Rough Set and Otsu Approach based Hybrid Image Classification under Uneven Lighting Conditions

Rough Set and Otsu Approach based Hybrid Image Classification under Uneven Lighting Conditions
  IJETT-book-cover           
  
© 2021 by IJETT Journal
Volume-69 Issue-12
Year of Publication : 2021
Authors : Mamata Wagh, Pradipta Kumar Nanda
DOI :  10.14445/22315381/IJETT-V69I12P211

How to Cite?

Mamata Wagh, Pradipta Kumar Nanda, "Rough Set and Otsu Approach based Hybrid Image Classification under Uneven Lighting Conditions," International Journal of Engineering Trends and Technology, vol. 69, no. 12, pp. 92-102, 2021. Crossref, https://doi.org/10.14445/22315381/IJETT-V69I12P211

Abstract
Uneven lighting creates vagueness in pixel intensities of the real-world images. This poses a great challenge in the process of image classification. Further, image classification is the fundamental step in the robot vision system. In order to handle the vagueness created due to uneven lighting conditions, a Rough set and Otsu approach-based Hybrid (RSOH) image segmentation scheme is proposed in this research work. In the proposed RSOH scheme, the Otsu and rough set approaches are hybridized in such a way that the resultant hybridized scheme overcomes the limitations of the rough set and Otsu approach and makes use of advantages of both the approaches. Hence, RSOHmodel has the potential to give accurate image classification performance. Through the window growing approach, the image is partitioned into different sub-images, i. e., windows, and inside each window, the proposed RSOHimage segmentation scheme is employed to make the thresholding adaptive. The proposed scheme is compared with granular computing as well as non-granular techniques. The performance of the proposed technique is quantified using four performance indexes such as PM, DC, VI, and BHD. From the performance indexes, it is evident that the proposed RSOH scheme is found to be superior to the existing techniques.

Keywords
Image segmentation, Uneven lighting conditions, Adaptive windowing, Granular computing, Rough set, Otsu thresholding.

