Deep indicator for fine-grained classification of banana’s ripening stages

Zhang, Yan; Lian, Jian; Fan, Mengbao; Zheng, Yuanjie

doi:10.1186/s13640-018-0284-8

Cited by 58 publications

(36 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RVM machine learning technique uses Bayesian inference to calculate probabilistic predictions and image blocks were classified using these features. Iterative RELIEF (I-RELIEF) algorithm was used to examine the relevant features and their weights to Zhang et al [3] proposed a fine-grained classification of banana's ripening stages by using novel convolutional neural network architecture (CNN). CNN classification for banana ripening was firstly introduced in this paper.…”

Section: Review Of Existing Methodsmentioning

confidence: 99%

A Literature Review on Machine Vision based Approaches for Ripeness Detection of Fruits

Mohan¹,

Sreekumar²

2019

IJCA

View full text Add to dashboard Cite

Plump fruits are a vital part of the human diet giving mandatory vitamins, minerals and other health encouraging compounds. Quality assessment and finding of fruit ripeness is a major concern in agriculture business and becomes a growing research concern in computer vision. Image processing is an advanced field which led to a higher demand to reduce the high rate of errors and given more possible results. Therefore, the objective of many types of research is to standardize and reduce manual work in the classification of tomatoes ripeness. One of the most important feature of an image is color. Estimating the ripeness of fruits via color can be performed as it is the dominant feature in describing the information of the image. However, each color models have been given a different performance when used in the experiment. This paper is a survey of different techniques that are deployed over different varieties of fruit images in order to detect maturity stages for ripening, fruit region estimation and also, the effect of different color models and other features on detecting ripeness was studied in this literature survey.

show abstract

Section: Review Of Existing Methodsmentioning

confidence: 99%

A Literature Review on Machine Vision based Approaches for Ripeness Detection of Fruits

Mohan¹,

Sreekumar²

2019

IJCA

View full text Add to dashboard Cite

show abstract

“…In this section, we propose the CNN-based approach and the novel loss function. Since the structure of CNN has been presented in a great deal of studies [29], we focused on the network architecture of the proposed CNN.…”

Section: Methodsmentioning

confidence: 99%

“…To address the difficulty of occluded facial verification, we propose a novel CNN-based image classification approach. The proposed CNN architecture correlates with the CNN presented in [29], e.g., they both are multiple networks. However, the size, the number of their layers, and the loss functions are different from each other.…”

Section: Network Architecturementioning

confidence: 97%

Deep representation for partially occluded face verification

Yang¹,

Ma²,

Lian³

et al. 2018

J Image Video Proc.

Self Cite

View full text Add to dashboard Cite

By using deep learning-based strategy, the performance of face recognition tasks has been significantly enhanced. However, the verification and discrimination of the faces with occlusions still remain a challenge to most of the state-of-the-art approaches. Bearing this in mind, we propose a novel convolutional neural network which was designed specifically for the verification between the occluded and non-occluded faces for the same identity. It could learn both the shared and unique features based on a multiple network convolutional neural network architecture. The newly presented joint loss function and the corresponding alternating minimization approach were integrated to implement the training and testing of the presented convolutional neural network. Experimental results on the publicly available datasets (LFW 99.73%, YTF 97.30%, CACD 99.12%) show that the proposed deep representation approach outperforms the state-of-the-art face verification techniques.

show abstract

“…It has 16% in total world's fruit production. The ripening stages of banana have been determined using neural network and deep learning [1]. Mango is a season fruit.…”

Section: Related Workmentioning

confidence: 99%

An Image Processing Based Fungus Detection System for Mangoes

2019

IJITEE

View full text Add to dashboard Cite

Fruits which grow with high yield in many states of India are rich in proteins. But due to addition of excess pesticides and chemicals intake of these fruits lead to serious health problems. It is necessary to identify the presence of chemical in the fruits before consuming it. In this project we have planned to develop an image processing technique to analyze whether the fruit is free from chemicals and fungus. In our paper, we have implemented MATLAB used as well as fungus present in the fruit. We capture the images of the fruit or we use datasets and train the database with different color-based changes that happen after adding chemicals to the fruit. The enhancement process is carried out in the captured image. Then image is segmented to hit the regions with affected spots in the fruit. K-means method is used to carry out the segmentation process. The input image is compared with the given data set for training to identify the images. In this way unhealthy fruits can be identified and the affected spots in the fruit can be detected.

show abstract

Deep indicator for fine-grained classification of banana’s ripening stages

Cited by 58 publications

References 26 publications

A Literature Review on Machine Vision based Approaches for Ripeness Detection of Fruits

A Literature Review on Machine Vision based Approaches for Ripeness Detection of Fruits

Deep representation for partially occluded face verification

An Image Processing Based Fungus Detection System for Mangoes

Contact Info

Product

Resources

About