ARTIFICIAL NEURAL NETWORK BASED DISCRIMINATION OF MINELIKE OBJECTS IN INFRARED IMAGES
Journal Title: Indian Journal of Computer Science and Engineering - Year 2014, Vol 5, Issue 4
Abstract
An artificial neural network (ANN) model with a simple architecture containing a single hidden layer is presented to discriminate the landmine objects from the acquired infrared images. The proposed method consists of preprocessing, segmentation, feature extraction and ANN based classification. Texture features based on gray level co-occurrence matrix (GLCM) are considered as inputs to the neural network classifier. The proposed method is tested on the infrared images acquired from two different soil types namely black cotton soil and Maharashtra sand. The ability of the back propagation neural network in discriminating the landmines from the clutters in the infrared images acquired from inhomogeneous soil is discussed. The results of the field experiments carried out at the outdoor land mine detection test facility, DRDO, Pune are presented. The results are encouraging.
Authors and Affiliations
G. Suganthi , Reeba Korah , N. Seetharaman
Keywords
Related Articles
- EP ID EP147636
- DOI -
- Views 128
- Downloads 0
Design of JK Flip-Flop using MODFET Technology
The pertinent choice of flip-flop topologies is an essential importance in the design of VLSI integrated circuits for high speed and high performance MODFET circuits. Understanding the suitability of flipflops and select...
Signed Numbers Conversions
Signed integers are normally represented using 2’s complement representation. Addition and subtraction of signed numbers is done in the same manner as for unsigned numbers. However carry (or borrow) is simple ignored. Un...
Performance Evaluation of Dynamic and Static Sensor Node in Wireless Sensor Network
A wireless sensor network (WSN) consists of spatially distributed autonomous sensors to monitor physical or environmental conditions, such as temperature, sound, pressure, etc. and to cooperatively pass their data throug...
DIGITAL WATERMARKING SCHEMES FOR AUTHORIZATION AGAINST COPYING OR PIRACY OF COLOR IMAGES
This paper presents digital watermarking methods for authorization against copying or piracy of color images. Watermarking is a very important field for copyrights of various electronic documents and media. With images w...
PERFORMANCE OF CONCURRENCY CONTROL MECHANISMS IN CENTRALISED DATABASE SYSTEMS
The objective of this study is to propose user control system that definitely increases the performance of realtime data service. However the most existing work on this RTDB was based on very critical closed loop control...