Informatics Publishing Limited

Gauri Agrawal ¹, Sanjay Kumar Maurya ²

Affiliations
1 Department of Electronics and Communication Engineering, B.S.A. College of Engineering and Technology, IN
2 Department of Electrical Engineering, GLA University, IN

Abstract

In real world, applications designing of a robust face recognition system have always been a big challenge. This paper presents an approach to face recognition using embedding of dual tree complex wavelet transform, Self-organizing map and ensemble of weak classifier. The DT-CWT is applied on the images to obtain dynamic and multi scale informational characterization of the face images. Thus, a multidimensional feature vector is formed by combining DT-CWT coefficients. Self Organizing Map (SOM) is further used in embedding the feature vector which also results in reduction of feature vector. Finally, ensembles of k-Nearest Neighbor (k-NN) weak classifiers are used for classification of recognition system. The proposed approach is tested on image of ORL database. The experiment shows an impressive recognition result that culminated during the testing.

Keywords

Face Recognition, Wavelet Transform, Self-Organizing Map (SOM).

Full Text

     

Sanjay Kumar Maurya ¹, Akhandanand Shukla ², R. K. Ngurtinkhuma ³

Affiliations
1 Research Scholar, Department of Library & Information Science, Mizoram University, Aizawl, Mizoram, IN
2 Assistant Professor, Department of Library & Information Science, Mizoram University, Aizawl, Mizoram, IN
3 Professor, Department of Library & Information Science, Mizoram University, Aizawl, IN

Abstract

The purpose of study is to measure the coverage of LIS academia in Google Scholar and Microsoft Academic using scientometric indicators. The study is based on simple search queries in Google Scholar and Microsoft Academic for each LIS faculty whose information is available on their university website. Duplicate names for LIS faculties have been filtered by adding the extra search string with their names and non-LIS publications have been removed from the study. The study found more coverage for Google Scholar than Microsoft Academic. Google Scholar based “document types” are quite unclear and considered as its’ limitations. The study is limited to 26 LIS faculties from five Central Universities of North-East India. The results are limited due to use of simple search in Google Scholar and Microsoft Academic rather than profile search. The study provides insight for the individual researcher and LIS departments to focus on indexing of their research in Google Scholar and Microsoft Academic.

Keywords

Research Performance, Google Scholar, Microsoft Academic, Research Coverage, LIS Research.

Full Text