Researchers Develop Convolutional Neural Network Algorithm for Vegetable Classification

Researchers at Universitas Islam Negeri have developed a Convolutional Neural Network (CNN) algorithm to classify vegetable types using a dataset of 31,000 images. The study aimed to explore the potential of the CNN algorithm for image classification and its application in the agricultural sector. The researchers achieved a highest validation accuracy of 95.83% and a testing accuracy of 93% using the TensorFlow and Keras libraries.

Key Takeaways:

The study classified 15 vegetable types using a dataset of 31,000 images, achieving a highest validation accuracy of 95.83% and a testing accuracy of 93%.
The researchers used the CNN algorithm with convolutional, pooling, and dense layers to recognize visual features such as color, texture, and shape.
The study demonstrated the potential of the CNN algorithm for image classification and its application in the agricultural sector.
The researchers suggested that the technology could address challenges in differentiating visually similar vegetable types, making it valuable in real-world agricultural or educational settings.
The study was published in the Paradigma journal and is available online at https://doi-org.sdpl.idm.oclc.org/10.31294/p.v27i1.7577.
The researchers include Wilis Arum Karunia, Safriya Murni Puspita, Dwi Rolliawati, and Ahmad Yusuf.

Statistics:

The researchers used a dataset of 31,000 images to classify 15 vegetable types.
The CNN algorithm achieved a highest validation accuracy of 95.83% and a testing accuracy of 93%.
The study demonstrated the potential of the CNN algorithm for image classification and its application in the agricultural sector.

Sources:

Paradigma journal, "Classification of Vegetable Types Using the Convolutional Neural Network (CNN) Algorithm," Universitas Bina Sarana Informatika, 2025.
https://doi-org.sdpl.idm.oclc.org/10.31294/p.v27i1.7577.