Skip to main content

Locating texts in images using computer vision

Project description

text-detector (algorithm accuracy work in progress)

Locating texts in images using machine vision algorithms

This project aims to use only image processing techniques to locate text regions in the image. More detailed information about the approach is given this link


pip install -r requirements.txt


import matplotlib.patches as mpatches
import matplotlib.pyplot as plt
from import imread

from text_detector import detect_text_regions

image_sample = 'sample_images/image7.jpg'
image = imread(image_sample)
box_groups = detect_text_regions(image)

fig, ax = plt.subplots()
for box in box_groups:
    minr = box[0]
    minc = box[1]
    maxr = box[2]
    maxc = box[3]
    rect = mpatches.Rectangle((minc, minr), maxc - minc, maxr - minr,
                              fill=False, edgecolor='red', linewidth=2)


Sample Results

Original Detected Text Regions


All my experiments are in this notebook also part of the project where I make changes to the algorithm and them move it to the detector file. Text Segmentation in Image.ipynb


The accuracy depends a lot on the threshold parameters in the file which may need tweaking for different kinds of datasets.


B. Epshtein, E. Ofek and Y. Wexler, "Detecting text in natural scenes with stroke width transform," 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Francisco, CA, 2010, pp. 2963-2970.

Tran, Tuan Anh Pham et al. “Separation of Text and Non-text in Document Layout Analysis using a Recursive Filter.” TIIS 9 (2015): 4072-4091.

Chen, Huizhong, et al. "Robust Text Detection in Natural Images with Edge-Enhanced Maximally Stable Extremal Regions." Image Processing (ICIP), 2011 18th IEEE International Conference on. IEEE, 2011.

Project details

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

text-detector-0.0.3.tar.gz (4.1 kB view hashes)

Uploaded source

Built Distribution

text_detector-0.0.3-py3-none-any.whl (5.8 kB view hashes)

Uploaded py3

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page