Identification of Age Factor of Fruit (Tomato) using Matlab- Image Processing Prof. Pramod G. Devalatkar 1, Mrs. Shilpa R. Koli 2 1 Faculty, Department of Electrical & Electronics Engineering, KLS Gogte Institute of Technology, Belagavi 2 Student, Department of Computer Networks, Vishvesharaya Technical University, Belagavi Abstract With the advances in preservation of fresh food products like fruits, vegetables etc. It is now essential parameter to obtain the advance visualization techniques for the safety of fruit and vegetables. It requires the implementation of a set rule for individual product based on its various features called upon as a algorithms for safe keeping. This research paper represents the analysis of an age factor of Tomato based on one of the visual feature of Tomato that is based on color. The performance of the product is been analyzed based on the color of Tomato i.e Red, Green or Orange. The performance of an algorithm was analyzed and discussed by observing the various sample products. Keywords RGB image, Gray Scale image, Region of Interest (ROI), Edge Detection, Background Subtraction etc I. INTRODUCTION Plants have become an important source of energy and are a fundamental piece in the puzzle to solve the problem of global warming crisis. Agriculture is an art and with the help of science it is being now far easier and efficient for farmer to obtain greater output at the end of growing time. With advances in insecticides and anti- bacterial for drop in reduction of loss in crop has made farmers to increase their interest in looking towards farm positively. There are various techniques had been brought in to use for surveillance and security of farms from various environmental disasters and harms due to human beings. The use of systems for observation on farms and intimation to the owner was being in greater use from past so many years. In the past few years the use of surveillance systems using video cameras was in greater use in both industries and farms also. This research paper focuses on visualization of tomato for age parameter using image analysis. Fruits find numerous uses in both fresh and artificial processed forms. Processed forms include jam, paste and juice. Export of these processed products of fruits yield more income for the country. In order to get good quality of processed products the quality of fruits should be good. Identifying good and bad quality fruits in industries manually is the main obstacle as it is time consuming and for high labour cost. Therefore it is very important to identify the quality of fruits for the purpose of its usage by an automatic sorting machine for various necessities in industries. To overcome this problem, image processing method in industries has become a major source in recent years. Using MATLAB software as a tool in image processing, we can find the quality of Fruits using various algorithms. Finally after collecting lot of trained data bases, we have proposed certain range. With these ranges we can identify the quality of Fruits, whether it is good or bad During ripening procedure, the color of tomatoes varies from mature green, yellow and orange to intense red color. Then a robot should pick up only red tomatoes and leave others. Many studies have been conducted to develop an expert system for picking red tomatoes. Most of them were based on color feature because the color is as an effective factor of the tomato quality. The ripeness of a tomato can be estimated through its surface color and traditionally consumers prefer a quite-red tomato. Color of a tomato is a major factor in determining its ripeness @IJRTER-2016, All Rights Reserved 7
The purpose of the present work is to analysis the age factor of the specimen using the technique mentioned that which will try to reduce the labor work and maintain the accuracy at its maximum, also the proposed technique is allow the process to become faster as compare to the manual system. It uses the various sub image processing algorithms to perform analysis. II. METHODOLOGY The purpose of this work is to develop a segregation system for analysis of tomatoes based on color based image analysis. Image processing would give more accurate result in detecting durability of tomato. The method uses the image processing tool for analyzing the desired age factor. We used Image Processing technique in MATLAB to identify the color of image and indicate to operator whether the tomato is ready to use or still could be stored. An images could be obtained live from camera interfaced to PC and can be accessed using image acquisition toolbox in Matlab during future work. In developing a system following stages were involved. ROI (Region of Interest) Edge detection. Colour Detection. RGB value & Maximum value comparison. Analysis based on maximum color value. Block diagram for detection of age factor of a tomato using Matlab image processing is as shown in Fig.1 below. Image as a Input Pre-Processing Segmantation Feature Machining Feature Training Feature Extraction III. Fig.1 Block Diagram of proposed system IDENTIFICATION STAGES An evaluation of system for the identification of age parameter of a tomato has several stages for obtaining accuracy A. Region of Interest (ROI): A region of interest (ROI) is a portion of an image that need to focus for further analysis. For choosing an proper area of interest out of entire image we need to define a ROI by creating a binary mask, which is a binary image that is the same size as the image that need to process with pixels that define the ROI set to 1 and all other pixels set to 0. It is possible to define more than one ROI for single image. The regions can be geographic in nature, such as polygons that encompass contiguous pixels, or they can be defined by a range of intensities. ROI is the process of applying a filter to a region in an image, where a binary mask defines the region. roifilt2 if the function used to filter an ROI in an image. Function roifilt2 specify: @IJRTER-2016, All Rights Reserved 8
