This Flask app scans a folder of images and makes the text inside them fully searchable, using open-source Tesseract OCR.
This could be helpful for someone who has a massive folder of screenshots or scanned documents and wants to find what they need without uploading everything to a cloud service. This app runs 100% locally on your own machine.
Instead of scrolling through hundreds of thumbnails to find a specific image, you can just search for the text contained in the image. You can use broad substring searches, or toggle “Exact Match” to look for specific whole words.
The dashboard includes a term frequency analyzer. It automatically displays the top 50 most frequently occurring words in all the extracted text, ignoring common words like the, and, or, etc.
As you add new images to the folder, you won’t need to rebuild the whole database. Simply click “Sync New Images” to process any new files, and make them searchable too.
Demonstration with a mock dataset.