WECIA Graph: Visualization of Classification Performance Dependency on Grayscale Conversion Setting

Pavel Skrabanek; Sule Yildirim Yayilgan

doi:10.13164/mendel.2018.2.041

Pavel Skrabanek Brno University of Technology, Faculty of Mechanical Engineering, Institute of Automation and Computer Science
Sule Yildirim Yayilgan Norwegian University of Science and Technology, Department of Information Security and Communication Technology

DOI: https://doi.org/10.13164/mendel.2018.2.041

Keywords: computer vision, generic object categorization, grayscale conversion, weighted means grayscale conversion, classification, performance evaluation, data visualization

Abstract

Grayscale conversion is a popular operation performed within image pre-processing of many computer vision systems, including systems aimed at generic object categorization. The grayscale conversion is a lossy operation. As such, it can signicantly in uence performance of the systems. For generic object categorization tasks, a weighted means grayscale conversion proved to be appropriate. It allows full use of the grayscale
conversion potential due to weighting coefficients introduced by this conversion method. To reach a desired performance of an object categorization system, the weighting coefficients must be optimally setup. We demonstrate that a search for an optimal setting of the system must be carried out in a cooperation with an expert. To simplify the expert involvement in the optimization process, we propose a WEighting Coefficients Impact Assessment (WECIA) graph. The WECIA graph displays dependence of classication performance on setting of the weighting coefficients for one particular setting of remaining adjustable parameters. We point out a fact that an expert analysis of the dependence using the WECIA graph allows identication of settings leading to undesirable performance of an assessed system.

References

Aubin, V., Mora, M.: A new descriptor for person identity verication based on handwritten strokes off-line analysis. Expert Systems with Applications 89, 241–253 (2017). DOI https://doi.org/10.1016/j.eswa.2017.07.039

Bankhead, P., Scholeld, C.N., McGeown, J.G., Curtis, T.M.: Fast retinal vessel detection and measurement using wavelets and edge location renement. PLOS ONE 7(3), 1–12 (2012). DOI 10.1371/journal.pone.0032435

Barbu, T.: Pedestrian detection and tracking using temporal dierencing and HOG features. Computers & Electrical Engineering 40(4), 1072–1079 (2014). DOI http://dx.doi.org/10.1016/j.compeleceng.2013.12.004

Bergstra, J., Bengio, Y.: Random search for hyper-parameter optimization. The Journal of Machine Learning Research 13, 281–305 (2012)

Burgos-Artizzu, X.P., Ribeiro, A., Tellaeche, A., Pajares, G., Fernandez-Quintanilla, C.: Analysis of natural images processing for the extraction of agricultural elements. Image and Vision Computing 28(1), 138–149 (2010). DOI http://dx.doi.org/10.1016/j.imavis.2009.05.009

Coope, I.D., Price, C.J.: On the convergence of grid-based methods for unconstrained optimization. SIAM Journal on Optimization 11(4), 859–869 (2001)

Cui, M., Hu, J., Razdan, A., Wonka, P.: Color-to-gray conversion using ISOMAP. The Visual Computer 26(11), 1349–1360 (2010). DOI 10.1007/s00371-009-0412-7

Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE Computer Society Conference on, vol. 1, pp. 886–893 (2005)

Forman, G., Scholz, M.: Apples-to-apples in cross-validation studies: Pitfalls in classier performance measurement. SIGKDD Explor. Newsl. 12(1), 49–57 (2010). DOI 10.1145/1882471.1882479

Gauman, K., Leibe, B.: Visual Object Recognition. Synthesis Lectures on Artificial Intelligence and Machine Learning. Morgan & Claypool Publishers (2010)

Grundland, M., Dodgson, N.A.: Decolorize: Fast, contrast enhancing, color to grayscale conversion. Pattern Recognition 40(11), 2891–2896 (2007)

Gunes, A., Kalkan, H., Durmus, E.: Optimizing the color-to-grayscale conversion for image classification. Signal, Image and Video Processing 10(5), 853–860 (2016). DOI 10.1007/s11760-015-0828-7

Howarth, R.J.: Sources for a history of the ternary diagram. The British Journal for the History of Science 29, 337–356 (1996)

Hsin, C., Le, H.N., Shin, S.J.: Color to grayscale transform preserving natural order of hues. In: Proceedings of the 2011 International Conference on Electrical Engineering and Informatics, pp. 1–6 (2011). DOI 10.1109/ICEEI.2011.6021794

