Image Segmentation on Convolutional Neural Network (CNN) using Some New Activation Functions
DOI:
https://doi.org/10.26713/cma.v14i2.2152Keywords:
Convolutional Neural Network (CNN), Activation function, NewSigmoid, Tansigmoid, Training algorithm, Relu, Adam optimizationAbstract
Image segmentation means subdividing the image into different objects. We use different methods for the segmentation of images. For getting different objects from a single image, we generally apply old methods, such as Fuzzy C-means, and K-means clustering techniques. In the case of getting different objects from huge amounts of image datasets, we generally apply the CNN technique. The Activation Function (AF) plays a major role during the segmentation of images through CNN. We can increase the power of CNN using activation functions. Generally, the exponential activation function is used for very complex and non-separable types of problems. So, in this paper, we segment the triangle and CamVid datasets on CNN using NewSigmoid AF and root2Sigmoid AF. Both AFs are exponential activation functions. We made a 12-layer CNN for the triangle segment and a 13-layer CNN for the CamVid segment. After that, we compare four activation functions on both CNNs. These activation functions are NewSigmoid, Relu, root2sigmoid, and Tanh. On the triangle image dataset, we have achieved global accuracy of 96.29% through NewSigmoid AF, 95.77% through Relu AF, 97.02% through root2sigmoid AF, and 96.47% through Tanh AF. On the CamVid dataset, we have achieved global accuracy of 93.97% through NewSigmoid AF, 94.01% through Relu AF, 94.19% through root2sigmoid AF, and 94.13% through Tanh AF. We also check the validation accuracy of the CamVid dataset. We take 10% of images for validation purpose. For the same dataset and same CNN network, we found validation accuracy of relu is 96.04%, root2simgoid is 96.26%, tanh is 96.20% and NewSimgois is 96.26%. Therefore, we can say that the root2sigmoid AF gives a better result as compared with NewSigmoid, Relu, and Tanh AFs.
Downloads
References
S. Adhikary, S. P. Tiwari and S. Banerjee, Realtime oil spill detection by image processing of synthetic aperture radar data, 2022 IEEE International Conference on Electronics, Computing and Communication Technologies (CONECCT), Bangalore, India (2022), pp. 1 – 5, DOI: 10.1109/CONECCT55679.2022.9865768.
H. Alghodhaifi, A. Alghodhaifi and M. Alghodhaifi, Predicting invasive ductal carcinoma in breast histology images using convolutional neural network, in: IEEE National Aerospace and Electronics Conference (NAECON 2019), Dayton, OH, USA (2019), pp. 374 – 378, DOI: 10.1109/NAECON46414.2019.9057822.
A. Amer, T. Lambrou and X. Ye, MDA-Unet: A multi-scale dilated attention U-net for medical image segmentation, Applied Sciences 12(7) (2022), 3676, DOI: 10.3390/app12073676.
M. A. Anjum, J. Amin, M. Sharif, H. U. Khan, M. S. A. Malik and S. Kadry, Deep semantic segmentation and multi-class skin lesion classification based on convolutional neural network, IEEE Access 8 (2020), 129668 – 129678, DOI: 10.1109/ACCESS.2020.3009276.
R. Avenash and P. Viswanath, Semantic segmentation of satellite images using a modified CNN with hard-Swish activation function, in: Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, Vol. 4 (2019), 413 – 420, Prague, Czech Republic, DOI: 10.5220/0007469604130420.
A. Bal, M. Banerjee, A. Chakrabarti and P. Sharma, MRI brain tumor segmentation and analysis using rough-fuzzy c-means and shape based properties, Journal of King Saud University-Computer and Information Sciences 34(2) (2022), 115 – 133, DOI: 10.1016/j.jksuci.2018.11.001.
J. Canny, A computational approach to edge detection, IEEE Transactions on Pattern Analysis and Machine Intelligence PAMI-8(6) (1986), 679 – 698, DOI: 10.1109/TPAMI.1986.4767851.
