AGE CLASSIFICATIONS BASED ON SECOND ORDER IMAGE COMPRESSED AND FUZZY REDUCED GREY LEVEL (SICFRG) MODEL
Journal Title: International Journal on Computer Science and Engineering - Year 2013, Vol 5, Issue 6
Abstract
One of the most fundamental issues in image classification and recognition are how to characterize images using derived features. Many texture classification and recognition problems in the literature usually require the computation on entire image set and with large range of gray level values in order to achieve efficient and precise classification and recognition. This leads to lot of complexity in evaluating feature parameters. To address this, the present paper derives a Second Order image Compressed and Fuzzy Reduced Grey level (SICFRG) model, which reduces the image dimension and grey level range without any loss of significant feature information. The present paper derives GLCM features on the proposed SICFRG model for efficient age classification that classifies facial image into a five groups. The SICFRG image mode of age classification is derived in three stages. In the first stage the 5 x 5 matrix is compressed into a 2 x 2 second order sub matrix without loosing any significant attributes, primitives, and any other local properties. In stage 2 Fuzzy logic is applied tPo reduce the Gray level range of compressed model of the image. In stage 3 GLCM is derived on SICFRG model of the image. The experimental evidence on FG-NET and Google aging database clearly indicates the high classification rate of the proposed method over the other methods.
Authors and Affiliations
Jangala. Sasi Kiran , Dr. V. Vijaya Kumar , Dr. B. Eswara Reddy
Keywords
Related Articles
- EP ID EP125546
- DOI -
- Views 114
- Downloads 0
Energy Efficient Event Driven Data Reporting System for Wireless Sensor Network
Power conservation is important in sensor devices since battery life is usually one of the critical components in extending the life time of the sensor network. Cluster technology that enables a group of sensor working c...
Person Identification Using Fingerprint by Hybridizing Core Point and Minutiae Features
Fingerprint recognition refers to the automated method of verifying a match between two human fingerprints. Fingerprints are one of many forms of biometrics used to identify an individual and verify their identity. The n...
Cluster level optimization of residual energy consumption in wireless sensor networks for lifetime enhancement
Network lifetime is perhaps the most important metric for the evaluation of sensor networks. In a resource-constrained environment, the consumption of every limited resource must be considered The network can only fulfil...
Opinion Mining Classification Using Key Word Summarization Based on Singular Value Decomposition
With the popularity of online shopping it is increasingly becoming important for manufacturers and service providers to ask customers to review their product and associated service. Typically the number of customer revie...
LOCATION DISCOVERY WITH SECURITY IN WIRELESS SENSOR NETWORK
Localization is one of the supporting technologies in wireless sensor networks. To identify the exact location of each and every sensor may not be feasible. In most of the sensor network application gathered by sensor wi...