International Journal of Modern Trends in Engineering and Research www.ijmter.com e-issn No.:2349-9745, Date: 28-30 April, 2016 Estimation of Shelf Life Of Mango and Automatic Separation Dhananjay Pawar 1* Dr. Vishal Wankhede 2 1 * Department of E&TC, SNJB s KBJ COE, Chandwad, 423101, Maharashtra(MH), India 2 pawar.djcoe@snjb.org Department of E&TC, SNJB s KBJ COE, Chandwad, 423101, Maharashtra(MH), India wankhede.vacoe@snjb.org Abstract- The Project Features a Computer vision based system for automatic segregation and grading of mango (magnifera indica L.) based on mainly three factors which are weight, color and color maturity. the main purpose behind implementing this computer vision based system is to replace human efforts by automation. The manual inspection creates problem in maintaining consistency and uniformity in grading and sorting. hence to increase the speed of the process as well as to maintain the consistency, uniformity, accuracy and efficiency, a prototype computer vision based automatic mango grading and sorting system is developed. this automated system captures the images from CCD camera placed on the top of conveyor belt carrying mangoes, then it processes the images in order to collect several relevant features which are sensitive to weight color and color maturity of the mango. Finally parameters of the individual classes are estimated using MATLAB software. For fulfillment of export requirements s essential to determine fruit features such Color and brightness, level of maturity and weight. A methodology to estimate these characteristics from a set of images of Mango samples is presented in this project. The methods used to determine level of Brightness and level of maturity resulted an overall accuracy of 90% and for weight estimation method, error margin did not exceed 7 grams Keywords: Mango; Shelf life; Conveyor; MATLAB; Maturity Level. I. INTRODUCTION India has emerged as the largest producer of fruits in the world, with an annual production of 57.60 million tones over an area of 5.2 million hectares, as against world production of 300 million tones. India produces around 50% of the world s mangoes. India is the largest producer of mango, with an annual production of about 10 million tones. More than 1000 varieties are grown in India, of which only 20 are commercially cultivated. Even though India is the largest producer of the choicest varieties of mango, the country is not a major player in the export market for either fresh mango or processed mango products. Out of 10 million tones, around 40,000 tons of mangos are exported as fresh fruit, accounting for about 40% of production. The main Objective of Project is to estimate Shelf life of Mangoes by using nondestructive Methods. Application of Machine vision based system, aimed to replace manual based technique for grading and sorting of Mango. For the fresh market the main factor affecting consumer preference is physical appearance to maximize return, great effort is expended ensuring that the appearance best matches a particular market. In the past years the technology was not much advanced which involved the parameters such as current and voltage were measured one after the other with the help of voltmeter, ammeter, etc. So, this type of measurement of parameters was waste of time or did not much accurate results. Parameters to be measured: 1. Color. 2. Weight. @IJMTER-2016, All rights Reserved
3. Skin color brightness. Load cell is used for weight measurement, as this load cells will measure the weight of mango which will be placed on conveyor belt. Camera is used for capturing the images of mango and for measuring the skin brightness and color. These operations are performed with help of MATLAB simulator. Then with help of some calculations mangoes are separated into basic categories and separation is carried out with the help of conveyor belt. Finally we get separated mangoes which can be distributed in various areas across countries and across the world as per their shelf life. II. SYSTEM DEVELOPMENT. Fig 1: Block Diagram for estimation of specifications and separation 2.1 Mango Input to System is Mango fruit of which we have to separate into different categories as shown in block diagram. These samples are feed at Beginning of Conveyor 1 which have Load Cell as a beginning Platform. 2.2 Conveyer 1 Conveyor 1 consists of Instruments such as Load cell, Camera. Load cell is used to calculate weight of sample mango. Camera is used to capture images of sample mangoes. Controller circuit have control on camera. Camera captures images only if mango is present beneath camera. We are estimating three parameters on conveyor 1 that are: Color shade Weight Color Maturity 2.3 Computation of shelf life This process is mainly carried out by MATLAB software with help of PC. This block includes calculations that give annual value determining shelf life of sample mango. This calculation uses results given by other three parameter estimation methods which are weight estimation, color shade measurement and color maturity estimation. @IJMTER-2016, All rights Reserved 799
2.4 Computer Database Computer database consists of following database: 1. Images of Standard Sample mangoes at different level of maturity. 2. Standard Values Of color components taken from standard samples at different level of maturity 3. Values of weight of mangoes of various volumes and various ages. 2.5 Controller Circuit Controller circuit is used to control various sections of project such as Camera, Conveyor 2. Two IR pairs are interfaced with controller circuit. IR pair 1 is used to detect presence of mango on load cell to control pushing shaft. IR pair 2 is used to detect presence of mangoes beneath camera in image acquisition chamber. It also controls conveyor 2 which is used to segregate mango samples as per their shelf life. 2.6 Conveyer 2 Conveyor 2 is used to separate mango samples as per their shelf life. It consists of three containers, each on to carry separate categorized mangoes. Conveyor 2 moves on command of controller circuit. 3.1 Image Acquisition III. OBJECTIVES OF SYSTEM Fig 2: Image acquisition chamber The proposed methods begin with a set of acquired images of the fruit. For image acquisition, the camera uses video adapters connected to the computer. This connection uses the serial port with transfer standard IEEE 1394. High resolution allows for better detail analysis, but since increasing the resolution also increases processing loads, we decided to set the image resolution at 480x352 pixels. For image acquisition, a diffuse front lighting system with four white-light 6-watt lamps is used as shown in gig below. In order to determine the main characteristics of the fruit from the images, we followed a series of steps: pre-processing, weight estimation, degree of maturation, and spots measurement. In each of the steps, the procedures used MATLAB 2010a software functions, and Image Acquisition Toolbox functions. @IJMTER-2016, All rights Reserved 800
