Abstract
Considering that apples are susceptible to physiological diseases, an effective image segmentation method is a key point for the fruit diseases detection. It is necessary to develop a novel and effective segmentation algorithm for apple skin disease images. Aiming at the shortcomings of noise interference and over-segmentation of the maximum class variance (OTSU) method in image segmentation, an image segmentation algorithm with memory-based Fruit Fly Optimization algorithm and adaptive weighting factor were proposed and applied in the apple skin disease images. The iterative memory step size was applied to the updating process of the individual position of the flies after one-time optimization to achieve fast global convergence. Combining the improved algorithm with the classical Otsu method, the segmentation algorithm with memory-based fruit fly optimization algorithm was formed. The algorithm encodes and processes the apple skin disease images, selects the inter-class variance of the image as its fitness value, and then, the improved Otsu method was used to segment skin disease of apple images. The convergence of speed and accuracy of memory-based fruit fly optimization algorithm are significantly superior to the other six algorithms. Three types of apple skin disease images including black spot disease under strong illumination, black spot disease under medium illumination and bitterness disease under weak illumination conditions were selected for segmentation experiments. Compared with other region segmentation methods and edge segmentation methods, the results indicate that the Otsu’s segmentation algorithm with memory-based fruit fly optimization algorithm has much better effect in the segmentation experiments of apple skin disease images. The benchmark apple images test results show that the proposed method achieves better segmentation effect than other two segmentation methods. The results show that the proposed algorithm achieves better segmentation effect and higher performance stability.
Similar content being viewed by others
Data availability
Benchmark Function Comparison Experiment
In this simulation experiments, Twenty-four benchmark functions selected from literature [2, 42, 44] were adopted to perform minimum value optimization performance comparison tests on the above seven algorithms.
[28] Seyedali Mirjalili, Seyed Mohammad Mirjalili, Andrew Lewis. Grey Wolf Optimizer [J]. Advances in Engineering Software, 2014, 69(3):46–61.
[29] Mousavirad S J, Ebrahimpour-Komleh H. Human mental search: a new population-based metaheuristic optimization algorithm [J]. Applied Intelligence, 2017.
[66] N. H. Awad, M. Z. Ali, J. J. Liang, B. Y. Qu, P. N. Suganthan. Problem Definitions and Evaluation Criteria for the CEC 2017 Special Session and Competition on Single Objective Bound Constrained Real-Parameter Numerical Optimization [R]. Technical Report, Nanyang Technological University, Singapore, November 2016.
Application experiment of apple skin disease image segmentation
Three types of apple epidermal disease images were randomly selected from the following three conditions for experiment, including black spot disease under strong illumination, black spot disease under medium illumination and bitterness disease under weak illumination.
The three apple images come from the international website, which URL is https://image.baidu.com/search/index?tn=baiduimage&ct=201326592&lm=-1&cl=2&ie=gb18030&word=%C6%BB%B9%FB%B2%A1%B0%DF%CD%BC%C6%AC&fr=ala&ala=1&alatpl=normal&pos=0&dyTabStr=MCwzLDIsNCw2LDUsMSw4LDcsOQ%3D%3D
Application experiment of benchmark image segmentation
Three apple images were randomly selected from fruit classification dataset based on Baidu easydl platform as benchmark images.
The three apple images come from the international website, which URL is https://pan.baidu.com/s/11SstydxQNXNNq9tk9kuyfg
In addition, all data generated or analysed during this study are included in this published article. The datasets generated during and/or analysed during the current study are available from the corresponding author on reasonable request.
References
Ali M, Abid S, Ghafar A, Ayub N, Arshad H, Khan S, Javaid N (2018) Earth Worm Optimization for Home Energy Management System in Smart Grid. Adv Broad-Band Wireless Comput Commun Appl 12:583–596
Awad NH, Ali MZ, Liang JJ, Qu BY, Suganthan PN. Problem Definitions and Evaluation Criteria for the CEC 2017 Special Session and Competition on Single Objective Bound Constrained Real-Parameter Numerical Optimization [R]. Technical Report, Nanyang Technological University, Singapore, November 2016.
