- 【Updated on May 12, 2025】 Integration of CiNii Dissertations and CiNii Books into CiNii Research
- Trial version of CiNii Research Automatic Translation feature is available on CiNii Labs
- Suspension and deletion of data provided by Nikkei BP
- Regarding the recording of “Research Data” and “Evidence Data”
An Image Classification Model that Learns Image Features and Numerical Information
-
- Suzuki Yuta
- Kanazawa University
-
- Hatano Toshiki
- Kanazawa University
-
- Tsuneda Toi
- Kanazawa University
-
- Kuyoshi Daiki
- Kanazawa University
-
- Yamane Satoshi
- Kanazawa University
Search this article
Description
In recent years, deep neural network technology has been developing rapidly, especially in the field of image recognition. However, since deep neural networks learn images based on pixel values, they can only learn the features of the image and not the meta-information that the image has. In this paper, we focused on the differences between image features and meta-information. For example, 0 and 9 are relatively similar in terms of image characteristics, but there is significant difference in terms of the numbers they actually mean. In contrast, 3 and 4 are relatively dissimilar in terms of image features, but the difference is small in terms of the values they actually mean. In order to solve problems like this example, this paper proposes a method for learning based not only on the features of the image, but also on the numerical information that the image has. Experiments were conducted on the MNIST and Kannada-MNIST datasets using three different models: DNN, CNN, and RNN. As a result, the numerical error is smaller in the proposed model than in the baseline.
Journal
-
- International Journal of Networking and Computing
-
International Journal of Networking and Computing 11 (2), 426-437, 2021
IJNC Editorial Committee
- Tweet
Keywords
Details 詳細情報について
-
- CRID
- 1390007149514363008
-
- NII Article ID
- 130008063317
-
- ISSN
- 21852847
- 21852839
-
- Text Lang
- en
-
- Data Source
-
- JaLC
- Crossref
- CiNii Articles
- OpenAIRE
-
- Abstract License Flag
- Allowed