Open Access Open Access  Restricted Access Subscription or Fee Access

Clustered Mining and Controlling to Arial Surveillance over Federated Database Samples

P.L. Kishan Kumar Reddy, T.V. Rao, A. Ananda Rao


This paper presents a hierarchical approach for recognition of urban arial images in federated database systems [13]. The paper focus on the separation of urban and natural images from the arial images based on color localization by segmenting the arial images with its region of boundaries. The regions which are extracted have been classified using co-occurrence features for the recognition of segmented regions. Generally there are nine distinct features to be calculated for the recognition of Arial image. The approach which is developed predominantly uses two local features like pattern and texture of the image. The proposed approach will increase the performance of the system under distributed environment. During evaluation of the system different variant traffic conditions are considered.


Distributed Mining, Federated Database, Local Features, Spatial Arial Images.

Full Text:



R. Haralick, K. Shanmugam, I. Dinestein, “Textural Features for Image Classification”,IEEE Transaaction,vol-3, pp.610- 621.

K Kim, K. Jung, “Support Vector Machines for Texture Classification”, TPAMI-2,24(11),pp.1540-1552.

S. Perkins, N. Harvey, S. Brumby, K. Lacker, “Support Vector Machines for Broad Area Feature Classification in Remotely Sensed Images”, Proc. SPIE 4381, April 2001.

VVapnik, The nature of Statistical Learning Theory, Springer Verlag, 1995, pp273-297.

R. Walker, P. Jackway, Longstaff, “Improving Co-Occurrence Matrix Feature Discrimination”, DICTA '95,pp.643-648.

R. Walker, P. Jackway, I.D Longstaff, “Recent Developments in the Use of the Co-occurrence Matrix for texture Recognition”, ICDSP '97,pp.125-132.

J.Zhang,(2002) “Brief review of invariant texture analysis methods”, 35,pp. 735-747.

V Kovalev (1996) “Multidimensional Co-occurrence Matrices for Object Recognition and Matching,” vol.58,pp.187–197.

F. I. Alam, R. U. Faruqui, (2011) “Optimized C alculations of Haralick Texture Features”, Vol. 50 pp. 543-553.

A. S. Kurani, J. Frust, (2004) “Co-occurrence matrices for volumetric Data”, The 7th IASTED 2004,Hawaii, USA.

RHaralick(1979) “Statistical and structu ral approaches to texture” IEEE, pp.786-804.

Matthias Butenuth, Guido v. Gösseln, Michael Tiedge, Christian Heipke, Udo Lipeck, Monika Sester, “Integration of heterogeneous geospatial data in a federated database”, ISPRS Journal of Photogrammetry and Remote Sensing, Volume 62, Issue 5, October 2007,pp.328-346.

J. Leon Zhao, “Schema coordination in federated database management: a comparison with schema integration”, Decision Support Systems, Volume 20, Issue 3, July 1997, pp.243-257.

Yildiray Yalman, “Histogram based perceptual quality assessment method for color images”, Computer Standards & Interfaces, Volume 36, Issue 6, November 2014, pp. 899-908.

Wen Nung Lie, “An efficient threshold-evaluation algorithm for image segmentation based on spatial gray level co-occurrences”, Signal Processing, Volume 33, Issue 1, July 1993, pp.121-126.

C. Burges, “A Tutorial on Support Vector Machines for Pattern recognition”, Data Mining and Knoledge Discovery 2, 1998.


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.