To obtain retrieval accuracy of content based images retrieval systems, the prime notice is on reduction of �semantic gaps� between the visual features and human linguistics than designing low-level feature extraction algorithm. This paper elucidates a comprehensive study on recent technical updates in high-level semantic-based image retrieval. Major recent publications are enclosed during this survey covering different aspects of the research during this space, as well as low-level image feature extraction, similarity mensuration, and deriving high-level linguistics options. We have a tendency to establish 5 major classes of the progressive techniques in narrowing down the� linguistics gap�: (1) victimisation object metaphysics to outline high-level concepts; (2) victimisation machine learning ways to associate low-level options with question concepts; (3) victimisation relevance feedback to find out user�s intention; (4) generating linguistics template to support high-level image retrieval; (5) fusing the evidences from markup language text and also the visual content of pictures for computer network image retrieval. Other connected problems reminiscent of image workand retrieval performance evaluation are mentioned.

CBIR,Feedback,Machine Learning,semantic,Linguistic template

[1].Gui-Song Xia, Julie Delon, Yann Gousseau �Accurate Junction Detection and Characterization in Natural Images � International Journal of Computer Vision , Volume 106, Issue 1, pp 31�56 ,January 2014.
[2] Herv�J�gou ,Christian Wengert, MatthijsDouze, �Bag-of-colors for improved image search� Proceeding MM `11 Proceedings of the 19th ACM international conference on Multimedia Pages 1437-1440 , ACM New York, NY, USA �2011, ISBN: 978-1-4503-0616-4.
[3] .Dengxin Dai, Luc Van Gool , �Ensemble Projection for Semi-supervised Image Classification � ICCV `13 Proceedings of the 2013 IEEE International Conference on Computer Vision Pages 2072-2079 , IEEE Computer Society Washington, DC, USA �2013
[4] Mamta R. Nagpure, Suchita S. Mesakar, Sonali R. Raut and Vanita P.Lonkar, "Image Retrieval System with Interactive Genetic Algorithm Using Distance", International Journal of Computer Sciences and Engineering, Volume-02, Issue-12, Page No (109-113), Dec -2014,
[5] Dengxin Dai ; Wen Yang �Satellite Image Classification via Two-Layer Sparse Coding With Biased Image Representation� IEEE Geoscience and Remote Sensing Letters ,Volume: 8, Issue: 1,Page(s): 173 � 176, Jan. 2011 .
[6] Emma Izquierdo-Verdiguier ; Luis G�mez-Chova ; Lorenzo Bruzzone ; Gustavo Camps-Valls , � Semi-supervised Nonlinear Feature Extraction For Image Classification� Geoscience and Remote Sensing Symposium (IGARSS), 2012 IEEE International Date of Conference: 22-27, July 2012.
[7] J�gou H1, Douze M, Schmid C.�Product Quantization for Nearest Neighbor Search�, IEEE Trans Pattern Anal Mach Intell. 33(1):117-2, Jan 2011.
[8] L. Haldurai and V. Vinodhini, "Parallel Indexing on Color and Texture Feature Extraction using R-Tree for Content Based Image Retrieval", International Journal of Computer Sciences and Engineering, Volume-03, Issue-11, Page No (11-15), Nov -2015,
[9] Aasish Sipani, Phani Krishna and Sarath Chandra, "Content Based Image Retrieval Using Extended Local Tetra Patterns", International Journal of Computer Sciences and Engineering, Volume-02, Issue-11, Page No (11-17), Nov -2014
[10] Shraddha S.Katariya and Ulhas B.Shinde, "Review of Content Based Image Retrieval Using Low Level Features", International Journal of Computer Sciences and Engineering, Volume-04, Issue-03, Page No (91-97), Mar -2016, E-ISSN: 2347-2693