I'm writing a script that converts my list of bookmarked words into SRS, with audio and image on it. Now, I'm writing a script to fetch an image from Google Image, but the images I got are mostly useless.

For example, when I searched for an image on a French word proviseur, I got the following list, which is a good representation of the word (principal).

enter image description here

But when I searched for a word nuire (meaning harm as a verb), the result is useless, with the top result being the conjugation table of nuire.

enter image description here

Or when I searched for the word fourni (well-equipped), the result is full of an island called fourni island.

enter image description here

Unfortunately, the most words are much closer to the latter than the former, once you leap over the very basic words (such as eat, dog, etc...) (but the results of nouns usually work well).

So how can I make an appropriate image for my SRS?

  • You say that you are writing a script. Does that mean you want to automate the assignment of images?
    – Tsundoku
    May 23, 2019 at 12:30
  • @ChristopheStrobbe Exactly, though I feel more and more like it is very difficult to implement.
    – Blaszard
    May 23, 2019 at 12:33
  • Personally, I don't see how it can be done using just an algorithm (as opposed to AI). When I was creating Anki decks for Chinese, I often had difficulty finding an image that was sufficiently unambiguous. For example, an image that expresses the concept of "cold" when you also need flashcards for "snow" and "ice". Sometimes I put two images on the same flashcard for better disambiguation.
    – Tsundoku
    May 23, 2019 at 12:47
  • 1
    @ChristopheStrobbe Initially I wrote a Python script that fetches images with the word and its language as input, but only found out that many images are not what I was looking for due the reasons I stated. Now I consider only automating the process of opening the search result of the image and saving it, while I choose the image manually.
    – Blaszard
    May 23, 2019 at 12:58
  • For verbs, you might start with an example sentence. The more abstract a verb is, the harder it will be to visualize in a picture. For your example, I looked in a dictionary and found this example sentence: "L'alcool nuit à la santé." The idea of that sentence as a whole is probably easily visualized with a picture, but it's probably not something you could do with a script (you'd have to select the image that best evokes that idea).
    – Brandin
    Aug 26, 2021 at 9:37


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.