Binbin Lu, Zhenhong Jia, Di He et al (2011) Remote-sensing Image Segmentation Method based on Improved Otsu and Shuffled Frog-Leaping Algorithm. Comput Appl Softw 28(9):77–79
Chaofeng L, Shuijing L, Huan C et al (2020) Research on running state recognition method of hydro-turbine based on FOA-PNN. Measurement 2020:108498
Chen S. Locust Swarms - A new multi-optima search technique[C]. In Proceedings of the Eleventh Conference on Congress on Evolutionary Computation. Trondheim, Norway, 18–21 May 2009
Chen SW, Shivakumar SS, Dcunha S et al (2017) Counting apples and oranges with deep learning: a data-driven approach. IEEE Robotics Autom Lett 2:1–8
Cheng H, Tao W, Runwei G et al (2020) Rolling bearing fault diagnosis based on composite multiscale permutation entropy and reverse cognitive fruit fly optimization algorithm – Extreme learning machine. Measurement 10:108636
ChengZhong L, JunYing H (2014) Adaptive fruit fly optimization algorithm based on bacterial migration. Comput Eng Sci 36(4):690–696
Dinkar SK et al (2021) Opposition-based Laplacian Equilibrium Optimizer with application in Image Segmentation using Multilevel Thresholding. Expert Syst Appl 174:114766
Diwakar M, Kumar M (2018) A review on CT image noise and its denoising. Biomed Signal Process Control 42:73–88
Diwakar M, Kumar P (2020) Blind noise estimation-based CT image denoising in tetrolet domain. Int J Inf Comput Secur 12(2–3):234–252
Diwakar M, Kumar P, Singh AK (2020) CT image denoising using NLM and its method noise thresholding. Multimed Tools Appl 79(21):14449–14464
Diwakar M, Singh P (2020) CT image denoising using multivariate model and its method noise thresholding in non-subsampled shearlet domain. Biomed Signal Process Control 57:101754
Du T-S, Ke X-T et al (2018) DSLC-FOA: Improved fruit fly optimization algorithm for application to structural engineering design optimization problems. Appl Math Modell 55:314–339
Elaziz MA, Heidari AA, Fujita H et al (2020) A competitive chain-based Harris Hawks Optimizer for global optimization and multi-level image thresholding problems. Appl Soft Comput 95:95
Esmaeili L, Mousavirad SJ, Shahidi Ne Jad A (2021) An efficient method to minimize cross-entropy for selecting multi-level threshold values using an improved human mental search algorithm. Expert Syst Appl 5:115106
Eusuff MM, Lansey KE (2003) Optimization of water distribution network design using the shuffled frog leaping algorithm. J Water Sources Plann Manage 129(3):210–225
Fan Y, Wang P, Heidari AA et al (2020) Boosted Hunting-based Fruit Fly Optimization and Advances in Real-world Problems. Expert Syst Appl 2020:113502
Feng Y, Wang G, Deb S, Lu M, Zhao X (2019) Monarch butterfly optimization. Neural Comput Appl 31:1995–2014
Gao H, Fu Z, Pun C-M, Hu H, Lan R (2018) A multi-level thresholding image segmentation based on an improved artificial bee colony algorithm. Comput Electr Eng 70:931–938
Geem ZW, Kim JH, Loganathan GV (2001) A new heuristic optimization algorithm: harmony search. Simulation 76(2):60–68
Gu Q, Chang Y, Li X et al (2020) A novel F-SVM based on FOA for improving SVM performance. Expert Syst Appl 165:113713
Häni N, Roy P, Isler V (2019) A comparative study of fruit detection and counting methods for yield mapping in apple orchards. J Field Robot 37(2):263–282
Hao G, Xu W, Sun J et al (2010) Multilevel Thresholding for Image Segmentation Through an Improved Quantum-Behaved Particle Swarm Algorithm. IEEE Trans Instrum Meas 59(4):934–946
Heidari Ali Asghar, Mirjalili Seyedali, Faris Hossam, Aljarah Ibrahim, Mafarja Majdi, Chen Huiling (2019) Harris hawks optimization: Algorithm and applications. Futur Gener Comput Syst 97:849–872
Hongyang Z, Cheng C (2018) Lossless and Online Classification System for Apple Water Core Disease Based on Computer Vision. J Agric Mechanization Res 10:208–210
