Pyramid-Based Multi-scale LBP Features for Face Recognition

Wang, Wei; Chen, Weimin; Xu, Dan

doi:10.1109/cmsp.2011.37

Cited by 14 publications

(9 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some works perform face recognition, as [6], [7], [8], [9] that also implements gender recognition and [10] that also proposes a LBP multi-block approach. Some other works perform pedestrian detection, as [11] that uses optical and thermal imagery, [12] that also performs tracking, and [13] that also performs face and head detection.…”

Section: Related Workmentioning

confidence: 99%

Concrete and Asphalt Runway Detection in High Resolution Images Using LBP Cascade Classifier

Cruz

Shiguemori²,

Guimarães³

2013

2013 BRICS Congress on Computational Intelligence and 11th Brazilian Congress on Computational Intelligence

View full text Add to dashboard Cite

Automatic object recognition in digital satellite images is not a simple task due to several variations present in the capture process and object appearance and pose, consequently, different general purpose techniques have been proposed. In this paper, an approach with LBP boosted cascade classifier for automatic runway detection in high resolution satellite imagery is analyzed. Promising results are obtained with the methodology presented in this work, considering objects with variations of scale, rotation and images obtained by different sensors.

show abstract

Section: Related Workmentioning

confidence: 99%

Concrete and Asphalt Runway Detection in High Resolution Images Using LBP Cascade Classifier

Cruz

Shiguemori²,

Guimarães³

2013

2013 BRICS Congress on Computational Intelligence and 11th Brazilian Congress on Computational Intelligence

View full text Add to dashboard Cite

show abstract

“…The Matlab source code is available at http://web.uvic.ca/~mcote/PBLBP/code.zip. Table II presents the classification accuracy of our proposed approach for CLBP_S (classic LBP) using three standard ( , ) neighborhoods: (8,1), (16,2), and (24,3). Table III presents the classification accuracy of our proposed approach for all CLBP schemes from [14] using a (8,1) neighborhood.…”

Section: B Evaluationmentioning

confidence: 99%

“…This differs also from bag of features and pyramidbased approaches (e.g. [16]) as we do not use a global image representation through the pooling of codes from a codebook or through a massive concatenated feature vector. Our approach, which adds robustness to LBP classification methods with respect to any type of intra-class texture variations, differs from that of Guo et al [17] who increased robustness by favoring certain LBP codes through supervised learning of discriminative LBP codes.…”

Section: Introductionmentioning

confidence: 99%

Robust Texture Classification by Aggregating Pixel-Based LBP Statistics

Cote

Albu

2015

IEEE Signal Process. Lett.

View full text Add to dashboard Cite

This letter addresses the texture classification problem through a pixel-based local binary pattern (LBP) statistics aggregation mechanism. Real-world texture images often present challenges for classification algorithms in terms of intra-class variability due, among others, to variable illumination. The LBP operator, a state-of-the-art texture descriptor, possesses key properties for tackling real-world texture images: discriminative power and invariance against monotonic gray level changes. We propose a novel texture classification approach that increases the robustness of LBP-based methods with respect to any type of intra-class variations. The method locally characterizes each pixel with an LBP code histogram and globally computes the label of a textured image by aggregating pixel labels through a voting process. Our approach can be in principle applied to any LBP version, as it focuses on how statistics are computed from LBP codes. We show that the proposed pixel-based approach improves upon traditional LBP block-based approaches in terms of classification accuracy by up to 5.1 p.p. on the public Outex database for the classic LBP with various neighborhoods as well as for various LBP extensions.Index Terms-Image classification, image texture, local binary pattern, pixel-based classification.

show abstract

“…Wang et al [6], proposed a pyramid-based multi-scale LBP approach. To begin with, multi-scale analysis is used to construct the face image pyramid using Gaussian filter into several levels then the LBP operator is applied to each level of the image pyramid to extract facial features under various scales.…”

Section: Introductionmentioning

confidence: 99%

“…Then, each sub-image is divided into nine non-overlapping blocks from which LBP operator extract the characteristic spectrum and statistic histogram. In papers [6] and [7], non LL sub-bands (i.e. high-frequency sub-bands) are not used for feature extraction.…”

Section: Introductionmentioning

confidence: 99%

LBP based on multi wavelet sub-bands feature extraction used for face recognition

Rashid

Jassim

Sellahewa

2013

2013 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)

View full text Add to dashboard Cite

The strategy of extracting discriminant features from a face image is immensely important to accurate face recognition. This paper proposes a feature extraction algorithm based on wavelets and local binary patterns (LBPs). The proposed method decomposes a face image into multiple sub-bands of frequencies using wavelet transform. Each sub-band in the wavelet domain is divided into non-overlapping subregions. Then LBP histograms based on the traditional 8-neighbour sampling points are extracted from the approximation sub-band, whilst 4-neighbour sampling points are used to extract LBPHs from detail sub-bands. Finally, all LBPHs are concatenated into a single feature histogram to effectively represent the face image. Euclidean distance is used to measure the similarity of different feature histograms and the final recognition is performed by the nearest-neighbour classifier.The above strategy was tested on two publicly available face databases (Yale and ORL) using different scenarios and different combination of sub-bands. Results show that the proposed method outperforms the traditional LBP based features.

show abstract

Pyramid-Based Multi-scale LBP Features for Face Recognition

Cited by 14 publications

References 17 publications

Concrete and Asphalt Runway Detection in High Resolution Images Using LBP Cascade Classifier

Concrete and Asphalt Runway Detection in High Resolution Images Using LBP Cascade Classifier

Robust Texture Classification by Aggregating Pixel-Based LBP Statistics

LBP based on multi wavelet sub-bands feature extraction used for face recognition

Contact Info

Product

Resources

About