IMAGE RECOGNITION ON FLOWER CLASSIFICATION USING NEURAL NETWORK
Keywords:
Classification, Image Recognition, Artificial Neural Network, Segmentation, feature extractionAbstract
The integration of computer technology in various fields including agriculture has facilitated modernization and automation. One of the significant applications of computer technology in agriculture is the classification of flowers. Proper identification and classification of flowers are essential as they play a crucial role in the ecosystem. Morphological features of flowers and leaves are the basis of their classification. This study aims to propose a flower image classification system using an artificial neural network for four different types of flowers, namely sunflower, rose, lily, and dandelion. The proposed system can have various applications in floriculture and the classification of other plants. An image of a flower serves as the input to the system, and it is used to segmented based on the dataset images of similar flowers with comparable features. The artificial neural network is then trained using 125 samples of the four different groups of flowers. Using an artificial neural network, the proposed system achieves an accuracy of around 82%. This high accuracy is attributed to the integration of both DWT and GLCM techniques in the proposed system allows the extraction of accurate textural features, which enable efficient flower classification. The use of an artificial neural network in the proposed system allows the system to learn and improve its classification accuracy. The system can also be updated with additional data to improve its accuracy further. The proposed flower image classification system using an ANN is a significant development in the field of floriculture and the classification of plants. The system’s accuracy of approximately 82% showcases its potential for application in real-world scenarios. The system can be further enhanced by incorporating additional data to improve its accuracy and potentially be utilized in other areas of plant classification.
References
Electronics & Telecommunication, SVERI’s College of Engineering, Pandharpur, India and Mukane, S. M. (2013). Flower classification using neural network-based image processing. IOSR Journal of Electronics and Communication Engineering, 7(3), 80-85.
Saitoh, T., & Kaneko, T. (2000). Automatic recognition of wild flowers.Volume 2, 507-510.
Nilsback, M.-E. (n.d.). An automatic visual Flora - segmentation and classification of flower images. University of Oxford.
Arribas, J. I., Sánchez-Ferrero, G. V., Ruiz-Ruiz, G., & Gómez-Gil, J. (2011). Leaf classification in sunflower crops by computer vision and neural networks. Computers and Electronics in Agriculture, 78(1), 9-18.
Lee, H.-H., & Hong, K.-S. (2017). Automatic recognition of flower species in the natural environment. Image and Vision Computing, 61, 98–114.
Hiary, H., Saadeh, H., Saadeh, M., & Yaqub, M. (2017). Flower classification using deep convolutional neural networks. In 2017 International Conference on Engineering and Technology (ICET) (pp. 1-5). IEEE. doi: 10.1109/ICEngTechnol.2017.8309404.
Liu, Y., Zhou, D., Tang, F., Meng, Y., & Dong, W. (2017). Flower classification via convolutional neural network. Paper presented at the 2017 2nd International Conference on Image, Vision and Computing (ICIVC). doi: 10.1109/ICIVC.2017.7975069.
Cengil, E., & Çınar, A. (2020). Multiple classification of flower images using transfer learning. Computer Science, 66(2), 239-251.
Cengil, E. & Cinar, A. (2021). Multiple classification of flower images using transfer learning. In 2021 International Conference on Artificial Intelligence and Data Processing (IDAP) (pp. 1-5). Malatya, Turkey: IEEE. doi: 10.1109/IDAP52435.2021.9456527.
Guru, D. S., Sharath, Y. H., & Manjunath, S. (2014). Texture Features and KNN in Classification of Flower Images. International Journal of Computer Applications, 85(9), 42-46.
Mohanty, A. K., & Bag, A. (2017). Image mining for flower classification by genetic association rule mining using GLCM features. 2017 International Conference on Intelligent Computing and Control Systems (ICICCS), Madurai, India, pp. 128-133. doi: 10.1109/ ICCONS.2017.8252122.
Andono, P. N., Rachmawanto, E. H., Herman, N. S., & Kondo, K. (2018). Orchid types classification using supervised learning algorithm based on feature and color extraction. 2018 6th International Conference on Information and Communication Technology (ICoICT), Bandung, Indonesia, pp. 109-114. doi: 10.1109/ ICoICT.2018.8539246.
Almogdady, H., Manaseer, S., & Hiary, H. (2021). A Flower Recognition System Based On Image Processing And Neural Networks. International Journal of Computer Science and Information Security, 19(3), 8-14.
Li, Z., Zhang, J., Zhang, J., & Huang, K. (2016). Flower recognition using color and texture features. Neurocomputing, 173, 219-226.
Rahman, M. M., Lu, J., & Islam, M. R. (2018). Flower recognition using deep convolutional neural network and support vector machine. International Journal of Computer Applications, 181(46), 30-36.
Wang, S., Yan, Y., & Fang, G. (2019). Feature fusion-based flower recognition using improved deep convolutional neural network. In 2019 2nd International Conference on Robotics, Automation and Artificial Intelligence (ICRAAI) (pp. 297-301). IEEE.
Zhang, X., Ma, J., Zhang, Y., & Li, J. (2020). A novel deep learning-based flower recognition system. IEEE Access, 8, 92569-92578.