Input grayscale image to be filtered Binary mask image that defines the ROI Filter (either a 2-D filter or function In roifilt2 filters the input image and returns an image that consists of filtered values for pixels where the binary mask contains 1s and unfiltered values for pixels where the binary mask contains 0s. This type of operation is called masked filtering. B. Edge Detection: Edge detection is a type of image segmentation techniques which determines the presence of an edge or line in an image and outlines them in an appropriate way. The main purpose of edge detection is to simplify the image data in order to minimize the amount of data to be processed. There are many ways to perform edge detection. However, the majority of different methods may be grouped into two main categories as Gradient based edge detection and Laplacian based edge detection. Depending on the requirement for horizontal, vertical of tangential edges for further analysis and appropriate method is to be chosen out of sobel, canny, perwitt or robert cross method. Figure below shows various edge detection outputs along with specimen image for consideration. Fig. 2 Matlab Output for different types of edge detection2. C. RGB Value & Maximum Value Comparison RGB is one of the formats of color images. Here the input image is represented with three matrices of sizes matching the image format. The three matrices in each image correspond to one of the color red, green or blue. An RGB value of the input image can be obtain using image processing tool in Matlab. Based on the specified RGB amount for the image, maximum content of color can be obtained using maximum value for R G or B. Identification for RGB content for the specimen image is as shown below with code. Matlab Code: i=imread('green.jpeg'); y1=imresize(i,1/200); r1=y1(:,:,1); g1=y1(:,:,2); b1=y1(:,:,3); % read input image %resize the input image %determines the red colour in the image %determines the green colour in the image @IJRTER-2016, All Rights Reserved 9
l1=r1(1,2,1); %rgb to gray convesion m1=g1(1,2,1); %rgb to gray convesion n1=b1(1,2,1); %rgb to gray convesion r=l1 %move information l1 to r g=m1 %move information m1 to g b=n1 %move information n1 to b A=[r g b]; %forming A matrix M=max(A) %detemine max value from matrix A R=(r==M) % r value is compare with max value G=(g==M) % g value is compare with max value B=(b==M) % b value is compare with max value if (R==1) fprintf('colour is red','fontsize',fontsize) elseif (G==1) fprintf('colour is Green','fontsize',fontsize) end subplot(1,1,1); imshow(i); title('input IMAGE','fontsize',fontsize); Fig. 3 Input image green.jpeg @IJRTER-2016, All Rights Reserved 10
Fig. 4 Matlab output for the above code For the input image which is green in nature image processing analysis has been carried out which gives output as shown in Fig. 4 with R (245), G ( 249) and B (236). Based on the execution made for the code written above an comparison is been carried out which gives maximum value as M (249) for the Fig 4 and value of M (249) it is clear that the image under consideration is Green one. Based on this the judgment has been made that the image under consideration is green in nature which is true as seen in Fig. 3 from input image. Hence it is cleared that the image is green one that means the resultant image tomato can be hold at least for a week of a time. Further it is clear that a code can be used efficiently for age judgment and classification of tomato based on color for quality as well. Further the process has been tested for an array of samples for which the results are been produced as shown below:
Fig.5 Array of images Fig.6 Result of Array @IJRTER-2016, All Rights Reserved 12
IV. CONCLUSION The image processing can be used more conveniently for the detection of age factor of tomato based on color. We have shown that the proposed color identification of tomato using image processing performs well in both small and large areas such as agricultural and industries. Using MATLAB software as a tool in image processing it is possible to develop a prototype of an application for a relatively very short time. Image analysis provides a consistent, accurate and reliable method to estimates disease severity. Multiple images can be used to identify the color (Red and Green) in very fast. In the future work, the system can be made more optimized with the two or more color analysis of fruits such as apples. REFERENCES 1. R.Kalaivani, Dr.S. Muruganand,Dr.Azha.Periasamy : Identifying the quality of tomatoes in image processing using matlab, ISO 3297,Vol. 2, Issue 8, August 2013. 2. Mahdi M. Ali, Ahmed Al-Ani, Derek Eamus and Daniel K.Y: a new image processing based technique to determine chlorophyll in plants, American-Eurasian J. Agric. & Environ. Sci., 12 (10): 1323-1328, 2012 ISSN : 1818-6769,DOI:.2012.12.10.1917 3. Basvaraj.S. Anami,J.D. Pujari, Rajesh.Yakkundimath: dentification and Classification of Normal and Affected Agriculture/horticulture Produce Based on Combined Colour and Texture Feature Extraction, ISSN: 2231-4946, Vol I, Issue III, September 2011. 4. Shan-e-Ahmed Raza, Gillian Prince, John P. Clarkson, Nasir M. Rajpoot : Automatic Detection of Diseased Tomato Plants Using Thermal and Stereo Visible Light Images. 5. Alok Mishra, Pallavi Asthana, Pooja Khanna, The quality identification of fruits in image processing using matlab, pp 2321-7308. 6. Jayme Garcia Arnal Barbedo, Digital image processing techniques for detecting, quantifying and classifying plant diseases. 7. Brendon J. Woodford, Nikola K. Kasabov and C. Howard Wearing(Department of Information Science and HortResearch).: Fruit image analysis using wavelets. 8. Davínia Font Calafell, Dr. Jorge Palacín Roca: Application of image processing methodologies for fruit detection and analysis Issue 30 th of July of 2014. @IJRTER-2016, All Rights Reserved 13