The week's pick
Random Articles
Reseach Article
A Comparative Study of Deep Learning based Image Classification Models for Material Classification
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 183 - Number 17 |
| Year of Publication: 2021 |
| Authors: Atharva Ajay Gokhale |
10.5120/ijca2021921518
|
Atharva Ajay Gokhale . A Comparative Study of Deep Learning based Image Classification Models for Material Classification. International Journal of Computer Applications. 183, 17 ( Jul 2021), 30-34. DOI=10.5120/ijca2021921518
Abstract
There are many instances in multiple fields where multiple objects are being used together and each of which can be composed of different materials. Hence the identification of these objects and their classification based on the material of which they are built is required. Due to recent developments in the field of Computer Vision and with the advent of multiple image classification technologies, it has enabled modern computer systems to play a role in this classification and identification process. A computer-based system making use of machine learning or deep learning models can be trained to differentiate between and hence classify objects into one of the multiple categories of materials under consideration. This can mainly be done in scenarios where objects of different materials are needed to be separated from one another in order to give further separate treatment to each one of them. A number of image classification models and algorithms can be used for such types of use cases by predetermining the classes to be considered where each class can correspond to a unique kind of material. The models trained for these purposes can be used to predict the class pertaining to a material when an image of an object is given as input to it for identification. Further, in order to make the models or the learning algorithm more robust, the number of classes can be increased in order to cover a greater number of different types of materials. Following this, one can also compare among similar image classification models that can be used for the mentioned use case scenario in order to gain insights for determining the best model for the said purpose among a variety of models. Hence, this paper aims towards giving insights for the determination of a better model by considering a comparison or a comparative study of three different image classification models which are based on neural networks.
References
- Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556.
- He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 770-778).
- Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., & Wojna, Z. (2016). Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 2818-2826).
- Hussain, M., Bird, J. J., & Faria, D. R. (2018, September). A study on cnn transfer learning for image classification. In UK Workshop on computational Intelligence (pp. 191-202). Springer, Cham.
- Tammina, S. (2019). Transfer learning using vgg-16 with deep convolutional neural network for classifying images. International Journal of Scientific and Research Publications (IJSRP), 9(10), 143-150.
- Agarwal, T., & Mittal, H. (2019, August). Performance comparison of deep neural networks on image datasets. In 2019 Twelfth International Conference on Contemporary Computing (IC3) (pp. 1-6). IEEE.
- Krishna, S. T., & Kalluri, H. K. (2019). Deep learning and transfer learning approaches for image classification. International Journal of Recent Technology and Engineering (IJRTE), 7(5S4), 427-432.
- Sharma, N., Jain, V., & Mishra, A. (2018). An analysis of convolutional neural networks for image classification. Procedia computer science, 132, 377-384.
- Pak, M., & Kim, S. (2017, August). A review of deep learning in image recognition. In 2017 4th international conference on computer applications and information processing technology (CAIPT) (pp. 1-3). IEEE.
- Lee, S. J., Chen, T., Yu, L., & Lai, C. H. (2018). Image classification based on the boost convolutional neural network. IEEE Access, 6, 12755-12768.
- Szegedy, C., Ioffe, S., Vanhoucke, V., & Alemi, A. A. (2017, February). Inception-v4, inception-resnet and the impact of residual connections on learning. In Thirty-first AAAI conference on artificial intelligence.
- Khan, A., Sohail, A., Zahoora, U., & Qureshi, A. S. (2020). A survey of the recent architectures of deep convolutional neural networks. Artificial Intelligence Review, 53(8), 5455-5516.
Index Terms
Keywords