Image fusion is the process of combining the most relevant information from multiple source images to obtain an accurate fused image. In this paper, we want to fuse visual and thermal satellite images.In order to provide enhanced information, we have investigated techniques of image fusion to obtain the most accurate information. This paper presents a technique which will produce an accurate fused image using discrete wavelet transform (DWT) for feature extraction and using Genetic Algorithms (GAs) to get the more optimized combined image. The performance of the proposed image fusion scheme is evaluated with mutual information (MI), root mean square error (RMSE), and it is also compared to the fused image that is generated by using Pixel Level GA based Image Fusion (PLGA_IF) and Discrete Wavelet Transform based Image Fusion (DWT_IF) techniques. Simulation results conducted with DWT and GA show that the proposed method outperforms the existing image fusion algorithms.

This paper presents the use of the Low Memory Locality Sensitive Hashing (LMLSH) technique operating in Euclidean space to build a data structure for the Defense Meteorological Satellite Program (DMSP) satellite imagery database. The LMLSH technique finds satellite image matches in sublinear search time. The texture feature vectors of the images are extracted using pyramid-structured wavelet transform coupled with Gaussian central moment technique. These feature vectors and families of hash functions, drawn randomly and independently from a Gaussian distribution, are used to build hash tables. Given a query, the hash tables are used to pull out the best matches to that query and this is done in a sublinear search time complexity. When tested, our algorithm has proven to be approximately twenty six times faster than the Linear Search (LS) algorithm. In addition, the LMLSH algorithm searches about two percent of the entire database randomly to find the possible matches to any given query without loss of accuracy compared to the absolute best matches returned by its LS counterpart.

No abstract

No abstract

No abstract