Kemal ADEM, Mahmut HEKİM, Onur CÖMERT

A hybrid model based on the convolutional neural network model and artificial bee colony or particle swarm optimization-based iterative thresholding for the detection of bruised apples

: In this study, apple images taken with near-infrared (NIR) cameras were classified as bruised and healthyobjects using iterative thresholding approaches based on artificial bee colony (ABC) and particle swarm optimization(PSO) algorithms supported by a convolutional neural network (CNN) deep learning model. The proposed modelincludes the following stages: image acquisition, image preprocessing, the segmentation of anatomical regions (stemcalyx regions) to be discarded, the detection of bruised areas on the apple images, and their classification. For this aim,by using the image acquisition platform with a NIR camera, a total of 1200 images at 6 different angles were taken from200 apples, of which 100 were bruised and 100 healthy. In order to increase the success of detection and classification,adaptive histogram equalization (AHE), edge detection, and morphological operations were applied to the images inthe preprocessing stage, respectively. First, in order to segment and discard the stem-calyx anatomical regions of theimages, the CNN model was trained by using the preprocessed images. Second, the threshold value was determined bymeans of the ABC/PSO-based iterative thresholding approach on the images whose stem-calyx regions were discarded,and then the bruised areas on the images with no stem-calyx anatomical regions were detected by using the determinedthreshold value. Finally, the apple images were classified as bruised and healthy objects by using this threshold value. Inorder to illustrate the classification success of our approaches, the same classification experiments were reimplementedby directly using the CNN model alone on the preprocessed images with no ABC and PSO approaches. Experimentalresults showed that the hybrid model proposed in this paper was more successful than the CNN model in which ABCand PSO-based iterative threshold approaches were not used.

