Implementation of Method for Identification of Ripening Factor of Fruit Based on Improved FCM and CNN

Abstract

In this paper we are designing new approach for detection of artificially ripened fruit. The overall approach is based on modified fuzzy C-Means (FCM) algorithm and improved convolutional neural network (CNN). The stated method will be applicable for regular and irregular shaped fruit image which are captured in natural light. Traditional FCM algorithm is powerful and used in segmentation to segment images. Study shows that FCM can be applicable for irregular shape fruit images but shows poor results for images taken in outside environment. Our modified approach will overcome the drawback of traditional FCM and will be suitable for images which are captured in outside varying intensity light. CNN is powerful tool which can be applied on predefined dataset. We know that fruits are having different shape and size; and ripening factor varies from fruit to fruit. The dataset available of fruits are captured in uniform light; so we have to modify the parameters of existing dataset as per our requirement before applying CNN. Our modified approach will make small changes in parameters of dataset before applying it to CNN; and finally CNN will show ripening factor.