J. Chen, Y. Zhang, F. Ma and Z. Tan, EB-LG module for 3D point cloud classification and segmentation, IEEE Robotics and Automation Letters 8(1) (2023), 160 – 167, DOI: 10.1109/LRA.2022.3223558.
E. R. Davies, Computer Vision: Principles, Algorithms, Applications, Learning, 5th edition, Academic Press, 858 pages (2018), DOI: 10.1016/C2015-0-05563-0.
A. J. Deo, A. Sahoo, S. K. Behera and D. P. Das, Iron ore pellet size analysis: A machine learning-based image processing approach, IEEE Industry Applications Magazine 29(1) (2023), 67 – 79, DOI: 10.1109/MIAS.2022.3214020.
I. Despotovic, B. Goossens and W. Philips, MRI segmentation of the human brain: Challenges, methods, and applications, Computational and Mathematical Methods in Medicine 2015 (2015), Article ID 450341, 23 pages, DOI: 10.1155/2015/450341.
R. C. Gonzalez and R. E. Woods, Digital Image Processing, 3rd edition, Pearson Education, Inc., New Jersey, xxii + 954 pages (2008), URL: https://dl.ebooksworld.ir/motoman/Digital.Image.Processing.3rd.Edition.www.EBooksWorld.ir.pdf.
R. C. Gonzalez, R. E. Woods and S. L. Eddins, Digital Image Processing using MATLAB, 2nd edition, Tata McGraw-Hill (2010), URL: https://in.mathworks.com/academia/books/digital-image-processing-using-matlab-gonzalez-in.html.
I. Goodfellow, Y. Bengio and A. Courville, Deep Learning, MIT Press, 800 pages (2016), URL: https://mitpress.mit.edu/9780262035613/deep-learning.
S. Gu, K-means image segmentation based on improved grey wolf optimizater, in: 3rd International Conference on Electronic Communication and Artificial Intelligence (IWECAI 2022), Zhuhai, China (2022), pp. 467 – 471, DOI: 10.1109/IWECAI55315.2022.00096.
V. Hemamalini, S. Rajarajeswari, S. Nachiyappan, M. Sambath, T. Devi, B. K. Singh and A. Raghuvanshi, Food quality inspection and grading using efficient image segmentation and machine learning-based system, Journal of Food Quality 2022 (2022), Article ID 5262294, 6 pages, DOI: 10.1155/2022/5262294.
D. J. Ho and Q. Lin, Person segmentation using convolutional neural networks with dilated convolutions, in: Proceedings of the IS&T International Symposium on Electronic Imaging: Imaging and Multimedia Analytics in a Web and Mobile World, (2018), 455-1 – 455-7, DOI: 10.2352/ISSN.2470-1173.2018.10.IMAWM-455.
F. Hoseini and A. Shahbahrami, An efficient implementation of fuzzy C-means and watershed algorithms for MRI segmentation, in: 8th International Symposium on Telecommunications (IST2016), Tehran, Iran (2016), pp. 178 – 184, DOI: 10.1109/ISTEL.2016.7881806.
A. Huang, Q. Wang, L. Jiang and J. Zhang, Automatic segmentation of median nerve in ultrasound image by a combined use of u-net and VGG16, in: IEEE International Ultrasonics Symposium (IUS 2021), Xi’an, China (2021), pp. 1 – 4, DOI: 10.1109/IUS52206.2021.9593861.
T. Kanungo, D. M. Mount, N. S. Netanyahu, C. D. Piatko, R. Silverman and A. Y. Wu, An efficient k-means clustering algorithm: analysis and implementation, IEEE Transactions on Pattern Analysis and Machine Intelligence 24(7) (2002), 881 – 892, DOI: 10.1109/TPAMI.2002.1017616.
J. Kim and Y. S. Heo, Efficient semantic segmentation using spatio-channel dilated convolutions, IEEE Access 7 (2019), 154239 – 154252, DOI: 10.1109/ACCESS.2019.2949076.
D. S. Kim, Y. H. Kim and K. R. Park, Semantic segmentation by multi-scale feature extraction based on grouped dilated convolution module, Mathematics 9(9) (2021), 947, DOI: 10.3390/math9090947.
