M. V. D. Prasad ¹, P. V. V. Kishore ¹, D. Anil Kumar ¹, Ch. Raghava Prasad ¹

Affiliations
1 Electronic and Communication Department, K L University, Guntur, Andra Pradesh, IN

Abstract

Objectives: Fuzzy classifying of continuous sign language videos with simple backgrounds with tracking and shape combined features is the focus of this work. Methods/Analysis: Tracking and capturing hand position vectors is the artwork of horn schunck optical flow algorithm. Active contours extract shape features from sign frames in the video sequence. The two most dominant features of sign language are combined to build sign features. This feature matrix is the training vector for Fuzzy Inference Engine (FIS). The classifier is tested with 50 signs in a video sequence. Ten different signers created 50 signs. Different instances of FIS are tested with different combination of feature vectors. The results are compared to our previous work using no tracking and with discrete sign language database. Findings: A Word Matching Scores (WMS) gauges the performance of the classifiers. A 92.5% average matching score is reported in this work. A through comparison for FIS gesture classifier between Discrete Cosine. Novelty/Improvement: Transform features, Elliptical Fourier descriptor features and the proposed hybrid features for continuous sign language videos show a 40% jump in word matching score.

Keywords

Active Contour Shape Analysis, Continuous Sign Language, Fuzzy Inference Engine, Hybrid Feature Vector, Optical Flow Tracking.

Full Text

   

K. Kade Mahesh ¹, P. V. V. Kishore ¹, J. Karande Kailash ²

Affiliations
1 Department of Electronics and Communication Engineering, KL University, Vijaywada – 522502, Andhra Pradesh, IN
2 Department of Electronics and Telecommunication Engineering, SKNSCOE, Korti, Solapur Univeristy, Solapur – 413304, Maharashtra, IN

Abstract

Objectives: Iris recognition is one of biometric identification methods adopted over worldwide. In this paper we intend to update the previous survey and cover the survey over the period of roughly 2010 to 2015. Methods: We focus on the paper that appeared in Springer, IEEE Xplore and International Conferences, National and International journals covering Image Processing, Signal Processing, Pattern recognition and Bioinformatics. This paper primarily focuses on the survey of Iris camera for Iris acquisition, Methods adopted for iris segmentation, feature extraction, matching and public Iris database. Iris segmentation and feature extraction are important steps in Iris recognition. As there are several publications on the segmentation and feature extraction separately in literature, we have selected and summarized only prominent work in our paper. Findings: We have compared the algorithm used by various researchers with the performance parameter obtained by other researchers. We have found that there is scope for improvement in algorithms and need to understand the Iris Code in detail. Application: This comparative analysis will help researcher to get view on present scenario related to Iris recognition system.

Keywords

Acquisition Segmentation, Database, Features, Iris, Matching.

Full Text