A HIGHLY EFFICIENT AUDIO-VISUAL RECOGNITION SYSTEM BASED ON MULTIBAND FEATURE
Journal: International Journal of Civil Engineering and Technology (IJCIET) (Vol.8, No. 10)Publication Date: 2017-10-18
Authors : D. MANIVANNAN N.K. MANIKANDAN; RAVIKUMAR S;
Page : 315-324
Keywords : Audio-Visual Recognition; Computational Complexity; Face Localization; Face Segmentation; Video-Based Face Recognition; Wavelet Transform.;
Abstract
This paper present a extremely high-octane audio-visual detection system in compression domain. For face recognition systems, the multiband feature fusion method selects the wavelet sub bands that are equable to illumination and facial expression variations. These sub bands will be distilled directly from the inverse quantization in the compression system. By taking the inverse quantized wavelet coefficient of the video as the input, the inverse wavelet transform which equivalents to image reconstruction is omitted. As a result, the computational complexity of the conventional video-based face recognition system is attenuated. To present a set of new face localization methods to localize the facial wavelet coefficients from the wavelet sub band image. The additional feature (Audio) will be added into the facial feature to enhance the recognition performance of the system. The dual optimal multiband feature fusion method is then used to fuse the two set of wavelet coefficients and generate the scores. The proposed system achieves high recognition accuracy in audio-visual database and also provides low computational complexity.
Other Latest Articles
- SUBSOIL CHARACTERIZATION USING GEOELECTRICAL AND GEOTECHNICAL INVESTIGATIONS: IMPLICATIONS FOR FOUNDATION STUDIES
- PREDICTION OF FRESH AND HARDENED PROPERTIES OF NORMAL CONCRETE VIA CHOICE OF AGGREGATE SIZES, CONCRETE MIX-RATIOS AND CEMENT
- A SOLAR TRACKER ASSISTED AUTOMATIC IRRIGATION SYSTEM FOR AGRICULTURAL FIELDS
- PERSON ANAMNESIS TRACKING SYSTEM USING CLOUD COMPUTING
- MINIMIZATION OF ENERGY CONSUMPTION USING RGB WHITE PROCESS IN CLOUD
Last modified: 2018-04-20 14:33:55