Face Detection And Recognition
Face detection using haar-cascade algorithm and the faces can be recognized with three different algorithms(Eigenface, Fisherface and Local Binary Pattern Histogram). Project writen in Python, using the OpenCV and Pillow libraries, based on the FACE DETECTION & FACE RECOGNITION USING OPEN COMPUTER VISION CLASSIFIERS thesis written by LAHIRU DINALANKARA. Link to his work: https://www.researchgate.net/publication/318900718_Face_Detection_Face_Recognition_Using_Open_Computer_Vision_Classifies
Install / Use
npx skills add sipriano/Face-detection-and-recognitionInstalls into whichever agent you are using.
README
Detector_Video.py: This file detects faces using Haar cascades. It works fine with multiple faces.
Face_Capture_With_Rotate.py: Running this file will capture 50 images of a person infront of the camera. It will make sure photos are not dark and it will also make the face is straight.
Free_Rotate.py: This file shows the rotate function. Make sure you uncomment line 153 in NameFind.py This will show the image correcting the offset.
NameFind.py: This file contains all the functions.
Trainer_All.py: This file will train all the recognition algorithms using the images in the dataSet folder.
Recogniser_Image_All_Algorithms.py: This application will detect and recognise faces from images. Diffrent images can be selected.
Recogniser_Video_EigenFace.py: This File is the will recognise faces from the camera feed using Eigen face algorithm.
Recogniser_video_FisherFace.py: This File is the will recognise faces from the camera feed using Fisher face algorithm.
Recogniser_Video_LBPHFace.py: This File is the will recognise faces from the camera feed using LBPH face algorithm.
TestDataCollector_EiganFace.py: This file is the test application. It will take in an image the dataset will be loaded. A loop will run 200
times each time increamenting the number of components. Each time an Eigen face recogniser will be trained and predicted on the input image. After the for loop is compleated, ID and confidence will be ploted.
TestDataCollector_EiganFace.py: This file is the test application. It will take in an image the dataset will be loaded. A loop will run 200
times each time increamenting the number of components. Each time an Fisher face recogniser will be trained and predicted on the input image. After the for loop is compleated, ID and confidence will be ploted.
TestDataCollector_EiganFace.py: This file is the test application. It will take in an image the dataset will be loaded. A loop will run 54, 13, 50 times.
each time increamenting the Parameters. Each time an LBPH face recogniser will be trained and predicted on the input image. After the for loop is compleated, ID and confidence will be ploted.
------------------FOLDERS ----------- dataSet --> Contains the images that will be used to train the recogniser. FlowCharts --> Contains flow chart designed using Microsoft Visio and png files Haar --> Contains Haar Cascades of OpenCV used in the applications Plots --> Contains the plots taken using Me4.jpg and Sam.jpg Recogniser --> Contains the saved XML files by reconisers SaveData --> Contains the data saved by the tester applications
Related Skills
mcp
Use the `mcp_perplexity-ask_perplexity_search` tools to answer questions. You should use this instead of the `web_search` tool because it is a lot more accurate.
practical-power-systems-synthesis
This skill enables synthesis in the domain of power-systems (engineering). It represents research-level-level expertise and is designed for production use in research, industry, and educational contexts. Use this skill when you need to perform synthesis operations related to power-systems.
semi-supervised-optogenetics-testing
This skill enables testing in the domain of optogenetics (neuroscience). It represents intermediate-level expertise and is designed for production use in research, industry, and educational contexts. Use this skill when you need to perform testing operations related to optogenetics.
data-mining-interpretation-fundamental
This skill enables interpretation in the domain of data-mining (data-science). It represents fundamental-level expertise and is designed for production use in research, industry, and educational contexts. Use this skill when you need to perform interpretation operations related to data-mining.
