New effective techniques for automatic detection and classification of external olive fruits defects based on image processing techniques

AbstractOne of the major concerns for fruit selling companies, at present, is to find an effective way for rapid classification and detection of fruit defects. Olive is one of the most important agricultural product, which receives great attention from fruit and vegetables selling companies, for its utilization in various industries such as oils and pickles industry. The small size and multiple colours of the olive fruit increases the difficulty of detecting the external defects. This paper presents new efficient methods for detecting and classifying automatically the external defects of olive fruits. The proposed techniques can separate between the defected and the healthy olive fruits, and then detect and classify the actual defected area. The proposed techniques are based on texture analysis and the homogeneity texture measure. The results and the performance of proposed techniques were compared with varies techniques such as Canny, Otsu, local binary pattern algorithm, K-means, and Fuzzy C-Means algorithms. The results reveal that proposed techniques have the highest accuracy rate among other techniques. The simplicity and the efficiency of the proposed techniques make them appropriate for designing a low-cost hardware kit that can be used for real applications.

[1]  David Zhang,et al.  LSDT: Latent Sparse Domain Transfer Learning for Visual Adaptation , 2016, IEEE Transactions on Image Processing.

[2]  Astha Baxi,et al.  A Review on Otsu Image Segmentation Algorithm , 2013 .

[3]  C. Swathi,et al.  Detection of external defects on mango , 2016 .

[4]  David Zhang,et al.  Evolutionary Cost-Sensitive Extreme Learning Machine , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[5]  Matti Pietikäinen,et al.  Dynamic Texture Recognition Using Local Binary Patterns with an Application to Facial Expressions , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Suchitra A. Khoje,et al.  Automated Skin Defect Identification System for Fruit Grading Based on Discrete Curvelet Transform , 2013 .

[7]  Ahmed A. Nashat,et al.  Automatic segmentation and classification of olive fruits batches based on discrete wavelet transform and visual perceptual texture features , 2017, Int. J. Wavelets Multiresolution Inf. Process..

[8]  Matti Pietikäinen,et al.  Median Robust Extended Local Binary Pattern for Texture Classification , 2016, IEEE Trans. Image Process..

[9]  Javier Gámez García,et al.  Sorting Olive Batches for the Milling Process Using Image Processing , 2015, Sensors.

[10]  R. N. Shebiah,et al.  Fruit Recognition using Color and Texture Features , 2010 .

[11]  Manisha Satone,et al.  Automatic Bruise Detection in Fruits Using Thermal Images , 2017 .

[12]  Ajit Danti,et al.  Construction of Co-occurrence Matrix using Gabor Wavelets for Classification of Arecanuts by Decision Trees , 2012 .

[13]  Gaston Lefranc,et al.  Olive Fruits Recognition Using Neural Networks , 2013, ITQM.

[14]  Modesto Castrillón,et al.  Face recognition using independent component analysis and support vector machines , 2003 .

[15]  Masashi Sugiyama,et al.  Local Fisher discriminant analysis for supervised dimensionality reduction , 2006, ICML.

[16]  Yudong Zhang,et al.  Classification of Fruits Using Computer Vision and a Multiclass Support Vector Machine , 2012, Sensors.

[17]  Bülent Sankur,et al.  Survey over image thresholding techniques and quantitative performance evaluation , 2004, J. Electronic Imaging.

[18]  Brani Vidakovic,et al.  Wavelet-based spectral descriptors for detection of damage in sunflower seeds , 2016, Int. J. Wavelets Multiresolution Inf. Process..

[19]  Matti Pietikäinen,et al.  Extended local binary patterns for face recognition , 2016, Inf. Sci..

[20]  Shubham Joshi,et al.  Image Segmentation using Morphological Operations , 2015 .

[21]  Mohammad Motiur Rahman,et al.  An Efficient Image Segmentation Method Based on Linear Discriminant Analysis and K-means Algorithm with Automatically Splitting and Merging Clusters , 2018 .

[22]  Kimcheng Kith,et al.  The Normalized Wavelet Descriptor for Shape Retrieval , 2008, Int. J. Wavelets Multiresolution Inf. Process..

[23]  G RauljiJitendrasinh.  A Review on Fuzzy C-Mean Clustering Algorithm , 2015 .

[24]  Yan Liu,et al.  Odor Recognition in Multiple E-Nose Systems With Cross-Domain Discriminative Subspace Learning , 2017, IEEE Transactions on Instrumentation and Measurement.

[25]  Lapo Governi,et al.  ANN-based method for olive Ripening Index automatic prediction , 2010 .

[26]  Jian Yang,et al.  Domain class consistency based transfer learning for image classification across domains , 2017, Inf. Sci..

[27]  Francesco Bianconi,et al.  A sequential machine vision procedure for assessing paper impurities , 2014, Comput. Ind..

[28]  Tonglin Zhu,et al.  Periodic wavelet descriptor of plant leaf and its application in botany , 2015, Int. J. Wavelets Multiresolution Inf. Process..

[29]  David Zhang,et al.  Robust Visual Knowledge Transfer via Extreme Learning Machine-Based Domain Adaptation , 2016, IEEE Transactions on Image Processing.

[30]  Jing Huang,et al.  Image indexing using color correlograms , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.