Adaptive classifier integration for robust pattern recognition

Chibelushi, Claude C.; Deravi, Farzin; Mason, John S.

doi:10.1109/3477.809043

Cited by 38 publications

(17 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various metrics exist, which can be used to capture this confidence information. Examples include score entropy [48], dispersion [48], variance [3], cross classifier coherence [16], and difference [13]. For a test observation vector , we have the set of ranked normalized scores .…”

Section: E Reliability Measuresmentioning

confidence: 99%

See 1 more Smart Citation

Robust Biometric Person Identification Using Automatic Classifier Fusion of Speech, Mouth, and Face Experts

Fox

Gross

Cohn

et al. 2007

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Abstract-Information about person identity is multimodal. Yet, most person-recognition systems limit themselves to only a single modality, such as facial appearance. With a view to exploiting the complementary nature of different modes of information and increasing pattern recognition robustness to test signal degradation, we developed a multiple expert biometric person identification system that combines information from three experts: audio, visual speech, and face. The system uses multimodal fusion in an automatic unsupervised manner, adapting to the local performance (at the transaction level) and output reliability of each of the three experts. The expert weightings are chosen automatically such that the reliability measure of the combined scores is maximized. To test system robustness to train/test mismatch, we used a broad range of acoustic babble noise and JPEG compression to degrade the audio and visual signals, respectively. Identification experiments were carried out on a 248-subject subset of the XM2VTS database. The multimodal expert system outperformed each of the single experts in all comparisons. At severe audio and visual mismatch levels tested, the audio, mouth, face, and tri-expert fusion accuracies were 16.1%, 48%, 75%, and 89.9%, respectively, representing a relative improvement of 19.9% over the best performing expert.

show abstract

Section: E Reliability Measuresmentioning

confidence: 99%

“…A visual train/test mismatch was not considered. In [16], robust audio-visual classifier fusion under both audio and visual train/test mismatch conditions was described. The adaptive fusion results were encouraging, with improved audio-visual accuracies over either modality alone.…”

mentioning

confidence: 99%

Robust Biometric Person Identification Using Automatic Classifier Fusion of Speech, Mouth, and Face Experts

Fox

Gross

Cohn

et al. 2007

IEEE Trans. Multimedia

View full text Add to dashboard Cite

show abstract

“…The approach is based on a localised representation of facial expression features, and on fusion of classifier outputs. Data fusion or sensor fusion has been used successfully in many fields such as pattern recognition [6,7,25] or distributed computing [4,5]. The ability to handle occluded facial features is important for achieving robust recognition.…”

Section: Introductionmentioning

confidence: 99%

Recognition of Facial Expressions in the Presence of Occlusion

Bourel

Chibelushi

Low

2001

Procedings of the British Machine Vision Conference 2001

View full text Add to dashboard Cite

We present a new approach for the recognition of facial expressions from video sequences in the presence of occlusion. Although promising results have been reported in the literature on automatic recognition of facial expressions, most techniques have been assessed using experiments performed in controlled laboratory conditions which do not reflect real-world conditions. The goal of the work presented herein, is to develop recognition techniques that will overcome some limitations of current techniques, such as their sensitivity to partial occlusion of the face. The proposed approach is based on a localised representation of facial features, and on data fusion. The experiments show that the proposed approach is robust to partial occlusion of the face.

show abstract

“…Some examples include score dispersion [12], score entropy [12], score variance [22], cross classifier coherence coefficient [7] and the difference, 5, of the top two best scores [2]. (is calculated as…”

Section: Audio-visual Fusionmentioning

confidence: 99%

“…In [22], audio visual speaker verification experiments are carried out on 36 subjects, however, only an audio train\test mismatch was tested, whereas a visual train\test mismatch was not considered. In [7], robust audio-visual classifier fusion under both audio and visual train\test mismatch conditions is described. The adaptive fusion results were encouraging, with improved audio-visual scores better than either modality alone.…”

Section: Introductionmentioning

confidence: 99%

Robust multi-modal person identification with tolerance of facial expression

Fox

Reilly

2004

2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583)

View full text Add to dashboard Cite

-The research presented in this paper describes audio-visual speaker identification experiments carried out on a large data set of 251 subjects. Both the audio and visual modeling is carried out using hidden Markov models. The visual modality uses the speaker> lip information. The audio and visual modalities are both degraded to emulate a train\test mismatch. The fusion method employed adapts automatically by using classijer score reliability estimates of both modalities to give improved audio-visual accuracies at all tested levels of audio and visual degradation, compared to the individual audio or visual modality accuracies. A maximum visual identification accuracy of 86% was achieved. This result is comparable to the perjormance of systems using the entire face, and suggests the hypothesis that the system described would be tolerant to vaving facial expression, since only the information around the speaker S lips is employed.

show abstract

Adaptive classifier integration for robust pattern recognition

Cited by 38 publications

References 12 publications

Robust Biometric Person Identification Using Automatic Classifier Fusion of Speech, Mouth, and Face Experts

Robust Biometric Person Identification Using Automatic Classifier Fusion of Speech, Mouth, and Face Experts

Recognition of Facial Expressions in the Presence of Occlusion

Robust multi-modal person identification with tolerance of facial expression

Contact Info

Product

Resources

About