Enhanced Attention-CNN for Classifying Fruits and Vegetables
Author Information
Author(s): Zeshan Aslam Khan, Waqar Muhammad, Khalid Mehmood Cheema, Bakar Mahmood Ali Abu, Ain Quratul Ain, Chaudhary Naveed Ishtiaq, Alshehri Abdullah, Alshamrani Sultan S., Zahoor Raja Muhammad Asif
Primary Institution: National Yunlin University of Science and Technology
Hypothesis
Can an enhanced attention-CNN model improve the classification accuracy of fruits and vegetables using visual features?
Conclusion
The proposed EA-CNN model achieved a classification accuracy of 98.1% on the Fruit-360 dataset and 96% on the Fruit Recognition dataset, outperforming existing models.
Supporting Evidence
- The EA-CNN model outperformed baseline models in terms of accuracy and computational cost.
- The model achieved a test accuracy of 98.1% on the Fruit-360 dataset.
- The proposed model demonstrated substantial performance on the Fruit Recognition dataset with a generalized accuracy of 96%.
- Utilizing the entire Fruit-360 database significantly enhanced the model's classification capabilities.
Takeaway
This study created a smart computer program that can tell different fruits and vegetables apart by looking at their pictures, and it does this really well!
Methodology
The study used a simplified CNN architecture with an attention mechanism and a customized pooling technique to classify fruits and vegetables from the Fruit-360 dataset.
Limitations
The study may be limited by the quality and diversity of the datasets used for training and testing.
Statistical Information
P-Value
p<0.05
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website