Hossam Anass, Bouzidi Abdelhamid, Riffi Mohammed Essaid (2019) Elephants Herding Optimization for Solving the Travelling Salesman Problem. Adv Intell Syst Sustain Dev (AI2SD’2018) 912:122–130
Houssein EH et al (2021) A novel Black Widow Optimization algorithm for multilevel thresholding image segmentation. Expert Syst Appl 167:114159
Huang C, Li X, Wen Y (2021) AN Otsu image segmentation based on fruitfly optimization algorithm. Alex Eng J 60:183–188
Huiguang Li, Lei Y, Lei S (2007) Automatic Selection of Image Threshold Based on Improved Otsu. Comput Simul 24(4):216–220
JunYing H, ChengZhong L (2014) Fruit Fly Optimization Algorithm based on history cognition. J Front Comput Sci Technol 8(3):368–375
JunYing H, ChengZhong L, LianGuo W (2013) Dynamic Double Subgroups Cooperative Fruit Fly Optimization Algorithm. Pattern Recognit Artif Intell 26(11):1057–1067
Karaboga D (2005) An Idea Based on Honey Bee Swarm for Numerical Optimization [R]. Erciyes University, Technical Report: TR06
Lahcen A, Kamal A, Mustapha H et al (2019) Peak-to-Average Power Ratio Reduction Using New Swarm Intelligence Algorithm in OFDM Systems. Procedia Manuf 32:831–839
Li Shimin, Chen Huiling, Wang Mingjing, Heidari Ali Asghar, Mirjalili Seyedali (2020) Slime mould algorithm: A new method for stochastic optimization. Futur Gener Comput Syst 111:300–323
Li L, Sun L, Xue Y et al (2021) Fuzzy Multilevel Image Thresholding Based on Improved Coyote Optimization Algorithm. IEEE Access 99:1–1
Liu L, Huo J (2018) Apple Image Segmentation Model Based on R Component with Swarm Intelligence Optimization Algorithm. Int J Performability Eng 14(6):1149–1160
Majeed Y, Zhang J, Zhang X et al (2020) Deep learning based segmentation for automated training of apple trees on trellis wires. Comput Electron Agric 170:105–277
Min Hu, Mei Li, Ronggui W (2010) Application of an improved Otsu algorithm in image segmentation. J Electron Meas Instrum 24(5):443–449
Mina S, Siamak F, Ahmad M et al (2021) A hybrid model based on general regression neural network and fruit fly optimization algorithm for forecasting and optimizing paclitaxel biosynthesis in Corylus avellana cell culture. Plant Methods 17(1):13
Mirjalili S (2015) Moth-flame optimization algorithm: A novel nature-inspired heuristic paradigm. Knowl-Based Syst 89:228–249
Mirjalili S, Mirjalili SM, Lewis A (2014) Grey Wolf Optimizer. Adv Eng Softw 69(3):46–61
Mortazavi A, Togan V, Moloodpoor M (2019) Solution of structural and mathematical optimization problems using a new hybrid swarm intelligence optimization algorithm. Adv Eng Softw 127:106–123
Mousavirad SJ, Ebrahimpour-Komleh H (2017) Human mental search: a new population-based metaheuristic optimization algorithm. Appl Intell 2017:10489
Mousavirad SJ, Schaefer G, Oliva DA et al (2021) HCS-BBD: an effective population-based approach for multi-level thresholding [C]. GECCO '21: Genetic and Evolutionary Computation Conference
Naji HS, Al-Qaness M, Elaziz MA et al (2020) Multi-Level Image Thresholding Based on Modified Spherical Search Optimizer and Fuzzy Entropy. Entropy 22(3):328
Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9(1):62–66
Pan WT (2012) A New Fruit Fly Optimization Algorithm: Taking the Financial Distress Model as an Example. Knowl-Based Syst 29:69–74
Qian JP, Yang XT, Wu XM (2012) Mature Apple Recognition based on Hybrid Color Space in Natural Scene [J]. Transactions of the Chinese Society of Agricultural Engineering 28(17):137–142
Rahaman J, Sing M (2021) An efficient multilevel thresholding based satellite image segmentation approach using a new adaptive cuckoo search algorithm. Expert Syst Appl 174:114633
Shougang R, Fuwei J, Xingjian G et al (2020) Recognition and segmentation model of tomato leaf diseases based on deconvolution-guiding. Trans Chin Soc Agric Eng 36(12):186–195
