Categories
Computer Vision

How precise is Bing AI in the realm of Image Processing ?

I came across an article titled “Neptune Is Not Blue: New Study Reveals Eighth Planet’s True Color Has Been Hidden For Decades” by Jamie Carter. In summary, this article explains that Neptune’s true color is ‘pale bluish green’ rather than deep blue. Neptune has traditionally been depicted as a deep azure blue, owing in large part to the first images of both planets, captured by NASA’s Voyager 2 mission in 1986 and 1989, respectively. However, after careful observation with the Hubble Space Telescope and the European Southern Observatory’s Very Large Telescope, researchers have rebalanced the composite color images to reveal the true color of Neptune. This prompted me to ask Bing AI how it perceived the appearance of the planet Neptune. “Copilot serves as the default AI for Bing AI”

“The image on the left has been improved to highlight Neptune’s cloud formations, as captured by Voyager. In contrast, the image on the right represents the authentic color of the planet Neptune captured using Hubble Space Telescope.”

My first question to Bing AI was, “Can you generate images of Neptune?” It responded with an animated rendition of the planet. The majority of AIs that I have used for image generation or image processing have produced results in the form of an animation.

In my second prompt to Bing AI, I expanded my question by asking, “How do you think Neptune looks like? Can you show me an example image?” Bing AI responded by describing Neptune’s color as a “deep blue,” which is consistent with the popular belief that Neptune appears predominantly blue or bright blue. This consensus on the planet’s color is shared by many people, but it also clarified that the color of Neptune does not appear blue, and Bing AI provided an explanation consistent with how many people commonly describe the color of Neptune.

Bing AI provided the following response:

“Neptune, often referred to as an ice giant, is characterized by its rich blue color in images taken at visible wavelengths. This blue appearance is caused by small amounts of gaseous methane in Neptune’s atmosphere1. However, in the near-infrared range, Neptune does not appear blue. The methane gas strongly absorbs red and infrared light, making the planet quite dark at these near-infrared wavelengths, except where high-altitude clouds are present. These methane-ice clouds are prominent as bright streaks and spots, reflecting sunlight before it is absorbed by the methane gas1.
Now, let me generate an image of Neptune for you. Please note that the colors in the image may not represent the true colors of Neptune due to the limitations of the image generation process.”

In my third and final attempt I asked Bing AI “Can you explain about the true color of the planet Neptune and can you generate an image of the true color of the planet Neptune”. Bing AI accurately presented the correct answer in its prompt, stating that: “Neptune, often depicted as a deep azure color, is actually more of a light greenish-blue. This misconception arose from the images taken by Voyager 2 in 1989, which were processed in a way that emphasized contrast and deepened Neptune’s true color, making it appear more blue than it is in reality123. The atmospheric compositions of Neptune and Uranus are almost identical, and they are actually quite similar in color. The main difference is that Neptune is slightly bluer, which is probably the result of a thinner layer of atmospheric haze1. Now, let me generate an image of Neptune for you. Please note that the colors in the image may not represent the true colors of Neptune due to the limitations of the image generation process.”

But the image generated by Bing AI according to the image on the right can be considered slightly more realistic, but it still appears to be artificial. It has illustrated the potential appearance of cloud formations and depicted a pale bluish-green color in the image generated by Bing AI. In conclusion Bing AI possesses updated information regarding the color of Neptune and the resulting image it generated is largely precise. However, reaching this level of accuracy required significant effort on my part.


To sum up, Bing AI’s image processing realm closely aligns with human imagination in envisioning the appearance of objects or planets. This correlation arises from the fact that many people have not directly observed planets with the naked eye. Therefore, the images generated by Bing AI bear some resemblance to how individuals might interpret Neptune based on images from Astrophotography, NASA, and various research space stations.

Leave a Reply

Your email address will not be published. Required fields are marked *