PDF

___

[1] Barrett DM, Somogyi L, Ramaswamy HS. Processing Fruits: Science and Technology. New York, NY, USA: CRC Press, 2004.
[2] Pandey R, Naik S, Marfatia R. Image processing and machine learning for automated fruit grading system: a technical review. International Journal of Computer Applications 2013; 81: 29-39.
[3] Mohana SH, Prabhakar CJ. Stem-calyx recognition of an apple using shape descriptors. Signal and Image Processing International Journal 2015; 5 (6): 17-31.
[4] Dubey SR, Jalal AS. Apple disease classification using color, texture and shape features from images. Signal, Image and Video Processing 2016; 10 (5): 819-826. doi: 10.1007/s11760-015-0821-1
[5] Sa I, Ge Z, Dayoub F, Upcroft B, Perez T et al. Deepfruits: A fruit detection system using deep neural networks. Sensors 2016; 16 (8): 1222. doi: 10.3390/s16081222
[6] Fuentes A, Yoon S, Kim SC, Park DS. A robust deep-learning-based detector for real-time tomato plant diseases and pests recognition. Sensors 2017; 17 (9): 2022. doi: 10.3390/s17092022
[7] Lu Y, Lu R. Histogram-based automatic thresholding for bruise detection of apples by structured-illumination reflectance imaging. Biosystems Engineering 2017; (160): 30-41. doi: 10.1016/j.biosystemseng.2017.05.005
[8] Zhang S, Wu S, Zhang S, Cheng Q, Tan Z. An effective method to inspect and classify the bruising degree of apples based on the optical properties. Postharvest Biology and Technology 2017; 127: 44-52. doi: 10.1016/j.postharvbio.2016.12.008
[9] Zarifneshat S, Rohani A, Ghassemzadeh HR, Sadeghi M, Ahmadi E et al. Predictions of apple bruise volume using artificial neural network. Computers and Electronics in Agriculture 2012; 82: 75-86. doi: 10.1016/j.compag.2011.12.015
[10] Zhihui H, Weiyu Y, Shanxiang L, Jiuchao F. Multi-level threshold image segmentation using artificial bee colony algorithm. Measuring Technology and Mechatronics Automation 2013; 2013: 707-711.
[11] Horng MH. Multilevel thresholding selection based on the artificial bee colony algorithm for image segmentation. Expert Systems with Applications 2011; 38 (11): 13785-13791. doi: 10.1016/j.eswa.2011.04.180
[12] Maitra M, Chatterjee A. A hybrid cooperative–comprehensive learning based PSO algorithm for image segmentation using multilevel thresholding. Expert Systems with Applications 2008; 34 (2): 1341-1350. doi: 10.1016/j.eswa.2007.01.002
[13] Akay B. A study on particle swarm optimization and artificial bee colony algorithms for multilevel thresholding. Applied Soft Computing 2013; 13 (6): 3066-3091. doi: 10.1016/j.asoc.2012.03.072
[14] Xing J, De Baerdmaeker J. Bruise detection on Jonagold apples using hyperspectral imaging. Postharvest Biology and Technology 2005; 37(2): 152-162.
[15] Karaboga D, Akay B. A comparative study of artificial bee colony algorithm. Applied Mathematics and Computation 2009; 214 (1): 108-132. doi: 10.1016/j.amc.2009.03.090
[16] Hao GS, Wang GG, Zhang ZJ, Zou DX. Comparison of PSO and ABC: from a viewpoint of learning. Transactions on Computer Science and Engineering 2017; 2: 108-112. doi: 10.12783/dtcse/aita2017/15999
[17] Le Cun Y, Bottou L, Bengio Y, Haffner P. Gradient based learning applied to document recognition. Proceedings of the IEEE 1998; 86 (11): 2278-2324.
[18] Girshick R. Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision; Santiago, Chile; 2015. pp. 1440-1448.
[19] Adem K. Exudate detection for diabetic retinopathy with circular Hough transformation and convolutional neural networks. Expert Systems with Applications 2018; (114): 289-295. doi: 10.1016/j.eswa.2018.07.053
[20] Lecun Y, Bengio Y, Hinton G. Deep learning. Nature 2015; 521 (7553): 436. doi: 10.1038/nature14539
[21] Karaboga D, Basturk B. A powerful and efficient algorithm for numerical function optimization: artificial bee colony (ABC) algorithm. Journal of Global Optimization 2007; 39 (3): 459-471. doi: 10.1007/s10898-007-9149-x
[22] Otsu N. A threshold selection method from gray-level histograms. IEEE Transactions on Systems, Man and Cybernetics 1979; 9 (1): 62-66.
[23] Onen U, Cakan A, Ilhan I. Performance comparison of optimization algorithms in LQR controller design for a nonlinear system. Turkish Journal of Electrical Engineering and Computer Sciences 2019; 27 (3): 1938-1953. doi: 10.3906/elk-1808-51
[24] Makas H, Yumusak N. Balancing exploration and exploitation by using sequential execution cooperation between artificial bee colony and migrating birds optimization algorithms. Turkish Journal of Electrical Engineering and Computer Sciences 2016; 24 (6): 4935-4956. doi: 10.3906/elk-1404-45
[25] Guvenc U, Isik AH, Yigit T, Akkaya I. Performance analysis of biogeography-based optimization for automatic voltage regulator system. Turkish Journal of Electrical Engineering and Computer Sciences 2016; 24 (3): 1150- 1162. doi: 10.3906/elk-1311-111
[26] Karakuzu C. On the performance of newsworthy meta-heuristic algorithms based on point of view fuzzy modelling. Turkish Journal of Electrical Engineering, Computer Sciences 2017; 25 (6): 4706-4721. doi: 10.3906/elk-1705-337
[27] Kennedy J, Eberhart R. Particle swarm optimization (PSO). In: Proceedings of the IEEE International Conference on Neural Networks; Perth, Australia; 1995. pp. 1942-1948.
[28] Adem K, Hekim M, Demir S. Detection of hemorrhage in retinal images using linear classifiers and iterative thresholding approaches based on firefly and particle swarm optimization algorithms. Turkish Journal of Electrical Engineering and Computer Sciences 2019; 27 (1): 499-515. doi: 10.3906/elk-1804-147