DCNN-Based Vegetable Image Classification Using Transfer Learning: A Comparative Study

Ahmed, Mumtaz; Mamun, S M Abdullah Al; Asif, Asif Uz Zaman

doi:10.1109/icccsp52374.2021.9465499

Cited by 30 publications

(17 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dataset of this paper is from the public dataset on Kaggle 10 . The dataset consists of 15 common vegetables, including, carrots, cauliflower, cucumber, papaya, potatoes, pumpkin, radish, etc.…”

Section: Dataset and Environmentmentioning

confidence: 99%

Lightweight vegetable detection algorithm based on improved YOLOv5

Guo

zhang²

2023

Third International Conference on Computer Vision and Data Mining (ICCVDM 2022)

View full text Add to dashboard Cite

With the rapid development of deep learning, vegetable detection based on computer vision in smart supermarkets can save a lot of manpower. To solve the problem that the reported target detection algorithm fails to balance detection accuracy and model size well, a lightweight vegetable detection method that is based on yolov5 model was proposed in this work. The method firstly improved the detection accuracy by adding a fusion attention mechanism (Convolutional Block Attention Module) in the backbone part, and then reduces the model parameters by replacing the normal convolution in the network with Ghost convolution to ensure the accuracy at the same time. The accuracy of localization was improved by using Alpha-IoU as the loss function of the bounding box regression. The experimental results show that the improved method achieves an average accuracy of 92.5%, which is 3.2% higher than yolov5, and the total model parameters are 6.1 MB, which is 1.0 MB lower than yolov5, meeting the requirement of balancing detection accuracy and model size.

show abstract

Section: Dataset and Environmentmentioning

confidence: 99%

Lightweight vegetable detection algorithm based on improved YOLOv5

Guo

zhang²

2023

Third International Conference on Computer Vision and Data Mining (ICCVDM 2022)

View full text Add to dashboard Cite

show abstract

“…The dataset used in this study is obtained from a publicly accessible dataset on Kaggle [11]. The dataset is composed of 15 popular vegetables, including carrots, cauliflower, cucumbers, papaya, potatoes, pumpkin, and radish.…”

Section: Dataset and Environmentmentioning

confidence: 99%

Vegetable image recognition algorithm based on Swin transformer

Guo,

Zhang

2023

Third International Conference on Signal Image Processing and Communication (ICSIPC 2023)

View full text Add to dashboard Cite

Target detection techniques based on computer vision can be used for vegetable recognition and classification, which can effectively avoid the time-consuming and labor-intensive problems faced by manual operations at the large supermarket checkout lanes and produce market. In order to accurately recognize vegetable image, an improved Faster R-CNN recognition technique based on the Swin Transformer is proposed in this paper. The backbone network is replaced by the Swin Transformer to improve the accuracy and efficiency of feature extraction. The ROI Align is employed to protect the integrity of image data. Furthermore, the more effective GIoU loss function is used to simplify the training process in order to reduce the computational resources and time consuming during training. Finally, the experimental results show that the proposed algorithm has an accuracy improvement of 6.1% compared with the previous methods.

show abstract

“…Support Vector Machine (SVM) for Mango scoring demonstrated 100% accuracy [16], while Grapevine detection demonstrated 97.70% accuracy [17]. Convolutional Neural Network (CNN) for vegetable recognition demonstrated 97.58% accuracy [18], the classification of fruits and vegetables demonstrated an accuracy of 95.6% [19] and 92,23% [20], the diagnosis of plant diseases demonstrated an accuracy of 99.53% [4], the classification of the type of rice demonstrated an accuracy of 99.31%, for the classification of the variety of Barley demonstrated an accuracy of 93% [21], identification of diseases on Cucumber leaves demonstrated an accuracy of 94.65% [5], vegetable classification demonstrated an accuracy of 96.5% [22], 99% [23] and 98,58% [24], for fruit classification demonstrated 98% accuracy [25], and for banana ripeness classification demonstrated 96.18% accuracy [26]. Multilayer Deep CNN (MDCNN) for fruit detection demonstrated 97.4% accuracy [27], Deep CNN (DCNN) for Cucumber disease recognition demonstrated 93.4% accuracy [28], and CNN + SVM for fruit detection demonstrated 97.50% accuracy [29].…”

Section: Introductionmentioning

confidence: 99%

“…2019 [20] 92. 23 13 species and 2700 images, CNN (classifier), GoogleNet (pre-trained). 2019 [5] 94.65 6 diseases and 600 images, CNN (classifier), Combining dilated convolution with global pooling using GPD, AlexNet (pre-trained).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Image Classification of Vegetable Quality using Support Vector Machine based on Convolutional Neural Network

Nurrani

Nugroho

Heranurweni

2023

J. RESTI (Rekayasa Sist. Teknol. Inf.)

View full text Add to dashboard Cite

As part of an effort to develop intelligent agriculture, new methods for enhancing the quality of vegetables are being continually developed. In recent years, the Convolutional Neural Network (CNN) has shown to be the most successful and extensively used approach for identifying the quality of pre-trained vegetables. However, this method is time-consuming due to the scarcity of truly large, significant datasets. Using a pre-trained CNN model as a feature extractor is a straightforward method for utilizing CNNs' capabilities without investing time in training. While, Support Vector Machine (SVM excels at processing data with tiny dimensions and significantly larger instances. SVM more accurately classifies the flatten/vector feature supplied by the CNN fully connected layer with small dimensions. In addition, implementing Data Augmentation (DA) and Weighted Class (WC) for data variety and class imbalance reduction can improve CNN-SVM performance. The research results show highest accuracy during training always achieves 100% across all experimental options. With an average accuracy of 69.66% in the testing process and 92.51% in the prediction process for all data, the experimental findings demonstrate that CNN-SVM outperforms CNN in terms of accuracy performance in all possible experiments, with or without WC and or DA approach.

show abstract

DCNN-Based Vegetable Image Classification Using Transfer Learning: A Comparative Study

Cited by 30 publications

References 9 publications

Lightweight vegetable detection algorithm based on improved YOLOv5

Lightweight vegetable detection algorithm based on improved YOLOv5

Vegetable image recognition algorithm based on Swin transformer

Image Classification of Vegetable Quality using Support Vector Machine based on Convolutional Neural Network

Contact Info

Product

Resources

About