Fruit Classification Based on Six Layer Convolutional Neural Network

Lu, Siyuan; Lu, Zhihai; Aok, Soriya; Graham, Logan

doi:10.1109/icdsp.2018.8631562

Cited by 35 publications

(15 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Hence, 40 kinds of fruits were classified successfully using VGG16 and SVM with an accuracy of 99.95%, which is better than the existing methods [45,46]. Based on image region selection and improved object proposals [45], five types of fruits were detected with a miss rate of 0.0377.…”

Section: Comparison Of Accuracy Score (%) With Other Image Classificamentioning

confidence: 93%

“…Based on image region selection and improved object proposals [45], five types of fruits were detected with a miss rate of 0.0377. Again, 9 types of fruits were classified using the six-layer convolutional layer and achieved 91.4% of accuracy [46]. So, considering the number of varieties of fruits and achieved accuracy is far better than the existing method.…”

Section: Comparison Of Accuracy Score (%) With Other Image Classificamentioning

confidence: 98%

See 1 more Smart Citation

Fruit Recognition using Support Vector Machine based on Deep Features

Behera¹,

Rath²,

Sethy³

2020

Karbala International Journal of Modern Science

View full text Add to dashboard Cite

Fruit recognition with its variety classification is a promising area of research. This research is useful for monitoring and categorizing the fruits according to their kind with the assurance of fast production chain. In this research, we establish a new high-quality dataset of images containing the five most popular ovalshaped fruits with their varieties. Recent work in deep neural networks has led to the development of many new applications related to precision agriculture, including fruit recognition. This paper proposes a classification model for 40 kinds of Indian fruits by support vector machine (SVM) classifier using deep features extracted from the fully connected layer of the convolutional neural network (CNN) model. Also, another approach based on transfer learning is proposed for recognition of Indian Fruits. The experiments are carried out in six most powerful deep learning architectures such as AlexNet, GoogleNet, ResNet-50, ResNet-18, VGGNet-16 and VGGNet-19. So, the six deep learning architectures are evaluated in two approaches, which makes 12 classification model in total. The performance of each classification model is assessed in terms of accuracy, sensitivity, specificity, precision, false positive rate (FPR), F1 score, Mathew correlation (MCC) and Kappa. The evaluation results show that the SVM classifier using deep learning feature provides better results than their transfer learning counterparts. The deep learning feature of VGG16 and SVM results in 100% in terms of accuracy, sensitivity, specificity, precision, F1 score and MCC at its highest level.

show abstract

Section: Comparison Of Accuracy Score (%) With Other Image Classificamentioning

confidence: 93%

Section: Comparison Of Accuracy Score (%) With Other Image Classificamentioning

confidence: 98%

Fruit Recognition using Support Vector Machine based on Deep Features

Behera¹,

Rath²,

Sethy³

2020

Karbala International Journal of Modern Science

View full text Add to dashboard Cite

show abstract

“…Filters are matrix of dimension axb. And these filters are moved across the image in order to find the parts where there is possibility of a feature to be present [16].…”

Section: Convolvingmentioning

confidence: 99%

“…It reduces size of output layer height and width, as it just extracts features which is required from a particular region ignoring other. Pooling Layer [16][15] can be of 2 types: Max and average Pooling. In max pooling, there is a window of some resolute size and it is moved over the output of previous layer and this window finds out the maximum value inside the existing window.…”

Section: Pooling Layermentioning

confidence: 99%

See 1 more Smart Citation

Autonomous Decision Making for a Vehicle

Isha¹,

Mamtesh²

2019

IJCA

View full text Add to dashboard Cite

It includes Deep Learning techniques using convolutional neural networks for getting the predictions and probabilities for the best decision that has to be made while driving a car like lane detection, traffic signals recognition and their localization and simultaneously developing a steering model to help to take decision regarding steering wheel, throttle thus stimulate a car like humans. In this paper, lane detection is the main concern is to move the steering in appropriate direction with proper angle and the problem is solved using convolutional neural networks via creating a model which then is trained over some collected training data of steering decisions on a track in a simulated environment.

show abstract

Fruit Image Recognition Based on Census Transform and Deep Belief Network

Liu

et al. 2020

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

View full text Add to dashboard Cite

Fruit image recognition plays an important role in the fields of smart agriculture and digital medical treatment. In order to overcome the disadvantage of the deep belief networks (DBN) that ignores the local structure of the image and is difficult to learn the local features of the image, and considering that the fruit image is affected by the change of illumination, we propose a new fruit image recognition algorithm based on Census transform and DBN. Firstly, the texture features of fruit images are extracted by Census transform. Secondly, DBN is trained by Census features of fruit images. Finally, DBN is used for fruit image recognition. The experimental results show that the proposed algorithm has a strong feature learning ability, and the recognition performance is better than the traditional recognition algorithm.

show abstract

Fruit Classification Based on Six Layer Convolutional Neural Network

Cited by 35 publications

References 36 publications

Fruit Recognition using Support Vector Machine based on Deep Features

Fruit Recognition using Support Vector Machine based on Deep Features

Autonomous Decision Making for a Vehicle

Fruit Image Recognition Based on Census Transform and Deep Belief Network

Contact Info

Product

Resources

About