Back to projects

ML · Computer vision Mar to May 2024

Facial Emotion Detection

Abstract.Classifying emotions such as sadness, joy and surprise from facial expressions.

Role
Developer
Period
Mar to May 2024
Context
Personal project
Team
Solo
Table 1Results.
~16k Face images
4 Models compared

01How it works

  1. Input Capture image A face image from the camera or the dataset.
  2. Step 02 Detect the face OpenCV finds the face, converts to grayscale and preprocesses.
  3. Step 03 Extract features Expression features for classification.
  4. Output Classify & evaluate Four models compared with confusion matrices and heatmaps.
Fig. 1Facial Emotion Detection, step by step.

02What I built

  1. Collected and preprocessed a dataset of about 16,000 face images with OpenCV (face detection, grayscale conversion).
  2. Compared KNN, logistic regression, naive Bayes and random forest classifiers.
  3. Evaluated with confusion matrices and heatmaps, and improved accuracy through feature work.

03Technologies

  • Python
  • OpenCV
  • scikit-learn
  • NumPy
  • Matplotlib
  • Seaborn

On request

Request my resume

I share my resume on request. Tell me a little about yourself, and I'll email it to you once I've reviewed your request.

I am a…

Which document?

0 / 100 words

Your details are used only to handle this request and are never shared.