figure shows structural view of image acquisition chamber consisting of camera. We are using IR LED as a Transmitter and IR sensor as a Receiver to detect presence of mango beneath camera. As conveyor belt is continuously moving, but we need to capture only the images of mango, so we used IR pair for the same. IR pair detects presence of mango and sends signal to MATLAB through PC. 4.1 Pre-Processing IV. MATHEMATICAL MODEL We applied traditional methods for image enhancement, de-noising and edge detection. This stage seeks to separate the fruit from the image background. To achieve this separation we performed color segmentation. In order to design a more accurate method to achieve this objective, we studied different color spaces, especially those in which color information is distinguishable from the intensity component, such as HSI (Hue, Saturation and Intensity) or YCbCr (Luminance and Chroma components) color spaces. We chose the YCbCr color space because it allows for more effective segmentation than other color spaces, resulting in a clear distinction between fruit and background colors. Colors in a mango fruit are usually in the green to red color spectrum. In the YCbCr color space, this spectrum range is in the second and third quadrants as shown in fig. 3, in the negative value segment [-1, 0] of the Cb channel. This means that by analyzing this region separation between fruit and background is straightforward. Due to the fact that only the Cb channel information is relevant, it is not necessary to make a complete transformation from an RBG image. For efficiency, the following function obtains the Cb channel information from an RGB image: b(x,y)=1 /255 (-37.979(x,y)-74.203(x,y)+112(x,y))+128 where, R(x,y), G(x,y) and B(x,y) are in the integer range of [0,255]. Fig 3: YCbCr color space and quadrants 4.2 Weight Estimation We can derive the weight of fruit from volume estimation. The analysis of spatial geometry is the basis for volume estimation, from which the total volume is the sum of the volumes of all sections formed by a transverse cut along the length of the fruit as shown in figure 4 Then, if we take a small enough h value (height of each cross section), it is possible to approximate the volume of each section to the elliptic cylinder volume, thus: V c = π a b h @IJMTER-2016, All rights Reserved 801
V total = V c(i)..for i = 1 to k V total = πaibih= πh aibi. for i = 1 to k Fig 4: Cross section of the fruit. 4.3 Maturity Level Estimation The level of maturity is a decisive factor in fruit classification for export and a key factor to determine conservation policies. We propose a non-invasive method to determine the maturity level by analyzing the color of the surface of a fruit. This analysis provides a criterion for classification according to the specifications for classification by color described in NTC 5139. For color treatment, we selected the HSI color space because it allows for better discrimination between the color information of the first two channels: the Hue-Saturation and the intensity channels. The following function permits the transformation of RGB to HSI space: H=cos -I ( ) ( ) ( ) ( )( ) S = 1-[3Min(R,G,B) / R+G+B] I = (1/3)(R+G+B) Once we get the transformation to HSI, we analyzed distribution variations by histogram analysis in a set of images. This analysis showed that the mean value of channels H and S is sensitive to changes in the color states. The training set had 15 fruits, each one with two features, hue and saturation mean, that were estimated by using a set of 5 images for each fruit, and the classes were defined by expert concept. The prior probabilities for classes were estimated from the relative frequencies of the classes in the training data. Finally, the category to which the fruit belongs according to the input parameters of hue and saturation can be defined by means of the Predict method. V. CONCLUSION In this Paper, we have proposed a method for detecting the shelf life of mango and automatic separation. Firstly, we surveyed all the information about alphonso mangoes and its various characteristics. Then using MATLAB coding, we converted the images into gray and binary images. @IJMTER-2016, All rights Reserved 802
We collected mathematical formulae to calculate various parameters of mango. We applied these formulae on tomatoes so as to check if correct results are obtained. References [1] Michael Barnes, Tom Duckett, Grzegorz Cielniak Boosting minimalist classifiers for blemishe detection in potatoes", International conference on image and vision computing, New Zealand, vol.24, pp. 397-402, 2009. [2] Jarimopas B, and Jaisin N. An experimental Machine Vision system for sorting sweet Tamarind", Journal of Food Engineering, vol. 89(3), pp. 291-297, 2008. [3] Adolfo Moreno Bermdez, Deimer Ballesteros Padilla,Germn Snchez Torres, Image analysis for automatic feature estimation of the Mango(Mangifera indica l.) fruit", Universidad del Magdalena (Colombia), Volume no.31,no.1, 2013. [4] Chandra Sekhar Nandi, Bipan Tudu, Chiranjib Koley An Automated Machine Vision Based System for Fruit Sorting and Grading", International conference on sensing technology, vol.6, pp. 195-200, 2012. [5] Unmesh Shashikant Sagare, Sunil N. Kore Fruits Sorting And Grading Based On Color And Size", International Journal of Emerging Technologies in Computational and Applied Sciences, vol.1, pp. 94-96, 2013. [6] Y.Zhao, D. Wang, and D. Qian \Machine Vision based image analysis for the estimation of Pear external quality", Second International Conference on Intelligent Computation Technology and Automation, pp 629-632, 2009. [7] D. J. Lee, J. K.Archibald, and Guangming Xiong. Rapid color grading for fruit quality evaluation using direct color mapping", IEEE Trans. Autom. Sci. Eng., vol. 8(2), pp. 292-302, 2011. [8] Z. Varghese, C. T. Morrow, P. H. Heinemann, H. J. Sommer, Y. Tao, and R. W. 50 Crassweller, Automated inspection of golden delicious apples using color computer vision", American Society of Agricultural Engineers, 16, 1991(7002). [9] B. K. Miller, and M. J. Delwiche, A color vision system for Peach grading", Transactions of the ASAE, vol. 32(4), pp. 484-490, 1989. @IJMTER-2016, All rights Reserved 803