Boosting Color Feature Selection for Color Face Recognition

Choi, Jae Young; Ro, Yong Man; Plataniotis, Konstantinos N.

doi:10.1109/tip.2010.2093906

Cited by 51 publications

(18 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this study, only texture-based local features are extracted from facial images. Inspired by the impressive recognition rate improvements achieved by combining texture and color features [36], [40], we plan to investigate the use of this effective combination approach in the metric learning framework in future research.…”

Section: Resultsmentioning

confidence: 99%

“…The use of texture and color information remains however an open problem [36]. Instead of designing handcrafted encoding methods, the approaches of [6] and [40] applied learning frameworks to select the discriminant features in order to avoid the difficulties associated to obtaining optimal encoding methods manually. In [6], an unsupervised learning-based method was proposed to encode the local micro-structures of a face into a set of more uniformly distributed discrete codes.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Discriminant Metric Learning Approach for Face Verification

2015

KSII TIIS

View full text Add to dashboard Cite

In this study, we propose a distance metric learning approach called discriminant metric learning (DML) for face verification, which addresses a binary-class problem for classifying whether or not two input images are of the same subject. The critical issue for solving this problem is determining the method to be used for measuring the distance between two images. Among various methods, the large margin nearest neighbor (LMNN) method is a state-of-the-art algorithm. However, to compensate the LMNN's entangled data distribution due to high levels of appearance variations in unconstrained environments, DML's goal is to penalize violations of the negative pair distance relationship, i.e., the images with different labels, while being integrated with LMNN to model the distance relation between positive pairs, i.e., the images with the same label. The likelihoods of the input images, estimated using DML and LMNN metrics, are then weighted and combined for further analysis. Additionally, rather than using the k-nearest neighbor (k-NN) classification mechanism, we propose a verification mechanism that measures the correlation of the class label distribution of neighbors to reduce the false negative rate of positive pairs. From the experimental results, we see that DML can modify the relation of negative pairs in the original LMNN space and compensate for LMNN's performance on faces with large variances, such as pose and expression.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Discriminant Metric Learning Approach for Face Verification

2015

KSII TIIS

View full text Add to dashboard Cite

show abstract

“…To provide solutions to these, the online updating model was integrated with the parameterized CovBoost. Boosting color-component feature selection framework as depicted in (Choi et al, 2011) find the best set of color-component features from various color spaces. However, other face features fails to readily incorporate to identify the most significant features for face recognition task.…”

Section: Related Workmentioning

confidence: 99%

Classification of Digital Images Using Fusion Elevated Order Classifier in Wavelet Neural Network

Arulmurugan¹

2014

Journal of Computer Science

View full text Add to dashboard Cite

The revival of wavelet neural networks obtained an extensive use in digital image processing. The shape representation, classification and detection play a very important role in the image analysis. Boosted Greedy Sparse Linear Discriminate Analysis (BGSLDA) trains the cascade level of detection in an efficient manner. With the application of reweighting concept and deployment of class-reparability criterion, lesser search was made on more efficient weak classifiers. At the same time, Multi-Scale Histogram of Oriented Gradients (MS-HOG) method removes the confined portions of images. MS-HOG algorithm includes the advanced recognition scenarios such as rotations transportations on multiple objects but does not perform effective feature classification. To overcome the drawbacks in classification of higher order units, Fusion Elevated Order Classifier (FEOC) method is introduced. FEOC contains a different fusion of high order units to deal with diverse datasets by making changes in the order of units with parametric considerations. FEOC uses a prominent value of input neurons for better fitting properties resulting in a higher level of learning parameters (i.e.,) weights. FEOC method features are reduced using feature subset collection method. However, elevation mechanisms are significantly applied to the neuron, neuron activation function type and finally in the higher order types of neural network with the functions of adaptive in nature. FEOC have evaluated sigma-pi network representing both the Elevated order Processing Unit (EPU) and pi-sigma network. The experimental performance of Fusion Elevated Order Classifier in the wavelet neural network is evaluated against BGSLDA and MS-HOG using Statlog (Landsat Satellite) Data Set from UCI repository. FEOC performed in MATLAB with factors such as classification accuracy rate, false positive error, computational cost, memory consumption, response time and higher order classifier rate.

show abstract

“…No que diz respeito a esta última categoria de descritores, o reconhecimento facial no humano adulto depende da informação de bandas de frequência e orientações espaciais específicas (Wenger & Townsend, 2000;Williams, Willenbockel, & Gauthier, 2009) que são processadas de maneira desproporcional: muitas tarefas de reconhecimento são executadas mais precisamente quando adultos têm acesso a frequências espaciais médias (8-16 ciclos/ face) e quando as faces são orientadas horizontalmente (Boutet, Collin, & Faubert, 2003;Dakin & Watt, 2009). Outras características sensoriais como a visão de cores tem importante papel no reconhecimento de faces (Bindemann & Burton, 2009;Choi, Ro, & Plataniotis, 2009, 2011 sugerindo grande importância do processamento bottom-up para esta construção subjetiva.…”

Section: Introductionunclassified

PERCEPÇÃO SOCIAL DE EMOÇÕES EM FACES: Julgando sexo, gênero e raça

2018

View full text Add to dashboard Cite

RESUMOO presente estudo teve como objetivo observar as relações entre sexo, raça e julgamento de emoções em faces humanas. Para a realização do estudo, foram coletados dados sobre a identificação e intensidade percebidas sobre a emoção de faces humanas. As faces apresentadas eram de diferentes sexo e raça, além de mostrar diferentes emoções. Durante o experimento, os participantes eram expostos a essas faces e eles respondiam por meio de formulário eletrônico, o nome da emoção apresentada e, em escala tipo Likert, a intensidade que julgava a emoção na figura apresentada. A análise estatística da coleta identificou uma preferência de julgamento para faces do mesmo sexo e raça do participante. A relevância dessa preferência está relacionada a empatia entre raças e sexo, representada minimamente pelo reconhecimento de emoções mutuamente. ABSTRACTThe present study aimed to observe the relationships between sex, race and judgment of emotions in human faces. To perform the research, data about identification and intensity perceived on the emotion of human faces were collected. The faces presented were different on sex and race, besides showing different emotions. During the experiment participants were exposed to these faces and answered through electronic form, the name of the presented emotion and, on a Likert scale, the intensity they judged the seen emotion. Statistical analysis of the collection identified a preference on emotion judgment for faces with the same sex and race of the participant. The relevance of this preference is related to the empathy between races and sex, minimally represented by the recognition of emotions to each other.

show abstract

Boosting Color Feature Selection for Color Face Recognition

Cited by 51 publications

References 27 publications

Discriminant Metric Learning Approach for Face Verification

Discriminant Metric Learning Approach for Face Verification

Classification of Digital Images Using Fusion Elevated Order Classifier in Wavelet Neural Network

PERCEPÇÃO SOCIAL DE EMOÇÕES EM FACES: Julgando sexo, gênero e raça

Contact Info

Product

Resources

About