George  Koelpin

George Koelpin


Instance-level Recognition

In this blog, I will walk through an introduction to instance-level recognition, use cases, challenges, currently available dataset, and state of the art results (recent winner solutions) on these challenges/datasets.


Instance Level Recognition (ILR), is a visual recognition task to recognize a specific instance of an object not just object class.

For example, as shown in the above image, painting is an object class, and “Mona Lisa” by Leonardo Da Vinci is an instance of that painting. Similarly, the Taj Mahal, India is an instance of the object class building.

Use cases

  • Landmark Recognition: Recognize landmarks in images.
  • Landmark Retrieval: Retrieve relevant landmark images from a large-scale database.
  • Artwork Recognition: Recognize artworks in images.
  • Product Retrieval: Retrieve relevant product images from a large-scale database.


  • Large scale: Most of the current state of the art results of recognition tasks are measured on very limited categories e.g. ~1000 image classes in ImageNet, ~80 categories in COCO. But use-cases like landmark retrieval and recognition, has 200K+ classes e.g. in Google Landmark Dataset V2 (GLDv2), 100K+ classes of the product on Amazon.
  • Long-tailedFew popular places have more than 1000+ images but many less know places have less than 5 images in GLDv2.

Google Landmarks Dataset v2 (GLDv2) Class Distribution, Image from

  • **Intra-class variability: **Landmarks are mostly spread across a wide region and have very high intra-class variability as shown in the below image.

Image for post

Images from Google Landmarks Dataset v2 (GLDv2)

  • **Noisy Labels: **The success of machine learning models depends on high-quality labeled training data, as the presence of labels errors can greatly reduce the model’s performance. These noisy labels as shown in the below image, unfortunately, noisy labels are part of a large training set and need additional learning steps.

Image for post

#object-detection #machine-learning #deep-learning #data-science #computer-vision

What is GEEK

Buddha Community

Instance-level Recognition
clemency beula

clemency beula


Fuse with the radical technology using the Face Recognition Employee Attendance Software

We are witnessing a lot of impacts in the world because of the COVID-19 pandemic. There is not much we could do to compensate for all the losses at once. But it can eventually be overcome. And the reason for this hope is ‘technology’.

Everything is just at an arm’s reach with the technology and it’s been proven time-to-time to us. One such thing that makes people still and stare for a moment is the Face Recognition Employee Attendance Software.

Face recognition is one of the most advanced technologies that is being implemented in the corporate industry now.

The software is mainly responsible for marking the attendance of the employees without them having to touch the screen.

Since ‘touch’ has become the most dangerous word in recent months, the system helps people to get away from it.

This software is also known as Contactless Attendance System that follows a highly hygiene scanning. Let’s look at the workflow:

  • The employee would stand in front of the device camera and the facial features get analysed. *
  • The features are then compared with the database containing the faces of all the employees. The user details are retrieved from the database.*
  • The user will be scanned to ensure that he/she has a mask and once they put the mask on, the system scans the face again.*
  • The social distancing guidelines are examined by scanning the area around the user. *
  • Once the criterias are matched, the attendance of the user is marked.

Working models of the software:
The software works in two different models such as:

Tab-based model:
The tablet having this software solution, will have to scan their faces at the entry points. They will wait for the system to confirm the checklist like detecting face masks and social distancing.

Mobile-based model:
The mobile-based model is safer, since it involves logging in with the WiFi server and login to the accounts. After matching the criteria, attendance would be marked.

On a concluding note, Employee contactless attendance software is the future. So, make the most out of it by contacting our team right now!

#face recognition attendance software #face recognition employee software #face recognition employee attendance software #face recognition based attendance software #contactless facial recognition attendance system

Face Recognition with Python [source code included]

Python can detect and recognize your face from an image or video

Face Detection and Recognition is one of the areas of computer vision where the research actively happens.

The applications of Face Recognition include Face Unlock, Security and Defense, etc. Doctors and healthcare officials use face recognition to access the medical records and history of patients and better diagnose diseases.

About Python Face Recognition

In this python project, we are going to build a machine learning model that recognizes the persons from an image. We use the face_recognition API and OpenCV in our project.

Tools and Libraries

  • Python – 3.x
  • cv2 – 4.5.2
  • numpy – 1.20.3
  • face_recognition – 1.3.0

To install the above packages, use the following command.

pip install numpy opencv-python

To install the face_recognition, install the dlib package first.

pip install dlib

Now, install face_recognition module using the below command

pip install face_recognition

#machine learning tutorials #face recognition #face recognition opencv #ml project #python face recognition #face recognition with python

Rory  West

Rory West


Create EC2 instance from AWS Console

What is EC2 Instance?

Secure and resizable compute capacity in the cloud.

Amazon Elastic Compute Cloud ( Amazon EC2) is a web service that provides secure, resizable compute capacity in the cloud. It is designed to make web-scale cloud computing easier for developers.

In this article let us see how to create On-demand EC2 instance from Console.

#create-ec2-instance #aws-ec2-instance #ec2-instance #amazon-web-services #aws

Christa  Stehr

Christa Stehr


Creating a Speech Recognition App in Angular

We can extract text data from a speech by using speech recognition methods. There are many ways to carry out speech recognition in Angular, however, I’d like to focus on a simple method for this.

Here we use “Web Speech API” to recognize speech. Unfortunately, this API is only supported for a few browsers so I will list the supported browsers below:

  • Google chrome
  • Chrome for Android
  • Samsung Internet
  • QQ Browser
  • Baidu Browser

You can test this app in a browser from this list.

Okay, let’s begin. First of all, we have to create a new Angular project by using the below command in the terminal. I assume that you have installed Angular-CLI, but if you haven’t then the below command won’t work.

ng g new voice-recognition
cd ./voice-recognition

#speech-recognition #angular #web-speech-api #api #voice-recognition

Trystan  Doyle

Trystan Doyle


Torch: Spoken digits recognition from features to model.

Explore the features extracted from voice data and the different approaches to building a model based on the features.

#digits-recognition #pytorch #speech-recognition #spoken-digit #convolutional-neural-net