A. Kumar and S. S. Sodhi, Comparative analysis of fuzzy c-means and k-means clustering in the case of image segmentation, in: 8th International Conference on Computing for Sustainable Global Development (INDIACom 2021), New Delhi, India (2021), pp. 194 – 200, URL: https://ieeexplore.ieee.org/document/9441121.
S. Kumawat and S. Raman, Local phase U-net for fundus image segmentation, in: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2019), Brighton, UK (2019), pp. 1209 – 1213, DOI: 10.1109/ICASSP.2019.8683390.
Y. Li, J. Shi and Y. Li, Real-time semantic understanding and segmentation of urban scenes for vehicle visual sensors by optimized DCNN algorithm, Applied Sciences 12(15) (2022), 7811, DOI: 10.3390/app12157811.
J. Li, L. Su, J. Huang, Y. Ma, L. Liu and K. Luo, A modified pulse coupled neural network model for nut image segmentation, in: Chinese Automation Congress (CAC 2018), Xi’an, China (2018), pp. 2554 – 2558, DOI: 10.1109/CAC.2018.8623754.
J. Liu, Z. Wu, Y. Hong, G. Zhong and M. Liu, Image semantic segmentation based on dilated convolution and multi-layer feature fusion, in: IEEE International Conference on Artificial Intelligence and Industrial Design (AIID 2021), Guangzhou, China (2021), pp. 339 – 342, DOI: 10.1109/AIID51893.2021.9456560.
J. MacQueen, Some methods for classification and analysis of multivariate observations, Berkeley Symposium on Mathematical Statistics and Probability 1967 (1967), 281 – 297, URL: https://projecteuclid.org/ebooks/berkeley-symposium-on-mathematical-statistics-and-probability/Proceedings-of-the-Fifth-Berkeley-Symposium-on-Mathematical-Statistics-and/chapter/Some-methods-for-classification-and-analysis-of-multivariate-observations/bsmsp/1200512992?tab=ChapterArticleLink.
L. Man, H. Wu, J. Man, X. Shi, H. Wang and Q. Liang, Machine learning for liver and tumor segmentation in ultrasound based on labeled CT and MRI images, in: IEEE International Ultrasonics Symposium (IUS 2022), Venice, Italy (2022), pp. 1 – 4, DOI: 10.1109/IUS54386.2022.9957634.
J. Mao, Z. Cao, H. Wang, B. Zhang, Z. Guo and W. Niu, Agricultural robot navigation path recognition based on K-means algorithm for large-scale image segmentation, 2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA), Xi’an, China (2019), pp. 1233 – 1237, DOI: 10.1109/ICIEA.2019.8834296.
D. Mehta, A. Skliar, H. B. Yahia, S. Borse, F. Porikli, A. Habibian and T. Blankevoort, Simple and efficient architectures for semantic segmentation, in: IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2022), New Orleans, LA, USA, (2022), 2627 – 2635, DOI: 10.1109/CVPRW56347.2022.00296.
S. Piao and J. Liu, Accuracy improvement of UNet based on dilated convolution, Journal of Physics: Conference Series 1345(5) (2019), 052066, DOI: 10.1088/1742-6596/1345/5/052066.
Y. Qin, X. Wang and J. Zou, The optimized deep belief networks with improved logistic sigmoid units and their application in fault diagnosis for planetary gearboxes of wind turbines, IEEE Transactions on Industrial Electronics 66(5) (2019), 3814 – 3824, DOI: 10.1109/TIE.2018.2856205.
A. A. Rafique, A. Jalal and A. Ahmed, Scene understanding and recognition: statistical segmented model using geometrical features and gaussian Naïve bayes, 2019 International Conference on Applied and Engineering Mathematics (ICAEM), Taxila, Pakistan (2019), pp. 225 – 230, DOI: 10.1109/ICAEM.2019.8853721.
S. Saifullah, R. Drezewski, A. Khaliduzzaman, L. K. Tolentino and R. Ilyos, K-means segmentation based-on lab color space for embryo detection in incubated egg, Jurnal Ilmiah Teknik Elektro Komputer dan Informatika 8(2) (2022), 175 – 185, DOI: 10.26555/jiteki.v8i2.23724.
