For the problems of complex forest canopy images and poor segmentation accuracy, a novel canopy image segmentation method based on improved northern goshawk algorithm (INGO) by using multi-strategy fusion was proposed. Firstly, a random reverse learning strategy was introduced for the initialization of northern goshawk to increase population diversity and improve search efficiency. Adaptive weight factors were added in the exploration phase of the northern goshawk to improve the algorithm's search ability and accelerates its convergence speed. Non-linear convergence factors were introduced in the development stage of northern goshawk to balance global search and local development capabilities. Secondly, multiple-threshold Kapur entropy was employed as the fitness function, the improved algorithm was tested using eight benchmark functions, and the results demonstrated that it effectively enhanced both accuracy and search speed. Finally, the improved algorithm was applied to threshold segmentation research on forest canopy images, and comparative analysis was conducted on fitness value, peak signal-to-noise ratio of forest image segmentation (PSNR), structural similarity (SSIM), and feature similarity (FSIM). Experimental results indicated that the improved algorithm can obtain more accurate forest canopy segmentation thresholds and higher segmentation accuracy.
SUNT G, LIL B, ZHANGH,et al.Study on the effects of tree moisture physiology and canopy structure on net photosynthesis photosynthetic rate based on the rough set theory[J].Ecology and Environmental Sciences,2015,24(7):1137-1142.
[5]
OTSUN.A threshold selection method from gray-level histograms[J].IEEE Transactions on Systems Man & Cybernetics,1979,9(1):62-66.
XINGZ K, JIAH M, SONGW L.Multi-threshold image segmentation based on Levi Flying Salpa group optimization algorithm[J].Acta Automatica Sinica,2021,47(2):363-377.
HUANGP, ZHENGQ, LIANGC.Review of image segmentation methods[J].Journal of Wuhan University(Science Edition),2019,66(6):519-531.
[10]
MINAEES, BOYKOVY Y, PORIKILF,et al.Image segmentation using deep learning: A survey[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2021,44(7):3523-3542.
ZHUL K, SHAOS X, JINGW P,et al.PSO-optimized fast segmentation algorithm for 3D otsu forest canopy image[J].Journal of Harbin University of Science and Technology,2019,24(5):128-133.
[15]
常君杰.启发式算法在图像分割中的应用研究[D].淄博:山东理工大学,2022.
[16]
CHANGJ J.Research on the application of heuristic algorithms in image segmentation[D].Zibo: Shandong University of Technology,2022.
[17]
詹志宇,安友军,崔文超.图像阈值分割算法及对比研究[J].信息通信,2017(4):86-89.
[18]
ZHANZ Y, ANY J, CUIW C.Image thresholding segmentation algorithm and contrastive study[J].Information & Communications,2017(4):86-89.
FUX, ZHUL K, HUANGJ P,et al.Multi threshold image segmentation based on improved Northern goshawk optimization algorithm[J].Computer Engineering,2023,49(7):231-241.
[21]
BHANDARIA K, KUMARA, SINGHG K.Tsallis entropy based multilevel thresholding for colored satellite image segmentation using evolutionary algorithms[J].Expert Systems with Application,2015,42(22):8707-8730.
[22]
ALI M, AHNC W, PANTM.Multi-level image thresholding by synergetic differential evolution[J].Applied Soft Computing,2014,1(17):1-11.
LUJ H, LIUH P, WANGM.Multi-threshold image segmentation based on improved seagulloptimization algorithm[J].Optoelectronics Laser,2022,33(9):932-939.
[29]
KHORRAMB, YAZDIM.A new optimized thresholding method using ant colony algorithm for mr brain image segmentation[J].Journal of Digital Imaging: the Official Journal of the Society for Computer Applications in Radiology,2019,32(1):162-174.
[30]
BANIANIE A, CHALECHALEA.Hybrid PSO and genetic algorithm for multilevel maximum entropy criterion threshold selection[J].International Journal of Hybrid Information Technology,2013,6(5):131-140.
[31]
JIAH, PENGX, SONGW,et al.Multiverse optimization algorithm based on lévy flight improvement for multithresholdcolor image segmentation[J].IEEE Access,2019,7:32805-32844.
[32]
HERNÁNP V, ADRIÁNP D, RANJANP,et al.A Bio-Inspired method for mathematical optimization inspired by arachnida salticidade[J].Mathematics,2021,10(1):102.
[33]
CARREON-ORTIZH, VALDEZF.A new mycorrhized tree optimization nature-inspired algorithm[J].Soft Computing,2022,26(10):4797-4817.
[34]
NARUEII, KEYNIAF, SABBAGHM A.Hunter-prey optimization: Algorithm and applications[J].Soft Computing,2022,26(3):1279-1314.
[35]
NARUEII, KEYNIAF.Wild horse optimizer: A new meta-heuristic algorithm for solving engineering optimization problems[J].Engineering with Computers,2022,38(4):3025-3056.
[36]
ŠTĔPÁNMOHAMMAD D, PAVEL TH.Northern goshawk optimization:a new swarm-based algorithm for solving optimization problems[J].IEEE Access,2021(9):59-80.
[37]
LIANGY, HUX, HUG, DOUW.An enhanced northern goshawk optimization algorithm and its application in practical optimization problems[J].Mathematics.2022,10(22):43-83.
[38]
YUS, MAJ.Adaptive Composite fault diagnosis of rolling bearings based on the CLNGO algorithm[J].Processes,2022,10(12):2532.
[39]
SATRIAH, SYAHR B Y, NEHDIM L,et al.Parameters identification of solar PV using hybrid chaotic northern goshawk and pattern search[J].Sustainability,2023,15(6): 5027.
[40]
TIZHOOSH,H R.Opposition-based learning: A new scheme for machine intelligence[J].IEEE,2005,1(28):695-701.
[41]
LONGW, JIAOJ, LIANGX,et al.A random opposition-based learning grey wolf optimizer[J].IEEE Access,2019,7(13):10-25.
[42]
KAPURJ N, SAHOOP K, WONGA K C.A new method for gray-level picture thresholding using the entropy of the histogram[J].Computer Vision,Graphics,and Image Processing,1980,29(3):273-285.
[43]
YANZ, ZHANGJ, YANGZ,et al.Kapur's entropy for underwater multilevel thresholding image segmentation based on whale optimization algorithm[J].IEEE Access,2020,9:41294-41319.