Improving AdaBoost Based Face Detection Using Face-Color Preferable Selective Attention

Kim, Bumhwi; Ban, Sang-Woo

doi:10.1007/978-3-540-88906-9_12

Cited by 16 publications

(15 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Biologically inspired vision system may provide a critical clue to overcome the limitations of the current artificial vision system. Figure 2 shows the biologically inspired selective attention model for human face detection (Kim et al 2008). In order to implement a human-like efficient visual selective attention function, we consider the bottom-up saliency map (SM) model proposed in (Jeong et al 2008).…”

Section: Face Detectionmentioning

confidence: 99%

“…After obtaining the candidate salient areas for a human face, the obtained face candidate areas are used as an input of the AdaBoost algorithm (Viola and Jones 2004). We adopted an AdaBoost approach using simple Haar-like features as the face detection algorithm where face candidate regions are localized by the face-color preferable SM model (Kim et al 2008). There are two datasets for face feature extraction and learning for the AdaBoost model.…”

Section: Face Detectionmentioning

confidence: 99%

“…The first stage consists of the two processes: face detection and extraction of vocal features. In the face detection part, we simply consider a skin color preferable attention model for face color perception and Haar-like form features for face form perception, in which all the processes work in real time (Kim et al 2008;Viola and Jones 2004). In this model, a biologically motivated selective attention model with face-color preference selects face candidate areas in a natural scene.…”

Section: Introductionmentioning

confidence: 99%

“…This paper is organized as follows. Section 2 describes the proposed incremental personal authentication system which consists of bottom-up face detection using face color preferable attention for selecting face candidate areas (Kim et al 2008), audio feature extraction using MFCC, incremental learning of audiovisual features using incremental principal component analysis (IPCA) (Ozawa et al 2008), and the incremental learning of a neural classifier called resource allocating network with long-term memory (RAN-LTM) (Ozawa et al 2005). In Sect.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A real-time personal authentication system based on incremental feature extraction and classification of audiovisual information

Jang

Ozawa

2011

Evolving Systems

Self Cite

View full text Add to dashboard Cite

We propose a new approach to a real-time personal authentication system based on incrementally updated visual (face) and audio (voice) features of persons. The proposed system consists of real-time face detection, incremental audiovisual feature extraction, and incremental neural classifier model with long-term memory. The face detection part, a biologically motivated face-color preferable selective attention model first localizes face candidate regions in natural scenes, and then the Adaboost-based face detection identifies human faces from the localized facecandidate regions. The mel-frequency cepstral coefficient is used for vocal feature extraction of speakers. Moreover, incremental principal component analysis (IPCA) is used to reduce the dimensions of audiovisual features and to update them incrementally. The features extracted by IPCA is fed to the resource allocating network with long-term memory which learns facial and vocal features incrementally and recognizes faces in real time. Experimental results show that the proposed system can enhance the test performance incrementally without serious forgetting. In addition, a multi-modal (facial and vocal) feature effectively increases the robustness of the personal authentication system in noisy environments.

show abstract

Section: Face Detectionmentioning

confidence: 99%

Section: Face Detectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A real-time personal authentication system based on incremental feature extraction and classification of audiovisual information

Jang

Ozawa

2011

Evolving Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…Especially a complex background increases the chance of misclassification. To reduce false positives, complementary information, like skin color, was used in [7,12], however, without a light compensation technique. As a result, these algorithms missed skin regions, and as such, yielded a lower detection rate than the basic VJ detector.…”

Section: Introductionmentioning

confidence: 99%

Face Detection in Intelligent Ambiences with Colored Illumination

Katsimerou

Redi

Heynderickx

2013

Ambient Intelligence - Software and Applications

View full text Add to dashboard Cite

Abstract. Human face detection is an essential step in the creation of intelligent lighting ambiences, but the constantly changing multi-color illumination makes reliable face detection more challenging. Therefore, we introduce a new face detection and localization algorithm, which retains a high performance under various indoor illumination conditions. The method is based on the creation of a robust skin mask, using general color constancy techniques, and the application of the Viola-Jones face detector on the candidate face areas. Extensive experiments, using a challenging state-of-the-art database and a new one with a wider variation in colored illumination and cluttered background, show a significantly better performance for the newly proposed algorithm than for the most widely used face detection algorithms.

show abstract

Multiple Occluded Face Detection Based on Binocular Saliency Map

Kim

Ban

2009

Neural Information Processing

View full text Add to dashboard Cite

Improving AdaBoost Based Face Detection Using Face-Color Preferable Selective Attention

Cited by 16 publications

References 7 publications

A real-time personal authentication system based on incremental feature extraction and classification of audiovisual information

A real-time personal authentication system based on incremental feature extraction and classification of audiovisual information

Face Detection in Intelligent Ambiences with Colored Illumination

Multiple Occluded Face Detection Based on Binocular Saliency Map

Contact Info

Product

Resources

About