Abstract
Image segmentation is one of the most significant tasks in image analysis, and it plays an imperative job in image processing to analyse and attain meaningful information. Moreover, image segmentation is a major process of object recognition and categorization in computer vision domain. Image segmentation utilizes the image features for separating images into definite areas along with exclusive properties. Meanwhile, various colour image segmentation techniques are introduced in computer vision research area. However, these techniques are more time consuming and failed to afford anticipated segmentation outcome, because of poor segmentation results and high computational difficulty. To overcome these challenges, an effectual hybrid optimization-based Deep Learning (DL) technique is devised for colour image segmentation and classification in this research study. The median filter is applied for input image to eliminate the noises, which assists for better image segmentation and classification process. Moreover, Improved Invasive Weed Flower Pollination Optimization (IIWFPO) approach is introduced for image segmentation process in this work. In addition, Deep Residual Network (DRN) classifier is employed for image classification, and the classifier is trained by developed Fr-IIWFPO algorithm. The developed colour image segmentation and classification approach obtained better performance than traditional techniques with accuracy of 0.9187, sensitivity of 0.9334, and specificity of 0.8902.







Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Bora DJ (2018) Importance of image enhancement techniques in color image segmentation: a comprehensive and comparative study. arXiv preprint arXiv:1708.05081
Feng L, Li H, Gao Y, Zhang Y (2020) A color image segmentation method based on region salient color and fuzzy c-means algorithm. Circuits Syst Signal Process 39(2):586–610
Lei T, Jia X, Zhang Y, Liu S, Meng H, Nandi AK (2018) Superpixel-based fast fuzzy c-means clustering for color image segmentation. IEEE Trans Fuzzy Syst 27(9):1753–1766
Xing Z, Jia H (2019) Multilevel color image segmentation based on GLCM and improved salp swarm algorithm. IEEE Access 7:37672–37690
Liang H, Jia H, Xing Z, Ma J, Peng X (2019) Modified grasshopper algorithm-based multilevel thresholding for color image segmentation. IEEE Access 7:11258–11295
Bai M, Urtasun R (2017) Deep watershed transform for instance segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 5221–5229
Ma J, Li S, Qin H, Hao A (2016) Unsupervised multi-class co-segmentation via joint-cut over $ L_ 1 $-manifold hyper-graph of discriminative image regions. IEEE Trans Image Process 26(3):1216–1230
Yin S, Qian Y, Gong M (2017) Unsupervised hierarchical image segmentation through fuzzy entropy maximization. Pattern Recogn 68:245–259
Gong M, Li H, Zhang X, Zhao Q, Wang B (2015) Nonparametric statistical active contour based on inclusion degree of fuzzy sets. IEEE Trans Fuzzy Syst 24(5):1176–1192
Long J, Shelhamer E, Darrell, T (2015) Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3431–3440
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst 25:1097–1105
Gangappa M, Kiran Mai C, Sammulal P (2019) Enhanced crow search optimization algorithm and hybrid NN-cnn classifiers for classification of land cover images. Multimed Res 2(3):12–22
Alagarsamy S, Kamatchi K, Govindaraj V, Thiyagarajan A (2017) A fully automated hybrid methodology using Cuckoo-based fuzzy clustering technique for magnetic resonance brain image segmentation. Int J Imaging Syst Technol 27(4):317–332
Xing Z (2020) An improved emperor penguin optimization based multilevel thresholding for color image segmentation. Knowl-Based Syst 194:105570
Rad AE, Rahim MSM, Kolivand H, Amin IBM (2017) Morphological region-based initial contour algorithm for level set methods in image segmentation. Multimed Tools Appl 76(2):2185–2201
Zibetti MV, Helou ES, Pipa DR (2017) Accelerating overrelaxed and monotone fast iterative shrinkage-thresholding algorithms with line search for sparse reconstructions. IEEE Trans Image Process 26(7):3569–3578
Kline TL, Korfiatis P, Edwards ME, Blais JD, Czerwiec FS, Harris PC, King BF, Torres VE, Erickson BJ (2017) Performance of an artificial multi-observer deep neural network for fully automated segmentation of polycystic kidneys. J Digit Imaging 30(4):442–448
Bhandari AK (2020) A novel beta differential evolution algorithm-based fast multilevel thresholding for color image segmentation. Neural Comput Appl 32(9):4583–4613
Sowmya V, Govind D, Soman KP (2017) Significance of contrast and structure features for an improved color image classification system. In: Proceedings of 2017 IEEE international conference on signal and image processing applications (ICSIPA), pp. 210–215
Yang XS (2012) Flower pollination algorithm for global optimization. In: Proceedings of international conference on unconventional computing and natural computation, pp. 240–249
Misaghi M, Yaghoobi M (2019) Improved invasive weed optimization algorithm (IWO) based on chaos theory for optimal design of PID controller. J Comput Design Eng 6(3):284–295
Bhaladhare PR, Jinwala DC (2014) A clustering approach for the-diversity model in privacy preserving data mining using fractional calculus-bacterial foraging optimization algorithm. Adv Comput Eng 2014:1
Sun L, Luo B, Liu T, Liu Y, Wei Y (2019) Algorithm of adaptive fast clustering for fish swarm color image segmentation. IEEE Access 7:178753–178762
Xu G, Zhou J, Dong J, Chen CP, Zhang T, Chen L, Han S, Wang L, Chen Y (2020) Multivariate morphological reconstruction based fuzzy clustering with a weighting multi-channel guided image filter for color image segmentation. Int J Mach Learn Cybern 11(12):2793–2806
Chen Z, Chen Y, Wu L, Cheng S, Lin P (2019) Deep residual network based fault detection and diagnosis of photovoltaic arrays using current-voltage curves and ambient conditions. Energy Convers Manage 198:111793
Narmadha RP, Sengottaiyan N, Kavitha RJ (2022) Deep Transfer Learning Based Rice Plant Disease Detection Model. Intell Autom Soft Comput 31(2):1257–1271
Ananthi J, Sengottaiyan N, Anbukaruppusamy S, Upreti K, Dubey AK (2022) Forest fire prediction using IoT and deep learning. Int J Adv Technol Eng Explor 9(87):246
Stanford background dataset taken from. https://www.kaggle.com/balraj98/stanford-background-dataset, accessed on November 2021
Deepa SN, Rasi D (2019) Global biotic cross-pollination algorithm enhanced with evolutionary strategies for color image segmentation. Soft Comput 23(8):2545–2559
Rani KSK, Rasi D, Deepa SN (2018) Developed global biotic cross pollination algorithm for CIS. Int J Bus Intell Data Min 13(1–3):108–128
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors confirm no conflict of interest in publishing this work.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Rasi, D., Deepa, S.N. Hybrid optimization enabled deep learning model for colour image segmentation and classification. Neural Comput & Applic 34, 21335–21352 (2022). https://doi.org/10.1007/s00521-022-07614-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-022-07614-6