Definition :
- Learn from Data and Solve problems.
Data & Concept :
-
Human can Analyze, Identify the patterns and make decisions.
---> Numerical Data
---> Concept : ML & Deep Learning
-
Human can Listen & Speak
---> Text/ Audio Data
---> Concept : ML & NLP
-
Human can See & Recognize
---> Image/ Video Data
---> Concept : Computer Vision & Deep Learning
Step :
- Gathering Data
- Data Preparation
- Data Transformation | Data Cleaning | Data Combining
- Choose Model
- Concept | ML Algorithm
- Training
- Evaluation
- Parameter Tuning
- Prediction
Computer Vision involves the use of algorithms and techniques to enable computers to gain a deep understanding and extract relevant information from digital images or videos.
We used pip
for installing the necessary libraries.
pip install imutils
for resize image / handle images or videos.pip install opencv-python
for real-time computer visionpip install opencv-contrib-python
pip install pillow
- PIL supports for opening, manipulating, saving different image fie format. Also, supports high quality images than open-cv (eg: satellite images).pip install scikit-image
- includes algorithms to deal with segmentation, filtering, feature detection etc.- SciPy
- Numpy
- Mahotas
- Matplotlib
- Wheel
Object Recognition, Face Recognition, Autonomous Vehicle, Disease Detection, Emotion Recognition, Agriculture, Satellite Image Analysis, Mobile & Camera, OCR, Cryptography
Moving object detection is a technique used in computer vision and image processing. Multiple consecutive frames from a video are compared by various methods to determine if any moving object is detected.
Face detection refers to the task of locating the presence of a human face within an image or video frame. OpenCV provides a pre-trained Haar Cascade classifier that can be used to detect faces in images and videos. The Haar Cascade classifier is a machine learning-based approach that uses a set of features to detect faces. Once the face is detected, face tracking is performed to track the detected face as it moves around the video stream. Face tracking typically involves locating the face in each video frame and estimating its position and orientation.
π― DAY β 4 : Object Tracking based on color using OpenCV
π― DAY β 5 : Face Recognition using OpenCV
π― DAY β 6 : Face Emotion recognition using 68-Landmark Predictor OpenCV
π― DAY β 7 : Introduction to Deep learning | How to install DL libraries
π― DAY β 8 : Designing your First Neural Network
π― DAY β 9 : Object recognition from Pre-trained model
π― DAY β 10 : Image classification using Convolutional Neural Network
π― DAY β 11 : Hand gesture recognition using Deep Learning
π― DAY β 12 : Leaf disease detection using Deep Learning
π― DAY β 13 : Character recognition using Convolutional Neural Network
π― DAY β 14 : Label reading using Optical Character recognition
π― DAY β 15 : Smart Attendance system using Deep Learning
π― DAY β 16 : Vehicle detection using Deep Learning
π― DAY β 17 : License plate recognition using Deep Learning
π― DAY β 18 : Drowsiness detection using Deep Learning
π― DAY β 19 : Road sign recognition using Deep Learning
π― DAY β 20 : Introduction to Machine learning| How to install ML libraries
π― DAY β 21 : Evaluating and Deploying the various ML model
π― DAY β 22 : Fake news detection using ML
π― DAY β 23 : AI snake game design using ML
π― DAY β 24 : Introduction to NLP & itβs Terminology | How to install NLP Libraries NLTK
π― DAY β 25 : Title Formation from the paragraph design using NLP
π― DAY β 26 : Speech emotion analysis using NLP
π― DAY β 27 : Cloud-based AI, Object recognition using Amazon Web Service (AWS) & Imagga
π― DAY β 28 : Deploying AI application in Raspberry Pi with Neural Compute stick & Nvidia Jetson Nano
Β Language: Python
Β Knowledge Area: Artificial Intelligence
Β Libraries: open-cv
, imutils
, pillow
, mohotas
, scipy
, wheel
, numpy
, matplotlib
, sklearn
Don't forget to leave feedback if you find this repo useful or any improvements. βπΉπ₯§
Thank you π§‘
β¨π€ Pantech Solutions_INDIA
Internship
Artificial-Intelligence Concept