Skip to content
프로젝트

yaxan/Naruto_Handsign_Classification

GitHub에서 보기

yaxan/Naruto_Handsign_Classification has 39 GitHub stars and 7 forks. GitHot measured 0 stars in 24 hours, 0 in 7 days, and 0 in 15 days. Last checked 2026-11-17 14:35 UTC. Last push 2026-10-13.

이 수치를 측정하는 방법

측정된 스타 증가

in 24h
0
in 7 days
0
in 15 days
0
in 1 month
기록 수집 중

서로 겹치는 기간의 순증가량이며 일별 합계가 아닙니다. 측정값이 없으면 비워 둡니다. 스타는 관심도를 나타내며 품질을 보장하지 않습니다.

소개

Naruto Hand Gesture Recognition with OpenCV and Transfer Learning

머신러닝

README.md

Original

Noticing some recent stars on github probably from reels with similar projects.. this was done pre-LLMs when I was a sophomore, any LLM could one shot this kind of thing nowadays and be 100x better.

Naruto Hand Sign Classification

This is a project based on the anime Naruto by Masashi Kishimoto. In the show, the ninjas weave various hand-signs combinations as a way to use their techniques referred to as jutsus. This project attempts to use Deep Learning and Computer Vision techniques to identify what handsign an individual is making.

Live Demo Classification

The trained model performed great for 10 of the classes while classes Dog and Serpent are the machines weakpoints as it is not as consistent in classifying those two. See below for a demonstration of the live classification.

https://user-images.githubusercontent.com/41130598/174506955-9ea1c002-effd-4982-9365-2dba0703b6a7.mp4

Models

We experimented on MobileNetV2, ResNet50, VGG16, and InceptionV3 architectures due to their prominence in image classification tasks. We froze all but their last few layers to take advantage of their feature extraction capabilities they learned from being trained on the imagenet dataset, effectively using transfer-learning for our image-classifcation task. Out of the four models/architectures, VGG16 performed the best at an accuracy of 93.60% on the mannually curated static test dataset as well as a minimum accuracy of 83.33% for the live demo.

Architecture of the VGG16 model is shown below.

image

See links below for details of the four models.

  1. MobileNetV2
  2. ResNet50
  3. VGG16
  4. InceptionV3

Data

The data used in this project was manually collected and augmented by recording a video from a webcam utilizing OpenCV, following a number of data-augmentations such as flips and rotations to increase dataset size.

Packages Used

The requirements for the project are as follows:

  1. Python=3.7.7
  2. Tensorflow=2.8.0
  3. OpenCV=4.6.0.66
  4. Numpy=1.21.5
  5. Pillow=9.1.0
  6. Mediapipe=0.8.10

Contributers

Contributers of the project are listed below. Click the hyperlink to follow up on more projects.

  1. Saad Hossain
  2. Jaeyoung Kang
  3. Yazan Masoud
  4. Michael Frew