Benchmarking techniques for evaluation of compression transform performance in ATR applications

Image compression is increasingly employed in applications such as medical imaging, for reducing data storage requirement, and Internet video transmission, to effectively increase channel bandwidth. Similarly, military applications such as automated target recognition (ATR) often employ compression to achieve storage and communication efficiencies, particularly to enhance the effective bandwidth of communication channels whose throughput suffers, for example, from overhead due to error correction/detection or encryption. In the majority of cases, lossy compression is employed due the resultant low bit rates (high compression ratio). However, lossy compression produces artifacts in decompressed imagery that can confound ATR processes applied to such imagery, thereby reducing the probability of detection (Pd) and possibly increasing the rate or number of false alarms (Rfa or Nfa). In this paper, the authors' previous research in performance measurement of compression transforms is extended to include (a) benchmarking algorithms and software tools, (b) a suite of error exemplars that are designed to elicit compression transform behavior in an operationally relevant context, and (c) a posteriori analysis of performance data. The following transforms are applied to a suite of 64 error exemplars: Visual Pattern Image Coding (VPIC [1]), Vector Quantization with a fast codebook search algorithm (VQ [2,3]), JPEG and a preliminary implementation of JPEG 2000 [4,5], and EBLAST [6-8]. Compression ratios range from 2:1 to 200:1, and various noise levels and types are added to the error exemplars to produce a database of 7,680 synthetic test images. Several global and local (e.g., featural) distortion measures are applied to the decompressed test imagery to provide a basis for rate-distortion and rate-performance analysis as a function of noise and compression transform type.

[1]  Dan E. Dudgeon,et al.  ATR Performance Modeling and Estimation , 2000, Digit. Signal Process..

[2]  Sean Dougherty,et al.  Edge Detector Evaluation Using Empirical ROC Curves , 2001, Comput. Vis. Image Underst..

[3]  C.-Y. Lee,et al.  A JPEG-like texture compression with adaptive quantization for 3D graphics application , 2002, The Visual Computer.

[4]  Image compression using wavelets and JPEG 2000 : A Tutorial , 2003 .

[5]  Michael T. Orchard,et al.  A deblocking algorithm for JPEG compressed images using overcomplete wavelet representations , 1997, IEEE Trans. Circuits Syst. Video Technol..

[6]  Bao Zheng,et al.  Group-normalized wavelet packets for target extraction , 1996, Proceedings of Third International Conference on Signal Processing (ICSP'96).

[7]  J. O’Sullivan.  Performance Complexity Study of Several Approaches to Automatic Target Recognition from SAR Images , 2002 .

[8]  H. G. Lewis,et al.  Multiresolution image decomposition for processing reconnaissance images , 1992, Defense, Security, and Sensing.

[9]  J. Kelso,et al.  Fractal time and 1/ f spectra in dynamic images and human vision , 2001 .

[10]  Yujing Zeng,et al.  Piecewise linear approach: a new approach in automatic target recognition , 2000, SPIE Defense + Commercial Sensing.

[11]  Bir Bhanu,et al.  Predicting an upper bound on SAR ATR performance , 2001 .

[12]  Gerhard X. Ritter,et al.  Performance evaluation of data compression transforms for underwater imaging and object recognition , 1997, Oceans '97. MTS/IEEE Conference Proceedings.

[13]  Joseph N. Wilson,et al.  Handbook of computer vision algorithms in image algebra , 1996 .

[14]  Michael W. Marcellin,et al.  Universal trellis coded quantization , 1999, IEEE Trans. Image Process..

[15]  Alan C. Bovik,et al.  Visual pattern image coding , 1990, IEEE Trans. Commun..

[16]  Gregory K. Wallace,et al.  The JPEG still picture compression standard , 1992 .

[17]  Truong Q. Nguyen,et al.  Blocking artifact free inverse discrete cosine transform , 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

[18]  R. Logeswaran,et al.  Performance Survey of Several Lossless Compression Algorithms for Telemetry Applications , 2001 .

[19]  Peter Sussner,et al.  Morphological bidirectional associative memories , 1999, Neural Networks.

