Improved maximum average correlation height filter with adaptive log base selection for object recognition

Sensitivity to the variations in the reference image is a major concern when recognizing target objects. A combinational framework of correlation filters and logarithmic transformation has been previously reported to resolve this issue alongside catering for scale and rotation changes of the object in the presence of distortion and noise. In this paper, we have extended the work to include the influence of different logarithmic bases on the resultant correlation plane. The meaningful changes in correlation parameters along with contraction/expansion in the correlation plane peak have been identified under different scenarios. Based on our research, we propose some specific log bases to be used in logarithmically transformed correlation filters for achieving suitable tolerance to different variations. The study is based upon testing a range of logarithmic bases for different situations and finding an optimal logarithmic base for each particular set of distortions. Our results show improved correlation and target detection accuracies.

[1]  Carl F. R. Weiman,et al.  Logarithmic spiral grids for image-processing and display , 1979 .

[2]  Carl F. R. Weiman,et al.  3-D Sensing With Polar Exponential Sensor Arrays , 1988, Defense, Security, and Sensing.

[3]  Carl F. R. Weiman,et al.  Exponential Sensor Array Geometry And Simulation , 1988, Defense, Security, and Sensing.

[4]  B. Kumar,et al.  Performance measures for correlation filters. , 1990, Applied optics.

[5]  P Refregier.  Optimal trade-off filters for noise robustness, sharpness of the correlation peak, and Horner efficiency. , 1991, Optics letters.

[6]  Giulio Sandini,et al.  Active vision based on space-variant sensing , 1991 .

[7]  B. V. Vijaya Kumar,et al.  Unconstrained correlation filters. , 1994, Applied optics.

[8]  Tien-Hsin Chao,et al.  MACH filter synthesizing for detecting targets in cluttered environment for grayscale optical correlator , 1999, Defense, Security, and Sensing.

[9]  B. V. K. Vijaya Kumar,et al.  Correlation Pattern Recognition , 2002 .

[10]  Chris Chatwin,et al.  Position-, rotation-, scale-, and orientation-invariant multiple object recognition from cluttered scenes , 2006 .

[11]  Naveen K Nishchal,et al.  Wavelet-modified maximum average correlation height filter for rotation invariance that uses chirp encoding in a hybrid digital-optical correlator. , 2006, Applied optics.

[12]  C. Chatwin,et al.  Object Detection and Recognition in Cluttered Scenes Using Fully Scale and In-Plane Invariant Synthetic Discriminant Function Filters , 2007 .

[13]  Chris Chatwin,et al.  FULLY SCALE AND IN-PLANE INVARIANT SYNTHETIC DISCRIMINANT FUNCTION BANDPASS DIFFERENCE OF GAUSSIAN COMPOSITE FILTER FOR OBJECT RECOGNITION AND DETECTION IN STILL IMAGES , 2009 .

[14]  Philip Birch,et al.  Approximate bandpass and frequency response models of the difference of Gaussian filter , 2010 .

[15]  Alex Pappachen James,et al.  Nearest Neighbor Classifier Based on Nearest Feature Decisions , 2012, Comput. J..

[16]  R. Young,et al.  Logarithmically Pre-processed EMACH Filter for Enhanced Performance in Target Recognition , 2013 .

[17]  Seemab Latif,et al.  Synthesis of an adaptive CPR filter for identification of vehicle make & type , 2014, 2014 National Software Engineering Conference.

[18]  Vishnu Naresh Boddeti,et al.  Recent advances in correlation filter theory and application , 2014, Defense + Security Symposium.

[19]  Rupert Young,et al.  Human detection in sensitive security areas through recognition of omega shapes using MACH filters , 2015, Defense + Security Symposium.

[20]  Chris R. Chatwin,et al.  Sensor Geometry and Sampling Methods for Space-Variant Image Processing , 2002, Pattern Analysis and Applications.