ITU-R Recommendation BT.601: Studio encoding parameters of digital television for standard 4:3 and wide screen 16:9 aspect ratios (2011)

Jin, T., Hou, X., Li, P., Zhou, F.: A novel method of automatic plant species identification using sparse representation of leaf tooth features. PLOS ONE 10(10), 1–20 (2015). DOI 10.1371/journal.pone.0139482

Kanan, C., Cottrell, G.W.: Color-to-Grayscale: Does the Method Matter in Image Recognition? PLoS ONE 7(1), 1–7 (2012)

Krig, S.: Computer Vision Metrics: Survey, Taxonomy, and Analysis, 1st edn. Apress, Berkely, CA, USA (2014)

Leondes, C.: Image Processing and Pattern Recognition, vol. 5. Academic Press (1998)

Lionnie, R., Alaydrus, M.: A comparison of human skin color detection for biometrie identification. In: 2017 International Conference on Broadband Communication, Wireless Sensors and Powering (BCWSP), pp. 1–5 (2017). DOI 10.1109/BCWSP.2017.8272565

Pennisi, A., Bloisi, D.D., Nardi, D., Giampetruzzi, A.R., Mondino, C., Facchiano, A.: Skin lesion image segmentation using delaunay triangulation for melanoma detection. Computerized Medical Imaging and Graphics 52, 89 { 103 (2016). DOI http://dx.doi.org/10.1016/j.compmedimag.2016.05.002

Powers, D.M.W.: Evaluation: From precision, recall and f-measure to ROC, informedness, markedness & correlation. Journal of Machine Learning Technologies 2(1), 37–63 (2011)

Raghuwanshi, G., Tyagi, V.: Texture image retrieval using adaptive tetrolet transforms. Digital Signal Processing 48, 50–57 (2016). DOI http://dx.doi.org/10.1016/j.dsp.2015.09.003

Rasche, K., Geist, R., Westall, J.: Re-coloring images for gamuts of lower dimension. Computer Graphics Forum 24(3), 423–432 (2005)

Sokolova, M., Lapalme, G.: A systematic analysis of performance measures for classification tasks. Information Processing & Management 45(4), 427–437 (2009). DOI https://doi.org/10.1016/j.ipm.2009.03.002

Solomon, C., Breckon, T.: Fundamentals of Digital Image Processing: A Practical Approach with Examples in Matlab, 1st edn. Wiley Publishing (2011)

Stewart, C.V.: Robust parameter estimation in computer vision. SIAM Review 41(3), 513–537 (1999)

Theune, U.: Ternary plots. https://www.mathworks.com/matlabcentral/leexchange/7210-ternary-plots (2002-2005)

Tirui Wu, A.T.: Color-to-grayscale conversion through weighted multiresolution channel fusion. Journal of Electronic Imaging 23, (2014). DOI 10.1117/1.JEI.23.4.043004

Cadik, M.: Perceptual evaluation of color-to-grayscale image conversions. Computer Graphics Forum 27(7), 1745–1754 (2008). DOI 10.1111/j.1467-8659.2008.01319.x

Skrabanek, P., Dolezel, P.: On reporting performance of binary classiers. Scientic Papers of the University of Pardubice, Series D XXIV, 181–192 (2017)

Skrabanek, P., Dolezel, P.: Robust grape detector based on SVMs and HOG features. Computational Intelligence and Neuroscience 2017, 1–17 (2017). DOI 10.1155/2017/3478602

Skrabanek, P., Majerik, F.: Simplified version of white wine grape berries detector based on SVM and HOG features. In: Proceedings of the 5th Computer Science On-line Conference 2016 (CSOC2016). Springer International Publishing (2016). In press

Skrabanek, P., Majerik, F.: Detection of grapes in natural environment using HOG features in low resolution images. Journal of Physics: Conference Series 870(1), 012,004 (2017)

Skrabanek, P., Runarsson, T.P.: Detection of grapes in natural environment using support vector machine classier. In: Proceedings of the 21st International Conference on Soft Computing MENDEL 2015, pp. 143–150. Brno University of Technology, Brno, Czech Republic (2015)

Wright, H.: Introduction to scientific visualization. Springer (2007)

Yoo, H., Yang, U., Sohn, K.: Gradient-enhancing conversion for illumination-robust lane detection. IEEE Transactions on Intelligent Transportation Systems 14(3), 1083–1094 (2013)