Develop an API that searches through a large directory (thousands) of images to find similar matches
Budget: $50 – $500 USD
I'd like some help developing an efficient API that can quickly search through a local folder of images that could potentially be in the thousands, and return a result of closest matches (if there are any). There could be some indexing or hashing needed to build this solution in a way that is optimised enough to not take more than a few seconds to return a result. If that's a one-off process that's done once an image is added to the directory I'd like that to be included as well.
The API could be written i Python as it seems most open source libraries for this purpose are in Python. But I'm open to suggestions. It's important that a website can query the API by sending an image through and get matches back in return with a percentage similarity rating, and that this result is accurate of course.
Here are some guides and projects that I've stumbled across that seem to do what I'm looking for.
https://pypi.org/project/duplicate-images/
https://medium.com/@somilshah112/how-to-find-duplicate-or-similar-images-quickly-with-python-2d636af9452f
The API could be written i Python as it seems most open source libraries for this purpose are in Python. But I'm open to suggestions. It's important that a website can query the API by sending an image through and get matches back in return with a percentage similarity rating, and that this result is accurate of course.
Here are some guides and projects that I've stumbled across that seem to do what I'm looking for.
https://pypi.org/project/duplicate-images/
https://medium.com/@somilshah112/how-to-find-duplicate-or-similar-images-quickly-with-python-2d636af9452f