Date maturity and quality evaluation using color distribution analysis and back projection

Abstract A new color grading method is proposed in this paper to provide an automatic and intuitive way of evaluating the maturity and quality of harvested dates. Different from other existing methods that rely on complicated machine learning or artificial intelligent algorithms, this method uses 2D histograms of colors in each grading category to determine the co-occurrence frequency. Based on this color analysis result, a mapping matrix is generated for back projecting the input colors of the fruit to their designated color indexes. The date color, which strongly correlates to maturity and quality, can then be graded by analyzing the resulting back projected color indexes. With the proposed method, the operator is allowed to set or adjust the cutoff points of different maturity or quality groups of date for automatic inspection. This paper uses Medjool date grading as an example to demonstrate the performance of the proposed algorithm. It is suitable and can be easily adapted for other fruit or vegetable grading applications. The proposed method is proven accurate and user-friendly and has been implemented and used for commercial production for date maturity evaluation.

[1]  A. Peirs,et al.  Nondestructive measurement of fruit and vegetable quality by means of NIR spectroscopy: A review , 2007 .

[2]  Ahmad Ihsan Mohd Yassin,et al.  Monitoring of Watermelon Ripeness Based on Fuzzy Logic , 2009, 2009 WRI World Congress on Computer Science and Information Engineering.

[3]  Nikolaos Mavridis,et al.  Image-based date fruit classification , 2012, 2012 IV International Congress on Ultra Modern Telecommunications and Control Systems.

[4]  Jiewen Zhao,et al.  On-Line Sorting Maturity of Cherry Tomato Bymachine Vision , 2008, CCTA.

[5]  Dah-Jye Lee,et al.  Rapid Color Grading for Fruit Quality Evaluation Using Direct Color Mapping , 2011, IEEE Transactions on Automation Science and Engineering.

[6]  J. De Baerdemaeker,et al.  Development of an automated monitoring device to quantify changes in firmness of apples during storage , 2000 .

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

[8]  F. Mendoza,et al.  Application of Image Analysis for Classification of Ripening Bananas , 2006 .

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

[10]  Margarita Ruiz-Altisent,et al.  Olive classification according to external damage using image analysis. , 2008 .

[11]  Jasper G. Tallada,et al.  Bruise Detection using NIR Hyperspectral Imaging for Strawberry (Fragaria * ananassa Duch.) , 2006 .

[12]  Hélène Laurent,et al.  Calibration and quality control of cherries by artificial vision , 2004, J. Electronic Imaging.

[13]  James Archibald,et al.  Development of a machine vision system for automatic date grading using digital reflective near-infrared imaging , 2008 .

[14]  Josse De Baerdemaeker,et al.  Combination of chemometric tools and image processing for bruise detection on apples , 2007 .

[15]  I. Paulus,et al.  Shape Characterization of New Apple Cultivars by Fourier Expansion of Digitized Images , 1999 .

[16]  Qi Wang,et al.  Outdoor color rating of sweet cherries using computer vision , 2012 .

[17]  Yuchou Chang,et al.  Robust color space conversion and color distribution analysis techniques for date maturity evaluation , 2008 .

[18]  Renfu Lu,et al.  Prediction of firmness and soluble solids content of blueberries using hyperspectral reflectance imaging , 2013 .

[19]  Qixin Cao,et al.  A method for color classification of fruits based on machine vision , 2009 .

[20]  Aidil Azwin Zainul Abidin,et al.  Image processing of an agriculture produce: Determination of size and ripeness of a banana , 2008, 2008 International Symposium on Information Technology.