open cv computer visions package used in python if youre a beginner or youre a computer enthusiast then it will very usefull for you, because this repository contains the opencv tutorial from the beginning at a order of Tutorial names!! So, Enjoy!!, Happy Coding!!
Repo Contents:
-
Computer Vision Tutorial 1 - Getting Started with Images
-
Computer Vision Tutorial 2 - Basic Image Manipulations
-
Computer Vision Tutorial 3 - Annotating Images
-
Computer Vision Tutorial 4 - Basic Image Enchancement using matthematical operations
-
Computer Vision Tutorial 5 - Accessing camera using opencv
-
Computer Vision Tutorial 6 - Writing a video using opencv
-
Computer Vision Tutorial 7 - Using filters on live
-
Computer Vision Tutorial 8 - Image Alignment
-
Computer Vision Tutorial 9 - Creating panoramas using opencv
-
Computer Vision Tutorial 10 - High Dynamic Range (HDR) Imaging
-
Computer Vision Tutorial 11 - Object Tracking
-
Computer Vision Tutorial 12 - Face Detection
-
Computer Vision Tutorial 13 - Object Detection using Tensorflow Model
-
Computer Vision Tutorial 14 - Pose Detection
-
handTrackingBasics - Hand tracking using opencv and mediapipe to install mediapipe use:
pip install mediapipe
use the below image for the hand landmarks reference: -
generatingArucoMarkers - Code to generate aruco markers for marker based AR still using opencv-python to generate aruco markers sample images generated by the program
-
markerDetection - After generating markers for the marker based AR next, we need to detect the markers. so, this file contains of the basics of marker detection using opencv-python sample images:
-
imageAugmentationBasics - Image augmentation basics source code
-
poseEstimationBasics - Pose Estimation using open-cv and mediapipe
use the below image to refer the pose estimation landmark
-
faceDetectionBasics - Face Detection using open-cv and mediapipe
result:
-
faceMeshBasics - Face Mesh using open-cv and mediapipe
result:
-
fingerCounter - Counting fingers using open-cv and mediapipe
result:
-
ai_virtual_mouse - Virtual mouse using opencv-python and mediapipe
result:
-
ai_virtual_keyboard - Virtual keyboard using opencv-python and mediapipe
result:
-
useful_utils_opencv - Contains very useful random functions like cropping video, reversing video, saving video, etc
-
image_classification_using_scikit_learn - image classification using scikit learn. dataset used for the classification Dataset Link
-
image_classification_with_yolo - image classification using yolov8. dataset used for the classification Dataset Link
-
image_classification_with_tm - image class using teachable machine Link to the teachable machine , and the code file is checking the models accuracy score dataset used for this file is the same of yolov8
-
parking_spot_detection_and_counter - Parking spot counter on live video with machine learning image classification technique using scikit-learn. Link to the data, model, and position Link to the files used in this project
result:
-
american_sign_language_detection - american sign language detection using opencv, mediapipe and yolov8 for image classification. dataset and model used for this project Link
result:
-
object_detection_with_yolo - yolo-basics - This code file covers the yolo basic detection with images, videos, and real-time webcam
result:
-
Project 1 Car Counter Car counter project using yolo and for tracking we are using sort module. The video used in the project you can find here Link
result:
-
playing_videos_using_cv2_streamlit.py - Sample code of playing videos using streamlit and opencv-python
-
ElectionProject2k24 - A simple flask application to access camera and to capture photo
-
streamlit_multiple_cameras.py - Accessing multiple cameras using streamlit
-
Person-Counter - Customer in & Customer out count from a shop using opencv-python, sort, yolov8
result:
-
ImagesWithSpecificExposure - To create images with specific exposure timings manually.
-
FeatureMatching - Finding the matching patterns between two images (There will be two files one is ipynb and other one is py file)
Note
Google colab notebbok not working on git because file too large so for code Click Here!!
-
Extracting Digits With Easy OCR Extracting digits from an odometer using easy-ocr library.
-
Training a custom model using yolo with custom dataset Trained a custom model using yolo with custom dataset of images with the size of 640x640
-
preparing_dataset_with_image_annotation This notebook will guide you how to use labels.txt file for image annotations and cropping
-
CNN-TRAINING-FILE
- dataset_processing.py : Preparing dataset with custom data using the labels.txt file downloaded from
cvattool with label and annotations, cropping and resizing images for keras (224x224) size.
- dataset_processing.py : Preparing dataset with custom data using the labels.txt file downloaded from
-
Parquet Dataset Prepration
- parquet_dataset_preparation.py : Preparing parquet dataset using pandas, Pillow and pyarrow
-
Converting MRI Scans to Colored Images
- ConvertingMRIScanstoColoredImages.ipynb : Converting mri images to colored images using opencv, matplotlib and monai (medical open network for Artificial Intelligence)
-
Face Match
- face_match : Face match using face recognition
-
SwinTransformerForSingleImage
- This to demonstrate the swintransformer actual workflow with single image
-
UsingApretrainedSwinTransformerForClassification
-
Using a pretrained swin transformer model for image classification
dataset used for training model you can find here.
-
-
face_rec_web_cam
- Using webcam for face recognition
-
liveness_detection_webcam
- Using webcam for liveness detection
-
compressing_image_using_python
- Compressing image size using python
-
not_looking_at_camera.py
-
eye_blink_detector.py
-
GettingStartedWithDiffUsersPart1
- Using diffuers to generatw Text-To-Image
-
detecting_age_n_gender
-
detecting_emotion
- detecting emotion using
deepfacemodule
- detecting emotion using
-
face_detection_using_diff_yolo_models
- detecting faces and getting accuracy for different yolov models suchas
yolov8,yolov11s,yolov11n&yolov11m
- detecting faces and getting accuracy for different yolov models suchas
-
anti_spoof_detection
- anti spoof detection using
deepfacemodule
- anti spoof detection using
-
ConvertingGrayScaleImageToColor
- Converting grayscale images into color using opencv, deep neural network and streamlit
-
face_detection_using_insight_face
- Detecting faces and facial features using
insightfaceandopencv-pythonmodule
- Detecting faces and facial features using
-
face_recognition_using_insight_face
- Recognising faces using
insightfaceandopencv-pythonmodule
- Recognising faces using
-
Ultralytics_yolo11
- Using yolo11 for different tasks such as detection, segmentation, instant segmentation, post detection, etc
-
pose_estimation_using_yolo
- using yolo11 for pose estimation






























