Computer vision detection of defective apples using automatic lightness correction and weighted RVM classifier

Abstract Automatic detection of defective apples by computer vision system is still not available due to the uneven lightness distribution on the surface of apples and the similarity between the true defects, stems and calyxes. This paper presents a novel automatic defective apple detection method by using computer vision system combining with automatic lightness correction, number of the defect candidate (including true defect, stem and calyx) region counting, and weighted relevance vector machine (RVM) classifier. Automatic lightness correction was used to solve the problem of the uneven lightness distribution, especially in the edge area of the apples. According to the fact that the calyx and stem cannot appear at the same view of image, some apples could be classified as sound ( N  = 0, N is the number of defect candidate region) or defective ( N  ⩾ 2) apples based on the number of defect candidate region in the preliminary step without any other complex processing. For the rest uncertain apples ( N  = 1), further discrimination was conducted. Average color, statistical, and average textural features were extracted from each candidate region, the relevant features and their weights were also analyzed by using I-RELIEF algorithm. Finally, the defect candidate regions are classified as true defect or stem/calyx by the weighted RVM classifier, and the apples would be finally classified as sound or defective class according to the category of the candidate regions. The result with 95.63% overall detection accuracy for the 160 samples indicated that the proposed algorithm was effective and suitable for the defective apples detection. The limitation of our research is the one single limited inspection view of the apples. Future work will be focused on whole surface and fast on-line inspection.

[1]  D. L. Peterson,et al.  Performance of a System for Apple Surface Defect Identification in Near-infrared Images , 2005 .

[2]  Begüm Demir,et al.  Hyperspectral Image Classification Using Relevance Vector Machines , 2007, IEEE Geoscience and Remote Sensing Letters.

[3]  Fernando López-García,et al.  Automatic detection of skin defects in citrus fruits using a multivariate image analysis approach , 2010 .

[4]  Bernard Gosselin,et al.  Stem and calyx recognition on ‘Jonagold’ apples by pattern recognition , 2007 .

[5]  M. Destain,et al.  Development of a multi-spectral vision system for the detection of defects on apples , 2005 .

[6]  Xuhui Zhao,et al.  Development of a two-band spectral imaging system for real-time citrus canker detection , 2012 .

[7]  Da-Wen Sun,et al.  Improving quality inspection of food products by computer vision: a review , 2004 .

[8]  Yijun Sun,et al.  Iterative RELIEF for Feature Weighting: Algorithms, Theories, and Applications , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[9]  Robert M. Nishikawa,et al.  A study on several Machine-learning methods for classification of Malignant and benign clustered microcalcifications , 2005, IEEE Transactions on Medical Imaging.

[10]  Chi Zhang,et al.  Apple stem-end/calyx identification using a speckle-array encoding pattern , 2012, 2012 IEEE 11th International Conference on Signal Processing.

[11]  Scott C. Chapman,et al.  The Chromosomal Control of Leaf Characteristics of Early-Stage Plants in Wheat (Triticum aestivum L.) , 2011 .

[12]  Cheng-Liang Liu,et al.  [Detection of slight bruises on apples based on hyperspectral imaging and MNF transform]. , 2014, Guang pu xue yu guang pu fen xi = Guang pu.

[13]  José Blasco,et al.  Machine Vision System for Automatic Quality Grading of Fruit , 2003 .

[14]  Vincent Leemans,et al.  Selection of the most efficient wavelength bands for ‘Jonagold’ apple sorting , 2003 .

[15]  Ning Wang,et al.  Early detection of apple bruises on different background colors using hyperspectral imaging , 2008 .

[16]  Vincent Leemans,et al.  A real-time grading method of apples based on features extracted from defects , 2004 .

[17]  Nuria Aleixos,et al.  Erratum to: Advances in Machine Vision Applications for Automatic Inspection and Quality Evaluation of Fruits and Vegetables , 2011 .

[18]  Robert M. Nishikawa,et al.  Relevance vector machine for automatic detection of clustered microcalcifications , 2005, IEEE Transactions on Medical Imaging.

[19]  Gustavo Camps-Valls,et al.  Automatic correction of the effects of the light source on spherical objects. An application to the analysis of hyperspectral images of citrus fruits , 2008 .

[20]  Jiangbo Li,et al.  Automatic detection of common surface defects on oranges using combined lighting transform and image ratio methods , 2013 .

[21]  Kit L. Yam,et al.  A versatile and inexpensive technique for measuring color of foods , 2000 .

[22]  Baohua Zhang,et al.  Principles, developments and applications of computer vision for external quality inspection of fruits and vegetables: A review , 2014 .

[23]  M. A. Khan,et al.  Machine vision system: a tool for quality inspection of food and agricultural products , 2012, Journal of Food Science and Technology.

[24]  José Blasco,et al.  Multispectral inspection of citrus in real-time using machine vision and digital signal processors , 2002 .

[25]  P. Gupta,et al.  Relevance Vector Machine for Optical Diagnosis of Cancer , 2022 .

[26]  Da-Wen Sun,et al.  Inspection and grading of agricultural and food products by computer vision systems—a review , 2002 .

[27]  Pankaj B. Pathare,et al.  Colour Measurement and Analysis in Fresh and Processed Foods: A Review , 2012, Food and Bioprocess Technology.

[28]  Zou Xiaobo,et al.  In-line detection of apple defects using three color cameras system , 2010 .

[29]  A. Camelo,et al.  Comparison of color indexes for tomato ripening , 2004 .

[30]  Bernard Gosselin,et al.  Original paper: Automatic grading of Bi-colored apples by multispectral machine vision , 2011 .

[31]  Naoshi Kondo,et al.  Automation on fruit and vegetable grading system and food traceability. , 2010 .