S. Samaddar and A. R. Reddy, Comparative study of image segmentation techniques on chronic kidney diseases, International Journal of Pure and Applied Mathematics 118(14) (2018), 235 – 239, URL: https://acadpubl.eu/jsi/2018-118-14-15/articles/14/34.pdf.
R. Sumathi, A. Saravanan, P. Nagaraj and R. Venkatesh, Detection of tumor region in MRI images using kernel fuzzy c means with PSO, in: International Conference on Computer Communication and Informatics (ICCCI 2022), Coimbatore, India (2022), pp. 1 – 6, DOI: 10.1109/ICCCI54379.2022.9741007.
Z. Tian, B. Zhang, H. Chen and C. Shen, Instance and Panoptic segmentation using conditional convolutions, IEEE Transactions on Pattern Analysis and Machine Intelligence 45(1) (2023), 669 – 680, DOI: 10.1109/TPAMI.2022.3145407.
L. Wang, R. Li, C. Duan, C. Zhang, X. Meng and S. Fang, A novel transformer based semantic segmentation scheme for fine-resolution remote sensing images, IEEE Geoscience and Remote Sensing Letters 19 (2022), Article number 6506105, DOI: 10.1109/LGRS.2022.3143368.
X. Wang, Y. Qin, Y. Wang, S. Xiang and H. Chen, ReLTanh: An activation function with vanishing gradient resistance for SAE-based DNNs and its application to rotating machinery fault diagnosis, Neurocomputing 363 (2019), 88 – 98, DOI: 10.1016/j.neucom.2019.07.017.
J. Wang, Z. Xu and Y. Liu, Texture-based segmentation for extracting image shape features, 2013 19th International Conference on Automation and Computing, London, UK (2013), pp. 1 – 6, URL: https://ieeexplore.ieee.org/document/6662034.
Y. Wei, H. Xiao, H. Shi, Z. Jie, J. Feng and T. S. Huang, Revisiting dilated convolution: a simple approach for weakly- and semi-supervised semantic segmentation, in: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA (2018), pp. 7268 – 7277, DOI: 10.1109/CVPR.2018.00759.
Y. Zhang, M. Brady and S. Smith, Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm, IEEE Transactions on Medical Imaging 20(1) (2001), 45 – 57, DOI: 10.1109/42.906424.
J. Zhang, X. Ding, D. Hu and Y. Jiang, Semantic segmentation of COVID-19 lesions with a multiscale dilated convolutional network, Scientific Reports 12 (2022), Article number: 1847, DOI: 10.1038/s41598-022-05527-x.
C. Zhang, X. Lu, Q. Ye, C. Wang, C. Yang and Q. Wang, MFENet: Multi-feature extraction net for remote sensing semantic segmentation, in: 7th International Conference on Intelligent Computing and Signal Processing (ICSP 2022), Xi’an, China (2022), pp. 1986 – 1990, DOI: 10.1109/ICSP54964.2022.9778622.
Y. Zheng, B. Jeon, D. Xu, Q. M. Wu and H. Zhang, Image segmentation by generalized hierarchical fuzzy C-means algorithm, Journal of Intelligent & Fuzzy Systems 28(2) (2015), 961 – 973, DOI: 10.3233/IFS-141378.
L. Zhou, X. Xu, K. Zhou and J. Guo, LTS-NET: Lung tissue segmentation from CT images using fully convolutional neural tetwork, in: 11th International Conference on Information Science and Technology (ICIST 2021), Chengdu, China (2021), pp. 125 – 131, DOI: 10.1109/ICIST52614.2021.9440594.
J. Zhu, F. Wang and H. You, SAR image segmentation by efficient fuzzy c-means framework with adaptive generalized likelihood ratio nonlocal spatial information embedded, Remote Sensing 14(7) (2022), 1621, DOI: 10.3390/rs14071621.
Downloads
Published
How to Cite
Issue
Section
License
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a CCAL that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
