A cost effective tomato maturity grading system using image processing for farmers

Abstract

Maturity grading or in other words classifying the ripeness of a fruit, based on its color or texture, forms a very important process to be carried out by agriculturists and the food processing industry worldwide. Current techniques mainly involve manual inspection, which leads to erroneous classification, which in turn would cause economical losses due to inferior produce entering the market chain. A loss of yield during storage may also occur with this type of classification, since it would lead to wrong expiry date predictions as well. Several methodologies to automate this process exist but involve highly expensive setups and complicated procedures which are not a viable solution, especially for the agriculturists of a developing nation. In this paper we discuss a cost effective maturity grading system for one of the most popular fruit in the world -the tomato. A novel setup utilizing inexpensive material and image processing algorithms to identify the six important stages of tomato ripening have been presented. All algorithms were designed and developed using Simulink, a part of MATLAB 2011b on a 2.5 GHz CPU. An overall 98% accuracy was achieved with respect to maturity grade detection and an execution speed of greater than 7.6 times was obtained in comparison with two other popular methodologies.

Video Oculographic System using Real-Time Video Processing

“…The face holder consists of 3 parts [1] the face holder [2] the base [3] camera holder. The face holder is cut in a crescent fashion so the patient can mount his face on it without any movement of the face.…”

“…Frames are extracted from these video frames using inbuilt functions in java, as frames are nothing but the entities of video file. [3] Then each frame is analyzed and only the eye part is segmented from rest of the face features in order to count the blinks. The normal blink is differentiated from the intended blink based on the intensity i.e., how long the eyes are kept close.…”

Improvement of Convolutional Neural Network Accuracy on Salak Classification Based Quality on Digital Image

“…Getting the optimal threshold k which maximizes function or equivalent maximizing value of can use the following equation [6]:…”

“…(4) is a betweet-class variance with average of level from image histogram from and which is zeroth-order and first-order cumulative in k level of global threhsold. Otsu 192 thresholding intended to find the optimal threshold value of an image by finding the maximum value using the following equation [6]:…”

Digital Image Processing Application on Shallots Quality Determination

“…A research in citrus sorting can identify defects using multispectral computer vision. Results showed contributions where the detection accuracy of anthracnose increased from 86% by using NIR images; and the accuracy of green mould was increased from 65% to 94% by using images of fluorescence (2).An automatic defect detection in fruit has been proposed using HSV and RGB color space model to give image segmentation area of defect fruit (4). A classification of apples using three color cameras and segmentation using multi-threshold method may reduce unjustified acceptance of blemish apples (5).…”