You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Android example of document scanning with OpenCV featuring edge detection, perspective correction, and image enhancement. Demonstrates implementation of camera preview, image processing, and OCR integration for document scanner applications.
Automatically extract documents from images and perspectively correct them with classic computer-vision algorithms. In maintenance mode. Check out its successor at:
Photograph a document, get a real scan — straightened, cleaned and searchable. Runs on your own device, in the browser or as an Android and iOS app; nothing is uploaded. No sign-up, no watermark, no page limit.
OpenScanVision is an open-source Android computer vision engine for document, form, and card scanning. It provides perspective correction, template alignment, QR decoding, and OMR recognition for offline applications.
This is a projective geometry project aiming to correct perspective distortions in images after a user identifies pairs of horizontal and vertical lines.
Zero-tap document rectification for Android — automatic boundary detection, perspective correction, and clean rectangular output using classical CV with planned ML enhancement
Modular OCR pipeline for live-camera documents/screens. Auto-aligns perspective, blocks obstructions, and extracts text using interchangeable deep-learning models.
一个专为太阳能电池板等阵列结构设计的智能分割标注工具,支持均匀分割和基于波形分析的智能分割。A semi-automatic annotation tool for regular array structures such as photovoltaic panels, featuring uniform splitting and waveform-based smart segmentation.
For freely cropping and correcting images in batches, especially suitable for image editing with unfixed camera positions, where each image requires a unique designated cropping region.
An OpenCV project that automatically detects a document in an image and finds its corners for perspective correction. This notebook demonstrates a practical computer vision pipeline using morphological operations, Canny edge detection, and contour analysis to prepare for a "bird's-eye view" transformation.