Tian YN, Li E, Yang L et al. An image processing method for green apple lesion detection in natural environment based on GA-BPNN and SVM [C]. Proceedings of 2018 IEEE International Conference on Mechatronics and Automation (ICMA), Changchun, China, August 5–8, 2018, IEEE
Wang GG (2016) Moth search algorithm: a bio-inspired metaheuristic algorithm for global optimization problems. Memetic Comp 10:151–164
Wang X, Chen H, Heidari AA, Zhang X, Xu J, Xu Y, Huang H (2020) Multi-population following behavior-driven fruit fly optimization: a Markov chain convergence proof and comprehensive analysis. Knowl Based Syst 2020:106437
Wang XW, Yin SL, Sun K et al (2020) GKFC-CNN: modified gaussian kernel fuzzy c-means and convolutional neural network for apple segmentation and recognition. J Appl Sci Eng 23:555–561
Wei D, Wang Z, Si L, Tan C et al (2021) Preaching-inspired swarm intelligence algorithm and its applications. Knowl Based Syst 211:106552
Wen-Tsao P, Shi-Zhuan H, Li-Hui H et al (2018) Mixed Chaotic FOA with GRNN to Construction of a Mutual Fund Forecasting Model. Cogn Syst Res 52:380–386
Wu L, Yang Y, Maheshwari M et al (2019) Parameter optimization for FPSO design using an improved FOA and IFOA-BP neural network. Ocean Eng 175:50–61
Wunnava A, Naik MK, Panda R et al (2020) An adaptive Harris hawks optimization technique for two dimensional grey gradient based multilevel image thresholding. Appl Soft Comput 95:106526
Yang Y, Chen H, Heidari AA, Gandomi AH (2021) Hunger games search: visions, conception, implementation, deep analysis, perspectives, and towards performance shifts. Expert Syst Appl 2021:114864
Yeh WC (2019) Solving cold-standby reliability redundancy allocation problems using a new swarm intelligence algorithm. Appl Soft Comput 83:105582
Yusheng J, Xiangli S, Jingjing R (2010) 2D Otsu algorithm improvement based on genetic algorithm. Appl Res Comput 27(3):1189–1191
Yuxia Z, Keru W, Zhongying B et al (2007) Bayesian classifier method on maize leaf disease identifying based images. Comput Eng Appl 43(5):193–195
Zhang Q, Liu L, Li C, Jiang F (2018) Moth-flame optimization algorithm based on adaptive weight and simulated annealing[C]. International Conference on Intelligent Science and Big Data Engineering. Springer, Cham, 158–167
Zhang JW, Wang GG (2012) Image Matching Using a Bat Algorithm with Mutation. Appl Mech Mater 203:88–93
Zhao D, Liu L, Yu F et al (2020) Ant colony optimization with horizontal and vertical crossover search: Fundamental visions for multi-threshold image segmentation. Expert Syst Appl 2020:114122
Zhao D, Liu L, Yu F et al (2020) Chaotic random spare ant colony optimization for multi-threshold image segmentation of 2D Kapur entropy. Knowl Based Syst 2020:106510
Acknowledgement
This work was supported by the Gansu Provincial University Teacher Innovation Fund Project [grant number 2023A-051]; and, supported by Gansu Science and Technology Plan [grant number 20JR5RA032]; and, the Young Supervisor Fund of Gansu Agricultural University [grant number GAU-QDFC-2020-08].
Author information
Authors and Affiliations
Contributions
All authors contributed to the study conception and design. Material preparation, data collection and analysis were performed by Liqun Liu and all authors commented on previous versions of the manuscript. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Conflict of interest
The authors have no relevant financial or non-financial interests to disclose.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Liu, L. Disease spot image segmentation algorithm with memory-based fruit fly optimization algorithm. Multimed Tools Appl 82, 47135–47163 (2023). https://doi.org/10.1007/s11042-023-15630-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-023-15630-4