Entity

Time filter

Source Type

Sivakasi, India

Soundar K.R.,PSR Engineering College | Murugesan K.,Bharathiyar Institute of Engineering for Women
International Journal of Pattern Recognition and Artificial Intelligence | Year: 2011

Computer face recognition promises to be a powerful tool and is becoming important in our security-heightened world. Several research works on face recognition based on appearance, features like intensity, color, textures or shape have been done over the last decade. In those works, mostly the classification is achieved by finding the minimum distance or maximum variance among the training and testing feature set. This leads to the wrong classification when presenting the untrained image or unknown image, since the classification process locates at least one winning cluster having minimum distance or maximum variance among the existing clusters. But for the security related applications, these new facial image should be reported and necessary action has to be taken accordingly. In this paper, we propose the following two techniques for this purpose: (i) Use a threshold value calculated by finding the average of the minimum matching distances of the wrong classifications encountered during the training phase. (ii) Use the fact that the wrong classification increases the ratio of within-class distance and between-class distance. Experiments have been conducted using the ORL facial database and a fair comparison is made with the conventional feature spaces to show the efficiency of these techniques. © 2011 World Scientific Publishing Company. Source


Ruba Soundar K.,PSR Engineering College | Murugesan K.,Salem College
International Journal of Pattern Recognition and Artificial Intelligence | Year: 2010

Face recognition technologies can significantly impact authentication, monitoring and image indexing applications. Much research has been done on face recognition using global and local features over the last decade. By using global feature preservation techniques like Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA), we can effectively preserve only the Euclidean structure of face space, that are devoid of the lack of local features which may play a major role in some applications. On the other hand, the local feature preservation technique namely Locality Preserving Projections (LPP) preserves local information and obtains a face subspace that best detects the essential face manifold structure; however, it also suffers loss in global features which could be important in some of the applications. In this work, a new combined approach for recognizing faces which preserve both global and local information has been introduced. The proposed technique generates Combined Global and Local Preserving Features (CGLPF) that integrates the advantages of the global feature extraction technique LDA and the local feature extraction technique LPP. He et al. in their work used PCA to extract similarity features from a given set of images in order to reduce the dimensions followed by LPP. But in our method, we use LDA (instead of PCA) to extract discriminating features to reduce the dimension that yields improved facial image recognition results. This has been verified by making a fair comparison of the above two methods by the use of ORL, UMIST and 600 images formed by combining both databases. © 2010 World Scientific Publishing Company. Source


Ruba Soundar K.,PSR Engineering College | Murugesan K.,Bharathiyar Institute of Engineering for Women
IET Computer Vision | Year: 2010

Face recognition can significantly impact authentication, monitoring and indexing applications. Much research on face recognition using global and local information has been done earlier. By using global feature preservation techniques like principal component analysis (PCA) and linear discriminant analysis (LDA), the authors can effectively preserve only the Euclidean structure of face space that suffers lack of local features, but which may play a major role in some applications. On the other hand, the local feature preservation technique namely locality preserving projections (LPP) preserves local information and obtains a face subspace that best detects the essential face manifold structure; however, it also suffers loss in global features which may also be important in some of the applications. A new combined approach for recognising faces that integrates the advantages of the global feature extraction technique LDA and the local feature extraction technique LPP has been introduced here. Xiaofei He et al. in their work used PCA to extract similarity features from a given set of images followed by LPP. But in the proposed method, the authors use LDA (instead of PCA) to extract discriminating features that yields improved facial image recognition results. This has been verified by making a fair comparison with the existing methods. © 2010 The Institution of Engineering and Technology. Source


Priya M.,Smart Electrotech | Ranjith Kumar P.,PSR Engineering College
International Journal of Production Research | Year: 2015

Atherosclerosis is a condition in human circulatory, where the arteries become narrowed and hardened due to accumulation of plaque around artery wall. The growth of the disease is slow and asymptomatic. Currently, imaging methods are applied for predicting the disease progression; however, they are deficient in the required resolution and sensitivity for detection. In this work, clinical observations and habits of individuals are considered for assorting the pathologic community. Intelligent machine learning technique, decision tree forest is used for assorting the individuals. A case study was made in this work regarding the atherosclerosis disease progression and crucial features were extracted. Optimised missing value imputation strategy, iterative principal component analysis for STULONG data-set and efficient feature subset selection method, hybrid fast correlation-based filter (FCBF) have been employed for extracting the relevant features and ignoring the redundant features. Further proceeding with the methodology, our work has outperformed with extreme overall accuracy of about 99.47% compared with other state-of-the-art machine learning techniques. © 2015 Taylor & Francis Source


Raman N.,VHNSN College | Selvaganapathy M.,VHNSN College | Sudharsan S.,PSR Engineering College
Materials Science and Engineering C | Year: 2015

Abstract The coordination of therapeutically interesting designed complexes of stoichiometry [ML(Met)Cl2] [where M = Cu(II), Co(II), Ni(II), Mn(II) and Zn(II), L = benzylidene-4-aminoantipyrine and Met = methionine] has been ascertained on the basis of physicochemical techniques. Their interaction with CT DNA reveals that they are good intercalators. The anticancer mechanism of our complexes is documented from their enhanced DNA splitting personalities under physiological conditions. To reveal the chemotherapeutic action of these complexes, we explored the inflammatory response, analgesic and antioxidant activities. Moreover, all the complexes show good antimicrobial activity against few bacterial and fungal strains. Our study has identified the mechanism of action of these complexes on inhibiting tumor cells and suggested that they have great potential as novel anticancer agents. © 2015 Elsevier B.V. All rights reserved. Source

Discover hidden collaborations