Computer Vision

Smartphones have cameras, and taking a photo or video and sharing it has never been easier, resulting in the incredible growth of modern social networks like Instagram.

YouTube might be the second largest search engine and hundreds of hours of video are uploaded every minute and billions of videos are watched every day.

The internet is comprised of text and images. It is relatively straightforward to index and search text, but in order to index and search images, algorithms need to know what the images contain

What does this symbol mean?

5

8

Can we teach computers to learn Amharic numbers?

Problem

Pipeline

  1. Formulate problem
  2. Collect data
  3. Label data
  4. Build model
  5. Validate model

Data Collection

Libraries

  1.  Scikit Image
  2. OpenCv

Typical Code

import cv2
from skimage.filters import threshold_otsu


img = cv2.imread(amharic)
imggray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
plt.imshow(img)

See examples in notebook

DSA Intro to Computer Vision - Addis Ababa

By Benjamin Akera

DSA Intro to Computer Vision - Addis Ababa

Presentation on Computer Vision given at the Data Science Africa Summer School in Addis Ababa Ethiopia.

  • 32

More from Benjamin Akera