An Image Classification Model that Learns Image Features and Numerical Information

Yuta Suzuki, Toshiki Hatano, Toi Tsuneda, Daiki Kuyoshi, Satoshi Yamane


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.


Deep Learning; Image Recognition; Meta Learning

Full Text:



  • There are currently no refbacks.