Classification of Compressed Multichannel Images and Its Improvement

A task of classification of multichannel remote sensing images compressed in a lossy manner is considered. It is recalled that lossy compression usually leads to reduction of classification accuracy both in aggregate and for particular classes. Distortions due to compression are characterized by visual quality metric desired values of which can be provided at compression stage. Dependence of probability of correct classification on image quality and compression ratio is analyzed for several widely used classifiers using a test image composed of three component images of Landsat data in visible range. It is shown that different classifiers are sensitive to distortions introduced by lossy compression in sufficiently different degree. We also propose a way to combine classifiers' outputs to improve classification results.

[1]  Antonio J. Plaza,et al.  On the Impact of Lossy Compression on Hyperspectral Image Classification and Unmixing , 2011, IEEE Geoscience and Remote Sensing Letters.

[2]  Chih-Jen Lin,et al.  LIBLINEAR: A Library for Large Linear Classification , 2008, J. Mach. Learn. Res..

[3]  Nikolay N. Ponomarenko,et al.  Lossy compression of hyperspectral images based on noise parameters estimation and variance stabilizing transform , 2014 .

[4]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[5]  Nikolay N. Ponomarenko,et al.  Still image/video frame lossy compression providing a desired visual quality , 2015, Multidimensional Systems and Signal Processing.

[6]  Nikolay N. Ponomarenko,et al.  Processing of Hyperspectral Imagery for Contamination Detection in Urban Areas , 2011 .

[7]  Nikolay N. Ponomarenko,et al.  DCT Based High Quality Image Compression , 2005, SCIA.

[8]  Martin Sweeting,et al.  Image compression systems on board satellites , 2009 .

[9]  Chih-Jen Lin,et al.  A Practical Guide to Support Vector Classication , 2008 .

[10]  J. Astola,et al.  ON BETWEEN-COEFFICIENT CONTRAST MASKING OF DCT BASIS FUNCTIONS , 2007 .

[11]  Robert A. Schowengerdt,et al.  Remote sensing, models, and methods for image processing , 1997 .

[12]  Luciano Alparone,et al.  Near-lossless compression of 3-D optical data , 2001, IEEE Trans. Geosci. Remote. Sens..

[13]  R. Congalton.  Accuracy assessment and validation of remotely sensed and other spatial information , 2001 .

[14]  Joan Serra-Sagrista,et al.  Remote Sensing Data Compression , 2008 .

[15]  Vladimir Lukin,et al.  Improvement of Multichannel Image Classification by Combining Elementary Classifiers , 2019, 2019 IEEE International Scientific-Practical Conference Problems of Infocommunications, Science and Technology (PIC S&T).

[16]  E. Magli,et al.  A Tutorial on Image Compression for Optical Space Imaging Systems , 2014, IEEE Geoscience and Remote Sensing Magazine.

[17]  David W. Hosmer,et al.  Applied Logistic Regression , 1991 .