Segmentation Approach Towards PCM Images 1141
a large database of images with a large number of flocs and filaments, we would prefer edge-based algorithmto keep the
effect of failed segmentations minimal. However, for the segmentation of a single PCM image of AS, texture-based algorithm may perform better.
CONCLUSION
PCMimages have inherent artifacts of halos and shade-off. In addition to the artifacts, the flocs and filamentous bacteria contained in the AS samples have complex structure. The previously reported algorithms to segment PCMimages were specific to bone marrow cell or neurons, and cannot be used for AS images. We have explored nine different approaches for segmentation of AS PCM images. We assess the algo-
rithms for their effectiveness to segment free and attached filaments. The proposed edge and texture-based algorithms performed better compared with other approaches. For the segmentation of large databases of AS PCMimages, the edge- based algorithm is recommended. For few images of AS images, the texture-based algorithm is suggested when it is easier to detect the failed segmentation.
ACKNOWLEDGMENT
This work is sponsored by UTAR Research Fund (UTARRF) grant funded by Universiti Tunku Abdul Rahman, Malaysia (No. IPSR/RMC/UTARRF/2015-C1/L11). The authors also acknowledge the support of IndahWater Sdn. Bhd.,Malaysia for granting us access to their wastewater treatment plants.
REFERENCES
AMARAL, A.L., MESQUITA, D.P. & FERREIRA, E.C. (2013). Automatic identification of activated sludge disturbances and assessment of operational parameters. Chemosphere 91, 705–710.
BITTON, G. (2005). Wastewater Microbiology. Hoboken, NJ: John Wiley & Sons Inc.
BOZTOPRAK, H., ÖZBAY, Y., GÜÇLÜ,D.&KÜÇÜKHEMEK, M. (2015). Prediction of sludge volume index bulking using image analysis and neural network at a full-scale activated sludge plant. Desalination and Water Treatment 57, 17195–17205.
BRADHURST, C.J., BOLES,W.&XIAO, Y. (2008). Segmentation of Bone Marrow Stromal Cells in Phase Contrast Microscopy Images. In 23rd International Conference Image and Vision Computing, pp. 1–6. Christchurch, New Zealand: IEEE.
CAI, H., YANG, Z., CAO, X., XIA,W.&XU, X. (2014). A new iterative triclass thresholding technique in image segmentation. IEEE Trans Image Process 23, 1038–1046.
in Figure 12. In fact, only texture-based algorithm could detect the correct filaments. The TP remained zero for the other algorithms, resulting in unity FNR as depicted in Table 6. The edge and watershed detected false objects and Kittler could not detect a single object pixel. So, FNR is unity due to zero TP, and FPR is zero due to zero FP. It implies that only TN and FN are non-zero, detecting all the pixels as background for the image as shown in Figure 12f. We conclude from the results that if we want to segment
CENENS, C.,VAN BEURDEN, K.P., JENNÉ,R.&VAN IMPE, J.F. (2002). On the development of a novel image analysis technique to distinguish between flocs and filaments in activated sludge images. Water Sci Technol 46, 381–387.
DAS, K., MAJUMDER,A., SIEGENTHALER,M., KEIRSTEAD,H. & GOPI,M. (2011). Automated cell classification and visualization for analyzing remyelination therapy. Visual Comput 27,1055–1069.
DEBEIR, O., ADANJA, I.,WARZÉE, N., VAN HAM,P.&DECAESTECKER,C. (2008). Phase Contrast Image Segmentation by Weak Watershed Transform Assembly. In 5th IEEE International Symposium on Biomedical Imaging: from Nano to Macro. pp. 724–727. Paris, France: IEEE.
GONZALEZ, R.C., WOODS, R.L. & EDDINS, S.L. (2010). Digital Image Processing Using MATLAB. 2nd ed. New York, NY: McGraw Hill Education.
JACCARD,N., GRIFFIN, L.D., KESER,A.,MACOWN,R.J., SUPER,A., VERAITCH, F.S.&SZITA,N. (2014).Automated method for the rapid and precise estimation of adherent cell culture characteristics from phase contrast microscopy images. Biotechnol Bioeng 111, 504–517.
JENKINS, D., RICHARD, M.G. & DAIGGER, G.T. (2003). Manual on the Causes and Control of Activated Sludge Bulking, Foaming, and Other Solids Separation Problems. Hoboken, NJ: CRC Press.
