Sign in

Aspiring on Computer vision, Data science , NLP , IoT

We read text with the help of our eyes, The approach was to introduce to the machine to analyze and read text from images captured using the camera.

Introduction of AI in real-life applications of humans. Some examples are

Reading and analyzing passport details in the airport

License plate recognition and reading its text

Text extraction from 2D image

Approach was implemented and tested on Python3.7 and ubuntu 20.04

In this article, we will focus on Tesseract OCR. And to read the images we need OpenCV.

Installation of Tesseract OCR:

Installing Tesseract is quite simple to install and can be done using the following apt commands:

$ sudo apt…

After doing some computer vision projects I found some of the images taken from the camera in real-time are blurry. When I searched in google to identify blur detection using the OpenCV-based approach.

In below, I mentioned two approaches for blur detection using Fast Fourier Transform (FFT) and Laplacian

Fig Clear image vs Blurry image

Method 1

Laplacian approach for blur detection

The Laplace filter is mainly used to define the edge lines in a picture. What is meant here by the edge are the sharp color separations that usually separate objects from the background. …

In this post, you’ll learn how to build your very own AI-powered gym tracker using AI-Powered Pose estimation. You’ll leverage MediaPipe and Python to detect different posts from a webcam feed. Then render the results to the screen using OpenCV.

As part of it, you’ll also learn how to extract joint coordinates and calculate joint angles! You’ll learn how to:

To see demo:

Recently I came across a super cool library called Mediapipe which makes things pretty much simple for us. I would suggest you go through its official site to read more about it because the site explains…

The below mention steps are tested on Jetson Xavier and Linux machines.

The scripts provided include functions such as

  1. To stream radiometric thermal image
  2. Performing FFC manually
  3. To set various gain mode
  4. To set FFC in manual and auto mode.

Install software requirements

  1. Python 3
  2. OpenCV
  3. libuvc

To install and compile libuvc steps to follow

git clone

sudo apt-get install cmake -y

sudo apt-get install libusb-1.0–0-dev -y

sudo apt-get install libjpeg-dev -y

cd libuvc

mkdir build

cd build cmake .. make && sudo make install

sudo ldconfig -v

cd ../

The libuvc library is compiled and it should be tested before running the scripts

To test the compilation


We as a whole recall those marvelous youth days when we use to go to event congregations or area fairs. One of my #1 components of these carnivals was the fun-house reflect room.

Interesting mirrors are not plane mirrors however a mix of raised/sunken intelligent surfaces produce twisting results that look amusing as we move before these mirrors.

The primary inspiration for this post is to urge our perusers to learn principal ideas like the math of picture arrangement, camera projection network, characteristic and outward boundaries of a camera.

Before the finish of this post, you will actually want to…

During childhood, Everyone may have dreamed of becoming a hollow man So that no one can see you and do anything you think without public attention. I will show you how to use a Computer Vision library called OpenCV for Python to make you an invisible hollow man.

Before we start with the project, we need to understand how it works. Essentially, we are masking the foreground and background to look like the foreground is invisible.

The project was implemented and tested on Python 3.8 (both windows and linux)

Requirements :

  • python3,6+
  • opencv-python
  • numpy
  • pandas

Steps to make the Cloak…

Object Detection using Single Shot MultiBox Detector with Caffe MobileNet on OpenCV in Python.

SSD Framework

Single Shot MultiBox Detectors can be divided into two parts:

  • Extracting Features using a base network
  • Using Convolution Filters to make predictions

This implementation makes use of the MobileNet deep learning CNN architecture as the base network.

What is Object Detection?

Object Detection in Computer Vision is as simple as it sounds- detecting and predicting objects and localizing their area. Object Detection is based on image classification. Irrespective of the latter being performed using neural networks or primitive classifiers, image classification is always the first step…

Edge discovery is a picture handling strategy, which is utilized to recognize the limits (edges) of items, or locales inside a picture. Edges are among the main highlights related with pictures.


How are Edges Detected?
Sobel Edge Detection
Canny Edge Detection

How are Edges Detected?
Edges are characterized by sudden changes in pixel intensity. To detect edges, we need to go looking for such changes in the neighboring pixels. Come, let’s explore the use of two important edge-detection algorithms available in OpenCV: Sobel Edge Detection and Canny Edge Detection.

The image to be tested for canny edge detection
test image

Sobel Edge Detection

Sobel Edge Detection is one of the…

Sooraj S

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store