Automatic leaf segmentation using grey wolf optimizer based neural network

This study proposes a hybrid neural network model for the segmentation of leaf images with various illumination conditions. Segmentation of images with different illumination conditions is a quite challenging process. In particular, the shadows and dark regions in the image can be quite misleading for traditional segmentation algorithms. Using a single feature or reviewing them in a single colour space may work for some images, but this approach does not work on the entire dataset that have different colour. For this reason, automatic segmentation method is proposed in this study by using components from four different colour spaces. Firstly, the image is converted into RGB, HSV, XYZ and YIQ channels. Then, B, S, Z and I components are used to train hybrid neural network. Grey wolf optimizer is used for neural network optimization. The segmentation results of proposed method are compared with the well-known segmentation algorithms and are more successful. The results of proposed method are that sensitivity is 99.66 %, specificity is 98.42 % and accuracy is 99.31 %.

[1]  Wilfried Philips,et al.  Leaf Segmentation and Tracking Using Probabilistic Parametric Active Contours , 2011, MIRAGE.

[2]  Qian Chen,et al.  Face Detection From Color Images Using a Fuzzy Pattern Matching Method , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Jie Tian,et al.  Wheat leaf lesion color image segmentation with improved multichannel selection based on the Chan-Vese model , 2017, Comput. Electron. Agric..

[4]  Divya Tomar,et al.  Leaf Recognition for Plant Classification Using Direct Acyclic Graph Based Multi-Class Least Squares Twin Support Vector Machine , 2016, Int. J. Image Graph..

[5]  Andrew Lewis,et al.  Grey Wolf Optimizer , 2014, Adv. Eng. Softw..

[6]  Jing Wang,et al.  Recognition of Leaf Image Set Based on Manifold-Manifold Distance , 2014, ICIC.

[7]  Zhu-Hong You,et al.  Leaf image based cucumber disease recognition using sparse representation classification , 2017, Comput. Electron. Agric..

[8]  Yong Li,et al.  PSO-based neural network optimization and its utilization in a boring machine , 2006 .

[9]  Jyotismita Chaki,et al.  Plant leaf recognition using texture and shape features with neural classifiers , 2015, Pattern Recognit. Lett..

[10]  Jayme Garcia Arnal Barbedo,et al.  A new automatic method for disease symptom segmentation in digital photographs of plant leaves , 2017, European Journal of Plant Pathology.

[11]  Akshay Gore,et al.  Objective color image quality assessment based on Sobel magnitude , 2017, Signal Image Video Process..

[12]  Steven Verstockt,et al.  Leaf segmentation and parallel phenotyping for the analysis of gene networks in plants , 2013, 21st European Signal Processing Conference (EUSIPCO 2013).

[13]  Ren Yong,et al.  Optimization of Image Processing in Video-based Traffic Monitoring , 2012 .

[14]  Maolin Zhang,et al.  The Linear Transformation Image Enhancement Algorithm Based on HSV Color Space , 2017 .

[15]  J. G. A. Barbedo,et al.  A novel algorithm for semi-automatic segmentation of plant leaf disease symptoms using digital image processing , 2016, Tropical Plant Pathology.

[16]  A. K. Misra,et al.  Detection of plant leaf diseases using image segmentation and soft computing techniques , 2017 .