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 122
- Downloads 0
Three Party Authentication Key Distributed Protocols Using Implicit and Explicit Quantum Cryptography
Cryptography is the science of information security. Applications of cryptography include ATM cards, computer passwords, and electronic commerce. The combination of Implicit quantum key distribution protocol (3AQKDP) and...
Elimination of Estimation biases in the Software Development
The software effort estimations are usually too low and the prediction is also a very difficult task as software is intangible in nature. Also the estimation is based on the parameters that are usually partial in nature....
MULTILEVEL HIERARCHICAL DLQ ALGORITHM FOR NETWORK DISCOVERY IN WSN
Neighbour discovery is the determination of all nodes in the network that can communicate with a given node. Routing typically begins with neighbour discovery. Discovering neighbours should be both quick as well as energ...
NETWORK NEUTRALITY SURVEY
Network Neutrality is one of the most acrimoniously debated topics in Academia and Industry. Extensive literature has been written on it on both sides of the subject. In this survey paper we summarize the related promine...
A COMPARATIVE STUDY OF PROPOSED TOPOLOGY CONTROL ALGORITHMS FOR ENERGY EFFICIENT WIRELESS SENSOR NETWORK
Recent years showed a wide range of applications in Wireless Sensor Networks (WSN). For a WSN, Topology Control is crucial to obtain an energy efficient network without affecting the connectivity and other properties. In...