Reference
[1] Tao Wang, ZexuanJi, Quansen Sun, Qiang Chen, Qi Ge, and Jian Yang, Diffusive likelihood for interactive image segmentation, Pattern Recognition, 79 (2018) 440–451.
[2] A. Bhandary, A. Prabhuand, M. Basthikodi, and K. Chaitra, Early diagnosis of lung cancer using computer-aided detection via lung segmentation approach, International Journal of Engineering Trends and Technology, 69(5) (2021) 85–93.
[3] Weliwita, JAP Isuru, and S. C. Premaratne, Modeling abandoned object detection and recognition in real-time surveillance, International Journal of Engineering Trends and Technology, 69 (2) (2021) 188–193.
[4] D. Chakraborty, B. U. Shankar, and S. K. Pal, Granulation, rough entropy and spatiotemporal moving object detection, Applied Soft Computing, 13(9) (2013) 4001 – 4009.
[5] S. K. Pal, B. U. Shankar, and P. Mitra, Granular computing, rough entropy, and object extraction, Pattern Recognition Letters, 26 (16) (2005) 2509 – 2517.
[6] T. Deng and W. Xie, Granule-view based feature extraction and classification approach to color image segmentation in a manifold space, Neurocomputing, 99 (2013) 46 – 58.
[7] Qingming Huang, Wen Gao, and WenjianCai, Thresholding technique with adaptive window selection for uneven lighting image, Pattern Recognition Letters, Vol. 26(6) (2005) 801–808.
[8] MamataWagh, Pradipta Kumar Nanda, Fuzzy granulation and constraint neighborhood granulation structure for object classification in unevenly illuminated images, Applied Soft Computing, 74 (2019) 306–329.
[9] Qingmao Hu, ZujunHou, and WieslawLucjanNowinski, Supervised range-constrained thresholding, IEEE Transactions on Image Processing, 15(1) (2006) 228–240.
[10] P. Kanungo and P. K. Nanda and A. Ghosh, Parallel genetic algorithm-based adaptive thresholding for image segmentation under uneven lighting conditions, In proceedings of the IEEE International Conference on Systems, Man and Cybernetics, (2010) 1904–1911.
[11] N. Otsu, A threshold selection method from grey-level histogram, IEEE Trans. on Systems, Man and Cybernetics,. 9(1) (1979) 62–66.
[12] EkoPrasetyo, R. Dimas Adityo, NanikSuciati, and ChastineFatichah, Mango leaf image segmentation on hsv and ycbcr color spaces using otsu thresholding,3rdInternational Conference on Science and Technology - Computer (ICST), (2017) 99–103.
[13] Hasnae El Khoukhi, Youssef Filali, Ali Yahyaouy, My AbdelouahedSabri, and AbdellahAarab, A hardware implementation of otsu thresholding method for skin cancer image segmentation, International Conference on Wireless Technologies, Embedded and Intelligent Systems (WITS), (2019) 1–5.
[14] Patil Priyanka Vijay and N. C.Patil, Grayscale image segmentation using otsu thresholding optimal approach, Journal for Research, 2(05) (2016).
[15] Y. Feng, H. Zhao, Li Xiongfeiand X. Zang, A multi-scale 3d otsu thresholding algorithm for medical image segmentation, Digital Signal Processing, 60 (2017) 186–199.
[16] Ashish Kumar Bhandari, Immadisetty Vinod Kumar, and Kankanala Srinivas, Cuttlefish algorithm-based multilevel 3-d otsu function for color image segmentation, IEEE Transactions on Instrumentation and Measurement, 69(5) (2019) 1871-1880.
[17] AmilaAkagic, Emir Buza, Samir Omanovic, and AlmirKarabegovic. Pavement crack detection using otsu thresholding for image segmentation. 5 (2018).
[18] Ta Yang Goh, ShafrizaNishaBasah, HanizaYazid, Muhammad Juhairi Aziz Safar, and FathinulSyahir Ahmad Saad Performance analysis of image thresholding: Otsu technique, Measurement, 114 (2018) 298–307.
[19] Z. Pawlak, Rough Sets: Theoretical Aspects of Reasoning about Data. Theory and Decision Library D: System theory, knowledge engineering, and problem-solving. Springer Netherlands,( 2012).
[20] R. Jensen and Qiang Shen, Fuzzy-rough sets for descriptive dimensionality reduction, Proceedings of the IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), 1 (2002) 29–34.
[21] AvatharamGanivada, ShubhraSankar Ray, and Sankar K. Pal, Fuzzy rough granular self-organizing map and fuzzy rough entropy, Theoretical Computer Science, 466 (2012) 37 – 63.
[22] Abdullah Balamash, WitoldPedrycz, Rami Al-Hmouz, and Ali Morfeq, An expansion of fuzzy information granules through successive refinements of their information content and their use to system modeling, Expert Systems with Applications, 42(6) (2015) 2985–2997.
[23] S. K. Pal, S. K. Meher, and S. Dutta, Class-dependent rough fuzzy granular space, dispersion index and classification, Pattern Recognition, 45(7) (2012) 2690 – 2707.
[24] Ricardo L De Queiroz, Zhigang Fan, and Trac D Tran, Optimizing block-thresholding segmentation for multilayer compression of compound images, IEEE Transactions on Image Processing, 9(9) (2000) 1461–1471.
[25] Zizhao Zhang, Fuyong Xing, Xiaoshuang Shi, and Lin Yang, Revisiting graph construction for fast image segmentation Pattern Recognition, 78 (2018) 344–357.
[26] Khai-Yin Lim and RajeswariMandava, segmenting object with ambiguous boundary using information-theoretic rough sets, AEU-International Journal of Electronics and Communications, 77 (2017) 50–56.
[27] B. Wang, L. L. Chen, and M. Wang, Novel image segmentation method based on pcnn, Optik, 187 (2019) 193–197.
[28] Huizhu Pan, WanquanLiu, Ling Li, and Guanglu Zhou, A novel level set approach for image segmentation with landmark constraints, Optik, 182 (2019) 257–268.
[29] Yousheng Wang, XueGao, Yuting Wang, and Jinge Sun, Adventitia segmentation in intravascular ultrasound images based on improved snake algorithm, Optik, 241 (2021) 167-175.
[30] Xiaodong Long and Jian Sun, Image segmentation based on the minimum spanning tree with a novel weight, Optik, 221 (2020) 165308.
[31] A. Verma S. Arora, J. Acharya and P. K. Panigrahi. Multilevel thresholding for image segmentation through a fast statistical recursive algorithm, Pattern Recognition Letters, 29(2) (2008) 119–125.
[32] Zhi-Kai Huang and Kwok-Wing Chau, A new image thresholding method based on gaussian mixture model, Applied Mathematics and Computation, 205(2) (2008) 899–907.
[33] Sunil K. Sinha and Paul W. Fieguth. Segmentation of buried concrete pipe images, Automation in Construction, 15(1) (2006) 47–57.
[34] MiroslavBene?s and Barbara Zitova, Performance evaluation of image segmentation algorithms on microscopic image data, Journal of microscopy, 257(1) (2015) 65–85.