposed method incorporates local binary pattern, which extracts local texture features in the feature vector. The combined feature can effectively preserve global information as well as more discriminating local texture features of different cloud types. The experimental results have shown that applying the combined feature results in higher classification accuracy compared to using classical statistical texture features. In our experiments, it is also validated that using block-based classification outperforms classification on the entire images. Moreover, we report the classification accuracy using different classifiers including the k-nearest neighbor classifier, Bayesian classifier, and support vector machine.

show abstract

Section: Feature Extractionmentioning

confidence: 99%

Section: Distribution Of Local Texture Featuresmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Block-based cloud classification with statistical features and distribution of local texture features

Cheng

2015

Atmos. Meas. Tech.

View full text Add to dashboard Cite

show abstract

“…La comparación comienza con los pixeles que van de acuerdo a las manecillas del reloj, sí el valor de intensidad de gris del pixel central es mayor o igual al valor de intensidad de gris del pixel que se está evaluando, se coloca un "1" en dicha celda; caso contrario, se coloca un "0". (Suruliandi, Meena, & Reena Rose, 2012).…”

Section: Características Lbp (Local Binary Pattern)unclassified

Reconocimiento de hojas del árbol Pithecellobium Samán usando visión artificial

Gracia¹,

Ruiz²

2014

Investigatio

View full text Add to dashboard Cite

Existen algoritmos que ayudan en el aprendizaje de los agentes artificiales, de los cuales se aplicará en el presente trabajo los conocidos como, clasificadores en cascada. Los objetivos del presente estudio son: implementar y evaluar el rendimiento de ocho clasificadores en cascada usando dos tipos de extractores de características en el reconocimiento de hojas del árbol Pithecellobium Samán también conocido como árbol de Samán. Para la implementación de los clasificadores en cascada, se usa la librería EmguCV junto con Visual Studio y a cada clasificador, se le suministran imágenes del objeto a reconocer e imágenes que no lo sean. Los clasificadores se evaluarán usando las siguientes curvas: ROC (Receiver Operating Giaractersistic) para calcular el área bajo la curva, DET (Detection Error TradeofJ) para evaluar las muestras positivas mal clasificadas y PR (Precision and Recall) para medir la precisión. Como resultado, el extractor más eficiente es el Local Binary Pattern (LPB). PALABRAS CLAVE Aprendi.aje automático, cIasflcadores en cascada, Emgu CJ/ Haar, 1 .RP, visión artijicial, intelgencia artificiaL ABSTRACTThere are algorithms that assist in the learning of artificial agents, which will be applied in the present work known as cascade classifiers. The objectives of this study are: implementing and evaluating performance eight cascaded classiflers using two kinds of feature extractors to recognize Pithecellobium leaf tree also known as Saman Saman tree. For the implementadon of cascade classifiers, EmguCV library and Visual Studio are used, for each c1assi1ier is supplied with images of object to be recognized and images that are not. The classifiers are evaluated using the following curves: ROC (Receiver Operating Charactersisticl to calculate the area under the curve, DET (Detection Error Tradeoff to assess positive samples misclassified and PR (Precision and Recail) to measure accuracy. As a result, the most efficient extractor Local Binarv Pattern is (LPB). Cl/Ç Harr, LBP, compuler vision, artificial intel4gence. KEYWORDS Machine learning, class/lers cascade Emgu

show abstract

“…The artificial neural network [1], principle component analysis (PCA) [2], independent component analysis [3], linear discriminant analysis (LDA) [4], support vector machine [5] and K-nearest neighbour [6] are the most widely used methods. In addition, the hidden Markov model (HMM) [7] has been successfully used in face recognition during the last two decades.…”

mentioning

confidence: 99%

Low-Complexity Face Recognition using a Multilevel DWT and TwoStates of Continuous HMM to recognize Noisy Images

Farhan¹,

Mahmuod²,

Al-Muifraje³

et al. 2017

IJET

View full text Add to dashboard Cite

Abstract-Face recognition has become an important subject in modern life, especially in security and surveillance applications. This work introduces a face recognition method, which is characterized by high-speed, low-complexity, and high-efficiency in a noisy environment. The performance of this method is greatly improved by using a median filter, such that each image is filtered to eliminate the influence of noise and light illumination. Multiple levels of discrete wavelet transform are applied to the filtered image to reduce size and eliminate further noise. Subsequently, the resultant image is scanned using a window with a predefined overlap in raster fashion to construct a sequence of observation vectors used as the basis of a model. I. INTRODUCTION Face recognition has recently received considerable attention due to its important applications in many areas and fields such as credit card verification, security, and surveillance. The advantage of face recognition over other biometric techniques is the mechanism to recognize persons, which is frequently performed without requiring that the person have physical contact with the device, e.g. use of palm or fingers. The face image can be captured by a camera without informing the target person, especially in the case of criminal surveillance and apprehension.The methods introduced to recognize faces vary relative to the procedure used for feature extraction and type of classifier used. The artificial neural network [1], principle component analysis (PCA) [2], independent component analysis [3], linear discriminant analysis (LDA) [4], support vector machine [5] and K-nearest neighbour [6] are the most widely used methods. In addition, the hidden Markov model (HMM) [7] has been successfully used in face recognition during the last two decades. The advantage of applying HMM to face recognition is the flexibility of the selection of training models, such that it is easy to add or remove individuals. There is no need for re-training the overall system; however, a model with updated images must be re-trained.For dimensionality reduction, a particular feature extraction method is applied to form a sequence of observation vectors to model faces. Thereafter, for each individual, one HMM model is constructed by training a specified set of images for that individual. The training process depends on the estimation of the HMM parameters [8], such that the process is iterated several times before it converges. In the testing process, the algorithm computes the probability of the observations of unknown face image calibrated with the parameters derived from the training. The unknown face belongs to the person whose model computes the highest probability.The disadvantages of using more states of the HMM are: high computational complexities, large memory requirements, and low processing speed. The proposed work addresses the unfavourable features by using only two states of the HMM.

show abstract

Local binary pattern and its derivatives for face recognition

Cited by 74 publications

References 16 publications

Block-based cloud classification with statistical features and distribution of local texture features

Block-based cloud classification with statistical features and distribution of local texture features

Reconocimiento de hojas del árbol Pithecellobium Samán usando visión artificial

Low-Complexity Face Recognition using a Multilevel DWT and TwoStates of Continuous HMM to recognize Noisy Images

Contact Info

Product

Resources

About