MNet: A Framework to Reduce Fruit Image Misclassification

Abstract

Fast and accurate fruit classification is a major problem in the farming business. To achieve the same, the most popular technique used to build a classification model is "Transfer Learning", in which the weights of pretrained models are used in a new model to solve different but related problems. This technique assures the fast model building with a reduction in generalization error. After testing a popular image classification models namely, DenseNet161, InceptionV3, and MobileNetV2 on created dataset in which a "misclassification" is observed as a major problem which is overlooked by many researchers. This paper proposed a novel framework called "MNet: Merged Net" which not only improves the accuracy, but also addresses the misclassification problem. In this framework, the fruit classification problem is divided into small problems and build a separate model for each. In the final stage, the results of these models are combined. Two models called as FC_InceptionV3 (Fruit Classification InceptionV3) and MFC_InceptionV3 (Merged Fruit Classification InceptionV3) are created based on popular pretrained model InceptionV3. MFC_InceptionV3 is based on proposed framework. In this work, a dataset consisting of 12000 color images of top fruits in India with "Good" and "Bad" quality labels was created and published. The dataset consists of a total of 12 classes. The proposed framework MNet is tested on the most popular deep learning model called InceptionV3. The results of InceptionV3, FC_InceptionV3, and MFC_InceptionV3 are compared. The experimental results shows that the MFC_InceptionV3 model achieved 99.92% accuracy and moderates the image misclassification problem.

Dry fruit image dataset for machine learning applications

“…Although there are many datasets on fruits and vegetables, those working on machine learning models and/or apps need a dataset on dry fruits due to the numerous health benefits they offer [ 1 , 2 , 3 , 10 ]. Machine learning models can correctly categorize and identify the type of data when a decent dataset is available [ 5 , 6 , 7 , 8 , 11 , 12 ]. The dataset is used for cutting-edge dry fruit-related research, education, and medical applications such as spotting fungal infections in dry fruit [9] .…”

FruitNet: Indian fruits image dataset with quality for machine learning applications

“…In the agro-industry fast and accurate fruit classification is the highest need. The fruits can be classified into different classes as per their external features like shape, size and color using some computer vision and deep learning techniques [4] , [5] , [6] , [7] , [8] . The FruitNet dataset was created to include Indian fruits along with its quality parameters for those which are highly consumed or exported as per [9] .…”

VegNet: Dataset of vegetable quality images for machine learning applications

“…The greatest requirement in the agro-industry is for quick and accurate vegetable classification. Utilizing computer vision and deep learning techniques, the veggies may be divided into many groups based on their outward characteristics, such as shape, size, and color [5] , [6] , [7] , [8] , [9] . Vegetables with quality parameters for those that are heavily consumed or exported in accordance with Agricultural & Processed Food Products Export Development Authority (APEDA) are included in this VegNet dataset [10] .…”