OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Image & Video AI

Emotion Recognition

Emotion Recognition is a Python computer-vision application that analyzes webcam video and displays probabilities for detected facial emotion categories. Its repository includes a pretrained model for the real-time demo and a training script for FER2013.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Emotion Recognition — OpenViST project profile in Image & Video AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it for a hands-on exploration of webcam-based facial-expression classification or as a starting point for training experiments with FER2013.

Who it is for

  • Learners exploring facial-expression classification with a webcam.
  • Python developers interested in inspecting or adapting a compact emotion-classification project.

Documented uses

  • View predicted emotion-category probabilities alongside a live webcam scene.
  • Run a pretrained-model demonstration without first training a classifier.
  • Prepare FER2013 data and invoke the included classifier-training script.
Before you choose

Requirements & limits

The repository is public and identifies an MIT license.

  • The documented real-time workflow uses a webcam and the included pretrained model.
  • Training requires downloading FER2013 and placing its CSV in the specified directory.
  • The README reports 66% test accuracy on FER2013; this is a project-reported result, not a guarantee for other data.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Run the webcam demo with the included model

Open the real-time webcam scene and display detected emotion probabilities using the repository’s pretrained model.

Before you start

  • Python environment with dependencies listed in requirements.txt
  • Webcam
  • Repository files, including the provided pretrained model

Steps

  1. Install dependencies with the command below.

    Documented command
    pip install -r requirements.txt

  2. Run the command below.

    Documented command
    python real_time_video.py

Expected outcome

The program opens a window showing the webcam scene and a window displaying probabilities for detected emotions.

Guide limitations

  • The README describes webcam capture; it does not give steps for processing a recorded video.
  • The README does not specify supported Python versions or operating-system-specific setup.
Documentation 1 ↗
Source-based practical guide

Prepare FER2013 data and start model training

Prepare the dataset location and invoke the repository’s emotion-classifier training script.

Before you start

  • Dependencies listed in requirements.txt
  • FER2013 dataset CSV

Steps

  1. Install dependencies with the command below.

    Documented command
    pip install -r requirements.txt

  2. Download the FER2013 dataset.

  3. Place its CSV in fer2013/fer2013/.

  4. Run the command below.

    Documented command
    python train_emotion_classifier.py

Expected outcome

The repository’s training script is invoked with the dataset in the location specified by its README.

Guide limitations

  • The README reports 66% test accuracy on FER2013; it does not establish performance on other datasets or conditions.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
15 October 2026
Original website title
otaha178/Emotion-recognition · Official homepage title · retained in its source language
How we review sourcesSuggest a correction