JENNÉ, R., BANADDA, E.N., SMETS, I., DEURINCK,J. & IMPE, J. (2007). Detection of filamentous bulking problems: developing an image analysis system for sludge composition monitoring. Microsc Microanal 13,36–41.
JUNEAU, P.-M., GARNIER,A.&DUCHESNE, C. (2013). Selection and tuning of a fast and simple phase-contrast microscopy image segmentation algorithm for measuring myoblast growth kinetics in an automated manner. Microsc Microanal 19, 855–866.
KHAN, M.B., LEE, X.Y., NISAR, H.,NG, C.A., YEAP, K.H. &MALIK, A.S. (2015a). Digital image processing and analysis for activated sludge wastewater treatment. Adv Exp Med Biol 823, 227–248.
KHAN,M.B.,NISAR,H.,NG,C.A.&LO, P.K. (2016). Estimation of sludge volume index (SVI) using bright field activated sludge images. In IEEE International Instrumentation and Measurement Technology Conference,vol.I,pp. 407–411. Taipei, Taiwan: IEEE.
KHAN, M.B.,NISAR, H.,NG, C.A., LO, P.K.&YAP, V.V. (2015b). Local adaptive approach toward segmentation of microscopic images of activated sludge flocs. J Electron Imaging 24, 61102.
KHAN, M.B., NISAR, H., NG, C.A., LO, P.K. & YAP, V.V. (2017). Generalized classification modeling of activated sludge process based on microscopic image analysis. Environ Technol 39, 24–34.
KHAN, M.B., NISAR, H., NG, C.A., SALIH,Y.&MALIK, A.S. (2014). Segmentation assessment of activated sludge flocs at different magnifications for wastewater treatment. In 2014 IEEE International Conference on Control System, Computing and Engineering (ICCSCE), pp. 592–596. Penang, Malaysia: IEEE.
KITTLER,J.&ILLINGWORTH, J. (1986). Minimum error thresholding. Pattern Recognit 19,41–47.
KULKARNI, S. (ed.) (2012). Machine Learning Algorithms for Problem Solving in Computational Applications: Intelligent Techniques. Hershey, PA: IGI Global.
LEE, X.Y., KHAN, M.B., NISAR, H., HO, Y.K., NG, C.A. & MALIK, A.S.
(2014). Morphological analysis of activated sludge flocs and filaments. In IEEE Instrumentation and Measurement Technology Conference, pp. 1449–
1453.Montevideo, Uruguay: IEEE.
LLOYD, S. (1982). Least squares quantization in PCM. IEEE Trans Inf Theory 28, 129–137.
THEMATHWORKS, INC. (2015). MATLAB 8.5 R2015A. Natick, MA: The MathWorks, Inc.
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86 |
Page 87 |
Page 88 |
Page 89 |
Page 90 |
Page 91 |
Page 92 |
Page 93 |
Page 94 |
Page 95 |
Page 96 |
Page 97 |
Page 98 |
Page 99 |
Page 100 |
Page 101 |
Page 102 |
Page 103 |
Page 104 |
Page 105 |
Page 106 |
Page 107 |
Page 108 |
Page 109 |
Page 110 |
Page 111 |
Page 112 |
Page 113 |
Page 114 |
Page 115 |
Page 116 |
Page 117 |
Page 118 |
Page 119 |
Page 120 |
Page 121 |
Page 122 |
Page 123 |
Page 124 |
Page 125 |
Page 126 |
Page 127 |
Page 128 |
Page 129 |
Page 130 |
Page 131 |
Page 132 |
Page 133 |
Page 134 |
Page 135 |
Page 136 |
Page 137 |
Page 138 |
Page 139 |
Page 140 |
Page 141 |
Page 142 |
Page 143 |
Page 144 |
Page 145 |
Page 146 |
Page 147 |
Page 148 |
Page 149 |
Page 150 |
Page 151 |
Page 152 |
Page 153 |
Page 154 |
Page 155 |
Page 156 |
Page 157 |
Page 158 |
Page 159 |
Page 160 |
Page 161 |
Page 162 |
Page 163 |
Page 164 |
Page 165 |
Page 166 |
Page 167 |
Page 168 |
Page 169 |
Page 170 |
Page 171 |
Page 172 |
Page 173 |
Page 174 |
Page 175 |
Page 176 |
Page 177 |
Page 178 |
Page 179 |
Page 180
