Tag: ddn

Learn how to create a custom document scanning dataset using Python and OpenCV — capture real photos, save quadrilateral annotations, and synthesize training images for edge detection and deep learning.

Step-by-step SwiftUI document scanning tutorial for iOS and macOS. Detect document edges in real time, normalize scanned images, and display results using Dynamsoft Capture Vision SDK.

Step-by-step Python tutorial for detecting document edges, auto-cropping scanned documents, and correcting orientation using Dynamsoft Capture Vision SDK and Tesseract OCR on Windows, Linux, and macOS.

Step-by-step tutorial to integrate document scanning in a Python Flask app using the Dynamsoft Document Normalizer SDK. Capture documents via webcam, detect edges server-side with OpenCV, and rectify scanned pages in a web browser.

Detect duplicate scanned document images in JavaScript using Tesseract.js OCR and Levenshtein distance. Includes TypeScript code, online demo, and full source code.