Perspective recovery of text using transformed ellipses

Tried to run the program on some images, for some it worked, but on many I get this error:

python3 unproject_text.py lp8.png

abs_area_cutoff = 18.7572 got 6 contours with 1 small. got bounding rect -281 163 583 58 got bounding rect -305 186 586 12 got bounding rect 263 197 3 1 Traceback (most recent call last): File "unproject_text.py", line 503, in main() File "unproject_text.py", line 495, in main SRH = skew_detect(img, contours, RH) File "unproject_text.py", line 468, in skew_detect res = scipy.optimize.minimize_scalar(f, (-2.0, 0.0, 2.0)) File "/usr/local/lib/python3.6/site-packages/scipy/optimize/_minimize.py", line 653, in minimize_scalar return _minimize_scalar_brent(fun, bracket, args, **options) File "/usr/local/lib/python3.6/site-packages/scipy/optimize/optimize.py", line 2108, in _minimize_scalar_brent brent.optimize() File "/usr/local/lib/python3.6/site-packages/scipy/optimize/optimize.py", line 1892, in optimize xa, xb, xc, fa, fb, fc, funcalls = self.get_bracket_info() File "/usr/local/lib/python3.6/site-packages/scipy/optimize/optimize.py", line 1880, in get_bracket_info raise ValueError("Not a bracketing interval.") ValueError: Not a bracketing interval.

The image I tried was: https://liorazi.github.io/lp8.png

Open Source research tool to search, browse, analyze and explore large document collections by Semantic Search Engine and Open Source Text Mining & Text Analytics platform (Integrates ETL for document processing, OCR for images & PDF, named entity recognition for persons, organizations & locations, metadata management by thesaurus & ontologies, search user interface & search apps for fulltext search, faceted search & knowledge graph)

Open Semantic Search https://opensemanticsearch.org Integrated search server, ETL framework for document processing (crawling, text extraction, text a

684 Jan 6, 2023

Code related to "Have Your Text and Use It Too! End-to-End Neural Data-to-Text Generation with Semantic Fidelity" paper

DataTuner You have just found the DataTuner. This repository provides tools for fine-tuning language models for a task. See LICENSE.txt for license de

81 Jan 1, 2023

Handwritten Text Recognition (HTR) system implemented with TensorFlow (TF) and trained on the IAM off-line HTR dataset. This Neural Network (NN) model recognizes the text contained in the images of segmented words.

Handwritten-Text-Recognition Handwritten Text Recognition (HTR) system implemented with TensorFlow (TF) and trained on the IAM off-line HTR dataset. T

27 Jan 8, 2023

Code for generating synthetic text images as described in "Synthetic Data for Text Localisation in Natural Images", Ankush Gupta, Andrea Vedaldi, Andrew Zisserman, CVPR 2016.

SynthText Code for generating synthetic text images as described in "Synthetic Data for Text Localisation in Natural Images", Ankush Gupta, Andrea Ved

1.8k Dec 28, 2022

cv2.findContours fix

in the 135 line changed this

_, contours, hierarchy = cv2.findContours(work, cv2.RETR_CCOMP, cv2.CHAIN_APPROX_NONE)

to this

contours, hierarchy = cv2.findContours(work, cv2.RETR_CCOMP, cv2.CHAIN_APPROX_NONE)

it's because in a previous version of opencv that function used to return 3 values, now it returns just 2 values

opened by sumanmichael 0
Value Error: not enough values to unpack

Python 3 / OSX

$ python3 unproject_text/unproject_text.py samples/hd/IMG_1234.jpg Traceback (most recent call last): File "unproject_text/unproject_text.py", line 503, in main() File "unproject_text/unproject_text.py", line 490, in main contours, hierarchy = get_contours(img) File "unproject_text/unproject_text.py", line 135, in get_contours cv2.CHAIN_APPROX_NONE) ValueError: not enough values to unpack (expected 3, got 2)

opened by maxhallhatesm3 1
"ValueError: Not a bracketing interval." on some images

