International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395 -0056
Volume: 04 Issue: 04 | Apr -2017
p-ISSN: 2395-0072
www.irjet.net
An Image Processing Technique for Grading of Harvested Mangoes . Shahin Khan1, Tabbu Mulani2, Poonam Lalge3, Nazneen Shaikh4 1Shahin
Khan, Dept. Of Computer Engineering,Trinity Academy of Engineering, India , Pune , Maharashtra. Mulani, Dept. Of Computer Engineering,Trinity Academy of Engineering, India , Pune , Maharashtra. 3Poonam Lalge, Dept. Of Computer Engineering,Trinity Academy of Engineering, India , Pune , Maharashtra. 4Nazneen Shaikh, Dept. Of Computer Engineering,Trinity Academy of Engineering, India , Pune , Maharashtra. 2Tabbu
---------------------------------------------------------------------***--------------------------------------------------------------------Abstract - The proper grading of fruits is very important to increase the profitability in agricultural and food industry . In this paper, a scheme for automated grading of mango according to maturity has been proposed. The proposed scheme grades the mangoes in four different categories, which are determined on the basis of market distance and market value. The image of mango is given to the system thereafter several pre-processing algorithms like GrayScaling, Blurring, Thresholding are applied followed by RGB to HSV conversion algorithm and K-means algorithm are applied to get the final result.
which is essential during transportation from one place to another and it also helps to select the market distance and market demand for sending fresh fruits (before start rotten). In most of the work, practical purpose of grading and the automated system for the purpose have not been taken into account. In the proposed work authors developed an automated system for grading of harvested mangoes based on actual-days-to-rot and quality level. The necessity, the key innovation of this proposed work and also the main concern of this paper is clearly summarized in the following:
Key Words: Maturity, Quality, Grading, Days-to-rot, Grey scaling , Blurring.
• The proposed system not only predicts maturity level and quality level, but also predicts the actual-days-to-rot of mangoes. So the vendors can increase their profitability by reducing losses due to rotting of mangoes during transportation.
1.INTRODUCTION Because of flavor and taste Mangoes is popular fruit. Mango cultivation is carried out in different favorable regions. During summer mangoes are harvested from gardens and then transported to various markets by distributors. According to distance and demand of market quality, the distributors demand batches of homogeneous quality and maturity. The variations become much wider due to variation in variety, location and weather condition at the time of harvesting.
The main contribution of the present work is, development of a real time automated for grading of harvested mangoes according to maturity level in terms of actual-days-to-rot and the quality attributes like color of the fruit. The prediction of actual-days-to-rot is more important than the maturity level, in decision making on the account of transportation delay. The proposed method is discussed in Section 2. Pre-processing, 3. RGB to HSV ,4. K-means algorithm. We summarize our work and conclude this paper in Section 5.
The grading of mangoes is thus an essential step, however it is a tedious job and it is difficult for the graders to maintain constant vigilance. If this task could be performed automatically, the result would be more objective; it would also save labor and enhance output. In past, much research work has been carried for automated grading of fruits through analyzing aroma using electronic nose, in order to predict the ripeness of fruit [1]. In another work, a spectroscopy based fiber-optic and microoptic device is presented for testing the quality and safety of foods [2]. Recently peach maturity prediction has been performed by estimating the fruit flesh firmness using multivariate retrieval techniques applied to the reflectance spectra acquired with the spectrometer [3] . The application of machine vision in agriculture has increased considerably in recent years. There are many fields in which computer vision is involved, including terrestrial and aerial mapping of natural resources, crop monitoring [4], quality control in food and agriculture [5]–[7], No such system still proposed for prediction of actual-days-to-rot,
Š 2017, IRJET
|
Impact Factor value: 5.181
2. Overview The system aims in the automatic grading of mangoes based on the color of the mangoes. The color of the fruit gives us idea about the ripeness of the fruit. There are different maturity levels of the fruit based on its color. The system takes the images of mangoes as input and then performs several pre processing techniques like gray scaling, blurring and thresholding after which the actual processing of the system begins. The whole image of the mango is divided into blocks of size 16 x 16 pixels and each block is examined for black surface . The system is first trained with the training data set to which input will be compared. The training data set's each block's RGB values are converted into HSV values and stored into an array. The centroids of each HSV values of the training data set is calculated using K-means algorithm.
|
ISO 9001:2008 Certified Journal
| Page 825