Satellite Image Classification and Content-Base Image Retrieval Using Type-2 Fuzzy Logic
Journal Title: IOSR Journals (IOSR Journal of Computer Engineering) - Year 2014, Vol 16, Issue 6
Abstract
Abstract: The detection of oceanic structures, such as upwelling’s or eddies, from satellite images has significance for marine environmental studies, coastal resource management, and ocean dynamics studies. There is a lack of tools that allow us to retrieve automatically relevant structures from large satellite image databases. This Paper focuses on the development and validation of a Content-Based Image Retrieval (CBIR) system to classify and retrieve oceanic structures from satellite images with improved accuracy. The image we obtain from http://oceancolor.gsfc.nasa.gov/, which give images from different satellite like Sea-viewing Wide Field-of-view Sensor (SeaWiFS), Moderate Resolution Imaging Spectroradiometer (MODIS), or MEdium Resolution Imaging Spectrometer (MERIS). During the processing of satellite images, different types of imperfection (uncertainties, ambiguities and vagueness) can occur. These imperfections can involve the gray‐level intensities, the geometrical characteristics and relations among image objects, and the expert knowledge itself used to overcome these problems. The CBIR system includes several types of soft computing technologies, such as neural networks and fuzzy logic. An advantage of fuzzy logic approach is that the system can be more comprehensible to human users because fuzzy databases (DBs) manage a terminology close to natural languages. This system give retrieval of most relevant and typical oceanic structures, such as upwelling, eddies and wakes.
Authors and Affiliations
Prof. Anita Thengade , Shirish A. Agale
Keywords
Related Articles
- EP ID EP152845
- DOI -
- Views 86
- Downloads 0
Incremental Sequential Pattern Tree Mining
In this paper, we have proposed an Incremental Sequential Pattern Tree mining algorithm to retrieve new updated frequent sequential patterns from dynamic sequence database. Sequential Pattern Tree stores...
Providing High Security and Recovering Good Quality Image using Visual Cryptographic Technique
Abstract: Security is an important factor, since many digital images are transmitted through internet, which contains secret information. Symmetric and Asymmetric methods are two types of cryptographic techniques used to...
Survey of Machine Learning Techniques in Textual Document Classification
Classification of Text Document points towards associating one or more predefined categories based on the likelihood expressed by the training set of labeled documents. Many machine learning algorithms plays &nbs...
User Search Goal Prediction based on Feedback Sessions
Abstract : If the topic is very vast and the query is ambiguous, the users may be having different search goals when they submit the queries to a search engine. The goals of the users can be analysed in order to ma...
Object Query Optimization through Detecting Independent Sub queries
ABSTRACT: Database Switching includes execution of queries on same or different machines connected in LAN with different backend without rewriting any queries. Switching between the databases reduces the work of re...