Recently, local binary patterns (LBP) based descriptors and sparse representation based classification (SRC) become both eminent techniques in face recognition. Preliminary techniques of combining LBP and SRC have bee...
详细信息
ISBN:
(纸本)9781612843490
Recently, local binary patterns (LBP) based descriptors and sparse representation based classification (SRC) become both eminent techniques in face recognition. Preliminary techniques of combining LBP and SRC have been proposed in the literature. However, the state-of-art method suffers from the "curse of dimensionality" for real world scenarios. In this paper, a novel face recognition algorithm of combining LBP with SRC is proposed;in which the dimensionality problem is resolved by divide-and-conquer and the discriminative power is strengthen via its pyramid architecture. The proposed face recognition method is evaluated on AR Face Database and yields very impressive results.
In this paper a new facial expression recognition method based on local Fisher Discriminant Analysis (LFDA) is proposed. LFDA is used to extract the low-dimensional discriminant embedded data representations from the ...
详细信息
ISBN:
(纸本)9783642233203;9783642233210
In this paper a new facial expression recognition method based on local Fisher Discriminant Analysis (LFDA) is proposed. LFDA is used to extract the low-dimensional discriminant embedded data representations from the original high-dimensional local binary patterns (LBP) features. The K-nearest-neighbor (KNN) classifier with the Euclidean distance is adopted for facial expression classification. The experimental results on the popular JAFFE facial expression database demonstrate that the best accuracy based on LFDA is up to 85.71%, outperforming the used Principal Component Analysis (PCA), and Linear Discriminant Analysis (LDA).
Robust identity inference is one of the biggest challenges in current visual surveillance systems. Although, face is an important biometric for generic identity inference, it is not always accessible in video-based su...
详细信息
ISBN:
(纸本)9783642228223;9783642228216
Robust identity inference is one of the biggest challenges in current visual surveillance systems. Although, face is an important biometric for generic identity inference, it is not always accessible in video-based surveillance systems due to the poor quality of the video or ineffective viewpoints where the captured face is not clearly visible. Hence, taking advantage of additional features to increase the accuracy and reliability of these systems is an increasing need. Appearance and clothing are potentially suitable for visual identification and tracking suspects. In this research we present a novel approach for recognition of upper body clothing, using local binary patterns (LBP) and colour information, as an assistive tool for identity inference.
This paper presents age classification on facial images using subpattern-based local binary patterns (LBP) method. Classification of age intervals are conducted separately on female and male facial images since the ag...
详细信息
ISBN:
(纸本)9780819485830
This paper presents age classification on facial images using subpattern-based local binary patterns (LBP) method. Classification of age intervals are conducted separately on female and male facial images since the aging process for female and male is different for human beings in real life. The age classification performance of the holistic approaches is compared with the performance of subpattern-based LBP approach in order to demonstrate the performance differences between these two types of approaches. To be consistent with the research of others, our work has been tested on two publicly available databases namely FGNET and MORPH. The experiments are performed on these aging databases to demonstrate the age classification performance on female and male facial images of human beings using subpattern-based LBP method with several parameter settings. The results are then compared with the results of age classification of the holistic PCA and holistic subspace LDA methods.
An automatic, reliable and efficient prediction system for protein subcellular localization can be used for establishing knowledge of the spatial distribution of proteins within living cells and permits to screen syst...
详细信息
An automatic, reliable and efficient prediction system for protein subcellular localization can be used for establishing knowledge of the spatial distribution of proteins within living cells and permits to screen systems for drug discovery or for early diagnosis of a disease. In this paper, we propose a two-stage multiple classifier system to improve classification reliability by introducing rejection option. The system is built as a cascade of two classifier ensembles. The first ensemble consists of set of binary SVMs which generalizes to learn a general classification rule and the second ensemble focus on the exceptions rejected by the rule. To enhance diversity for the classifier ensembles, multiple features are introduced, including the local binary patterns (LBP), Gabor filtering and Gray Level Coocurrence Matrix (GLCM). Using the public benchmark 2D HeLa cell images, a high classification accuracy 96% is obtained with rejection rate 21%. (C) 2011 Published by Elsevier Ltd. Selection and/or peer-review under responsibility of the Asia-Pacific Chemical, Biological & Environmental Engineering Society (APCBEES)
Recognition of object under uncontrolled illumination environment is imprecise and vague. A simple image preprocessing chain is taken for precept. localbinary pattern (LBP) is capable of reducing noise levels in back...
