Face Recognition Using Convolution Based Dwt and CLBP Feature Vectors
Journal Title: IOSR Journals (IOSR Journal of Computer Engineering) - Year 2016, Vol 18, Issue 5
Abstract
Abstract: The face recognition is an essential criteria to identify a person in recent advanced security systems. In this paper, we propose efficient Face Recognition using Convolution based DWT and CLBP Feature Vectors. Here database images are first applied with DWT then normalized and convolved with the original image toachieve sharpening of images and filtering of high frequency components. The features thus obtained are applied to CLBP which generates more unique features. The same procedure is repeated for test image to obtain unique test features which are compared with database features using Euclidean Distance. The performance parameters are calculated for standard database and it is observed that the proposed method is better in comparison with the existing methods.
Authors and Affiliations
Narayan T Deshpande , Dr. S Ravishankar
Keywords
Related Articles
- EP ID EP149358
- DOI -
- Views 97
- Downloads 0
Super-Resolution Reconstruction of Images using Total Variation Regularization and Wiener Filter Deconvolution
Abstract: This paper presents a novel technique for reconstruction of High-resolution images from multiple Low-resolution images. A Multi-frame approach implements fusion of non-redundant information which was obtained f...
Survey and Comparative Study on Resource Allocation Strategies in Cloud Computing Environment
Cloud computing is an essential ingredient of modern computing systemsCloud computing provides an on demand service because it offers dynamic resource allocation for reliable and highly available services in pay as-you-c...
Sentiment Classification in Hindi
Abstract : Traditional approaches for classification of sentiments depend on lexical or syntax based feature oron both. Different methods for sentiments classifications are described .The main goal of analysis of thesent...
Enhanced Decision Tree Algorithm for Data Streams using adaptation of Concept Drift
Abstract: Construction of a decision tree is a well researched problem in data mining. Mining of streaming data is a very useful and necessary application. Algorithms such as VFDT and CVFDT are used for decision tr...
Computer Vision: Visual Extent of an Object
The visual extent of an object reaches beyond the object itself. It is reflected in image retrieval techniques which combine statistics from the whole image in order to identify the image within. Nevertheless, it...