JFBarryLi / ITSegmenterLinks
Image Text Segmentation using FAST corner detection and DBSCAN clustering with k-d tree data structure
☆13Updated 6 years ago
Alternatives and similar repositories for ITSegmenter
Users that are interested in ITSegmenter are comparing it to the libraries listed below
Sorting:
- Docker version API for MODNet-model Human Matting☆16Updated last year
- Detect paper corners in picture / video☆13Updated 5 years ago
- FETNet: Feature Erasing and Transferring Network for Scene Text Removal☆33Updated 2 years ago
- Using FCN to segment the book's content and background, then dewarping the pages,☆21Updated 4 years ago
- Perspective Transformation for Indoor Image Aesthetic Enhancement☆12Updated 5 years ago
- ☆41Updated 3 years ago
- PyTorch implementation of BMVC2022 paper Masked Vision-Language Transformers for Scene Text Recognition☆29Updated 2 years ago
- MODNet for clothing matting☆16Updated 4 years ago
- STIRER: A Unified Model for Low-Resolution Scene Text Image Recovery and Recognition -- ACMMM 2023☆14Updated 11 months ago
- SOTA image super-resolution in JavaScript/Wasm using an ONNX-ported SwinIR model☆35Updated 2 years ago
- Group project for 11-785 Fall 2022 @ CMU☆10Updated 2 years ago
- ☆82Updated 2 years ago
- Synthetic identity documents dataset☆28Updated 7 months ago
- ☆62Updated last year
- DoodleFormer: Creative Sketch Drawing with Transformers (ECCV22)☆29Updated 3 years ago
- A pipeline focused on the in-painting of text in images. For example the removal of subtitles in a screenshot of a movie.☆15Updated 3 years ago
- Some portrait matting models designed for mobile device.☆16Updated 6 years ago
- Repository for Intrinsic Decomposition of Document Images In-the-Wild (BMVC '20)☆49Updated 2 years ago
- ☆62Updated 3 months ago
- ☆29Updated 3 years ago
- SOTA Document Image Enhancement - T2T-BinFormer: Effective Document Image Enhancement Using tokens-to-token Transformer Network☆24Updated last year
- Automatic Color Palette Selection (Python)☆32Updated 9 years ago
- Implementation of paper: CLIPFont: Texture Guided Vector WordArt Generation☆15Updated 3 years ago
- WikiTableSet: A largest publicly available image-based table recognition dataset in three languages built from Wikipedia☆31Updated 4 months ago
- This code provides the implementation of Semantic Human Matting paper (by Alibaba)☆12Updated 6 years ago
- This repository is a concise collection of well known deep learning based document binarization models.☆25Updated 2 years ago
- ShabbyPages is a state-of-the-art corpus of born-digital document images with both ground truth and distorted versions appropriate for us…☆62Updated 7 months ago
- The official code for “DeepEraser: Deep Iterative Context Mining for Generic Text Eraser”, TMM, 2024.☆44Updated last year
- An Enhanced Implementation of the Colour Transfer Method Proposed by E Reinhard et al.☆57Updated 3 years ago
- [ACM MM 2020] Exploring Font-independent Features for Scene Text Recognition☆44Updated 4 years ago