• Chaitali Gajanan Gangane
• Prof. V. S. Mahalle

In recent years the content based image retrieval has received widespread research interest in field of computer vision and pattern reorganization. The main concept of CBIR is to reduce the gap between low level visual features and high level human concepts, based on the visual features such as color, shape & texture extracted from images, the CBIR System tries to fulfil the needs of users who are retrieving the images with the desired concept in their mind. As there is tremendous growth in satellite technology, the availability of remote sensing images in archives is growing and thus CBIR has get extensive attention in field of RS for the necessity to search and retrieval of RS images. However most of the systems assumes that the training images are annotated by single label but this assumption does not fit for the complexity of RS images that contain mulitiple land cover classes called multilabel. The CBIR multilabel RS aims to retrieve the relevant images from the very large image archives based on 1) characterization of images by set of features and 2) retrieval of images that are similar to query images. The different methods are discussed in literature survey

Content-based image retrieval (CBIR), correlated label propagation, multilabel categorization, region adjacency graph (RAG), remote sensing (RS), semi supervised learning, subgraph matching

"Survey Paper on Multilabel Remote Sensing Image Retrieval Using CBIR Techniques", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.163-166, April-2019, Available :http://www.jetir.org/papers/JETIR1904825.pdf

"Survey Paper on Multilabel Remote Sensing Image Retrieval Using CBIR Techniques", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp163-166, April-2019, Available at : http://www.jetir.org/papers/JETIR1904825.pdf