[20]  S. Lawson,et al.  Image compression using wavelets and JPEG2000: a tutorial , 2002 .

[21]  Mihai Datcu,et al.  Histogram analysis of JPEG compressed images as an aid in image deblocking , 1995, Proceedings DCC '95 Data Compression Conference.

[22]  Gerhard X. Ritter,et al.  Center-surround filters for the detection of small targets in cluttered multispectral imagery: background and filter design , 1995, Defense, Security, and Sensing.

[23]  Vivian George,et al.  Quantifying performance of mine detectors with fewer than 10,000 targets , 1997, Defense, Security, and Sensing.

[24]  Koeng Mo Sung,et al.  Two Fast Bearest Neighbor Searching Algorithms for Vector Quantization , 2001 .

[25]  Sethuraman Panchanathan,et al.  A lifting based system for optimal image compression in the wavelet domain , 2002, 2002 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[26]  Sean Dougherty,et al.  Edge detector evaluation using empirical ROC curves , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[27]  Ali M. Reza,et al.  Combined edge crispiness and statistical differencing for deblocking JPEG compressed images , 2001, IEEE Trans. Image Process..

[28]  S. Mallat.  A wavelet tour of signal processing , 1998 .

[29]  Rama Chellappa,et al.  Experimental Evaluation of FLIR ATR Approaches - A Comparative Study , 2001, Comput. Vis. Image Underst..

[30]  Mark S. Schmalz.  Processing of compressed imagery: basic theory with visual pattern image coding (VPIC) and block truncation coding (BTC) transformations , 1996, Defense, Security, and Sensing.

[31]  Gerhard X. Ritter,et al.  EBLAST: efficient high-compression image transformation: I. Background and theory , 1999, Optics + Photonics.

[32]  Kai Lin,et al.  Feature-coding-based algorithm for high-fidelity image compression , 1999, Optics & Photonics.

[33]  K. H. Barratt.  Digital Coding of Waveforms , 1985 .

[34]  Allen Gersho,et al.  Vector quantization and signal compression , 1991, The Kluwer international series in engineering and computer science.

[35]  M. Frydrych,et al.  Arithmetic coding with sliding window for control-point based image compression , 1999 .

[36]  Gerhard X. Ritter,et al.  Center-surround filters for the detection of small targets in cluttered multispectral imagery: analysis of errors and filter performance , 1995, Defense, Security, and Sensing.

[37]  Chin-Chen Chang,et al.  A fast LBG codebook training algorithm for vector quantization , 1998 .

[38]  Gerhard X. Ritter,et al.  EBLAST: an efficient high-compression image transformation 3. application to Internet image and video transmission , 2001, SPIE Optics + Photonics.

[39]  Alan H. Lettington,et al.  Nonlinear image restoration algorithm with artifact reduction , 1994, Optics & Photonics.

[40]  Thrasyvoulos N. Pappas,et al.  Perceptual criteria for image quality evaluation , 2005 .

[41]  Steven Schmidt,et al.  ATR discrimination-SNR for HRR assuming χ2 model of RCS variability , 2001, SPIE Defense + Commercial Sensing.

[42]  Gerhard X. Ritter,et al.  EBLAST: Efficient high-compression image transformation: II. Implementation and results , 2000, SPIE Optics + Photonics.

[43]  Mark S. Schmalz.  Processing of compressed imagery: multitarget image processing with VPIC-, BTC-, VQ-, and JPEG-compressed imagery , 1996, Defense, Security, and Sensing.

[44]  Kuldip K. Paliwal,et al.  Fast nearest-neighbor search based on Voronoi projections and its application to vector quantization encoding , 1999, IEEE Trans. Speech Audio Process..

[45]  Ahmet M. Eskicioglu,et al.  Quality measurement for monochrome compressed images in the past 25 years , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

[46]  Truong Q. Nguyen,et al.  Wavelets and filter banks , 1996 .

[47]  P. Vaidyanathan.  Multirate Systems And Filter Banks , 1992 .

[48]  Frank M. Caimi,et al.  Spatial exemplars and metrics for characterizing image compression transform error , 2001, SPIE Optics + Photonics.