详细信息
ISBN:
(纸本)9783642227134
Recognition of object under uncontrolled illumination environment is imprecise and vague. A simple image preprocessing chain is taken for precept. localbinary pattern (LBP) is capable of reducing noise levels in background regions. local ternary patterns (LTP) fragmenting less under noise in uniform regions. Gabor filter acts as a resounding filtering source for local spatial frequencies. Phase congruency is to extract the image in phase as well as in magnitude levels. The result is obtained by the KLDA based classifiers with combination of LBP and Gabor features. The above explained features are obtained from both the input and the data base image. In that the LBP and Gabor features are fused and the distance is calculated. If both the input and database images are same, the face is recognized;otherwise the face is not recognized. The simulation results exemplify the proposed technique for image with different lighting, expressions and structural defects.
The partial occlusion is one of the key issues in the face recognition community. To resolve the problem of partial occlusion, based on our previous work of local Gabor binarypatterns (LGBP) for face recognition, we ...
详细信息
The partial occlusion is one of the key issues in the face recognition community. To resolve the problem of partial occlusion, based on our previous work of local Gabor binarypatterns (LGBP) for face recognition, we further propose Kullback-Leibler divergence (KLD)-based LGBP for partial occluded face recognition. The local property of LGBP face recognition is thoroughly used in the method, by introducing KLD between the LGBP feature of the local region and that of the non-occluded local region to estimate the probability of occlusion. The probability is used as the weight of the local region for the final feature matching. The experimental results on the AR face database demonstrate the effectiveness of the KLD-based LGBP face recognition method for partially occluded face images.
Motivated by the advantages of using shape matching technique in detecting objects in various postures and viewpoints and the discriminative power of localpatterns in object recognition, this paper proposes a human d...
详细信息
ISBN:
(纸本)9781424478149
Motivated by the advantages of using shape matching technique in detecting objects in various postures and viewpoints and the discriminative power of localpatterns in object recognition, this paper proposes a human detection method combining both shape and appearance cues. In particular, local shapes of the body parts are detected using template matching. Based on body parts' shapes, local appearance features are extracted. We introduce a novel localbinary pattern (LBP) descriptor, called Non-Redundant LBP (NRLBP), to encode local appearance of human. The proposed method was evaluated and compared with other state-of-the-art human detection methods on two commonly used datasets: MIT and INRIA pedestrian test sets. We also performed extensive experiments on selecting appropriate parameters as well as verifying the improvement of the proposed method through all stages of the framework.
The gradient based feature, such as histograms of oriented gradients, focuses on the spatial distribution of edge orientations, but disregards the color information. Color-based features are very popular in image clas...
详细信息
The gradient based feature, such as histograms of oriented gradients, focuses on the spatial distribution of edge orientations, but disregards the color information. Color-based features are very popular in image classification but rarely used in human detection. In this paper we propose a new human detection method by combining texture-based features with color information. Basically, localbinary pattern (LBP) is used as a texture feature, and a new color feature, relational color similarity (RCS), is introduced to enrich the descriptor set. By combining RCS and LBP as the feature set, adopting linear support vector machine (SVM) as the classifier, carefully designed experiments demonstrate the superiority of RCS-LBP over other traditional features for human detection on INRIA human database. (C) 2011 Society of Photo-Optical Instrumentation Engineers (SPIE). [DOI: 10.1117/1.3621517]
An automatic, reliable and efficient prediction system for protein subcellular localization can be used for establishing knowledge of the spatial distribution of proteins within living cells and permits to screen syst...
详细信息
An automatic, reliable and efficient prediction system for protein subcellular localization can be used for establishing knowledge of the spatial distribution of proteins within living cells and permits to screen systems for drug discovery or for early diagnosis of a disease. In this paper, we propose a two-stage multiple classifier system to improve classification reliability by introducing rejection option. The system is built as a cascade of two classifier ensembles. The first ensemble consists of set of binary SVMs which generalizes to learn a general classification rule and the second ensemble focus on the exceptions rejected by the rule. To enhance diversity for the classifier ensembles, multiple features are introduced, including the local binary patterns (LBP), Gabor filtering and Gray Level Coocurrence Matrix (GLCM). Using the public benchmark 2D HeLa cell images, a high classification accuracy 96% is obtained with rejection rate 21%.
暂无评论