Tried to run the program on some images, for some it worked, but on many I get this error:

python3 unproject_text.py lp8.png

abs_area_cutoff = 18.7572 got 6 contours with 1 small. got bounding rect -281 163 583 58 got bounding rect -305 186 586 12 got bounding rect 263 197 3 1 Traceback (most recent call last): File "unproject_text.py", line 503, in main() File "unproject_text.py", line 495, in main SRH = skew_detect(img, contours, RH) File "unproject_text.py", line 468, in skew_detect res = scipy.optimize.minimize_scalar(f, (-2.0, 0.0, 2.0)) File "/usr/local/lib/python3.6/site-packages/scipy/optimize/_minimize.py", line 653, in minimize_scalar return _minimize_scalar_brent(fun, bracket, args, **options) File "/usr/local/lib/python3.6/site-packages/scipy/optimize/optimize.py", line 2108, in _minimize_scalar_brent brent.optimize() File "/usr/local/lib/python3.6/site-packages/scipy/optimize/optimize.py", line 1892, in optimize xa, xb, xc, fa, fb, fc, funcalls = self.get_bracket_info() File "/usr/local/lib/python3.6/site-packages/scipy/optimize/optimize.py", line 1880, in get_bracket_info raise ValueError("Not a bracketing interval.") ValueError: Not a bracketing interval.

The image I tried was: https://liorazi.github.io/lp8.png

opened by liorazi 5
Error with the usage command

m-c02sh1f0g8wl:unproject_text-master arg000m$ python unproject_text.py deskew0.jpg Traceback (most recent call last): File "unproject_text.py", line 503, in main() File "unproject_text.py", line 490, in main contours, hierarchy = get_contours(img) File "unproject_text.py", line 135, in get_contours cv2.CHAIN_APPROX_NONE) ValueError: need more than 2 values to unpack

could you help me with this ?

opened by anuragreddygv323 3

Perspective recovery of text using transformed ellipses

Related tags

Overview

unproject_text

Requirements

Usage

You might also like...

Code related to "Have Your Text and Use It Too! End-to-End Neural Data-to-Text Generation with Semantic Fidelity" paper

Handwritten Text Recognition (HTR) system implemented with TensorFlow (TF) and trained on the IAM off-line HTR dataset. This Neural Network (NN) model recognizes the text contained in the images of segmented words.

Code for generating synthetic text images as described in "Synthetic Data for Text Localisation in Natural Images", Ankush Gupta, Andrea Vedaldi, Andrew Zisserman, CVPR 2016.

This can be use to convert text in a file to handwritten text.

Text page dewarping using a "cubic sheet" model

Handwritten Text Recognition (HTR) using TensorFlow 2.x

Text language identification using Wikipedia data

Text Detection from images using OpenCV

Comments

cv2.findContours fix

Value Error: not enough values to unpack

"ValueError: Not a bracketing interval." on some images

Error with the usage command

Owner

Matt Zucker

Deskew is a command line tool for deskewing scanned text documents. It uses Hough transform to detect "text lines" in the image. As an output, you get an image rotated so that the lines are horizontal.

An Implementation of the alogrithm in paper IncepText: A New Inception-Text Module with Deformable PSROI Pooling for Multi-Oriented Scene Text Detection

Code for the paper STN-OCR: A single Neural Network for Text Detection and Text Recognition

text detection mainly based on ctpn model in tensorflow, id card detect, connectionist text proposal network

keras复现场景文本检测网络CPTN: 《Detecting Text in Natural Image with Connectionist Text Proposal Network》；欢迎试用，关注，并反馈问题...

Detecting Text in Natural Image with Connectionist Text Proposal Network (ECCV'16)

AdvancedEAST is an algorithm used for Scene image text detect, which is primarily based on EAST, and the significant improvement was also made, which make long text predictions more accurate.https://github.com/huoyijie/raspberrypi-car

OCR system for Arabic language that converts images of typed text to machine-encoded text.

OCR, Scene-Text-Understanding, Text Recognition

Total Text Dataset. It consists of 1555 images with more than 3 different text orientations: Horizontal, Multi-Oriented, and Curved, one of a kind.