What does a convolutional neural network recognize in the moon?

TL;DR

This study investigates how a convolutional neural network recognizes shapes in lunar maria patterns, revealing that recognition depends on image context and cultural influences, contrasting with human perception.

Contribution

The paper demonstrates how CNN recognition of lunar patterns varies with image context, highlighting differences from human perception influenced by culture.

Findings

CNN recognizes lunar shapes differently based on image context.

Recognition depends on lunar region included in the image.

Humans are influenced by cultural perceptions in pattern recognition.

Abstract

Many people see a human face or animals in the pattern of the maria on the moon. Although the pattern corresponds to the actual variation in composition of the lunar surface, the culture and environment of each society influence the recognition of these objects (i.e., symbols) as specific entities. In contrast, a convolutional neural network (CNN) recognizes objects from characteristic shapes in a training data set. Using CNN, this study evaluates the probabilities of the pattern of lunar maria categorized into the shape of a crab, a lion and a hare. If Mare Frigoris (a dark band on the moon) is included in the lunar image, the lion is recognized. However, in an image without Mare Frigoris, the hare has the highest probability of recognition. Thus, the recognition of objects similar to the lunar pattern depends on which part of the lunar maria is taken into account. In human recognition, before we find similarities between the lunar maria and objects such as animals, we may be persuaded in advance to see a particular image from our culture and environment and then adjust the lunar pattern to the shape of the imagined object.