Adamouization / Computer-Vision-Filtering-and-Object-Recognition-and-Features

:eyes: Image matching using intensity-based and feature-based template matching (SIFT) algorithms.

Computer Vision: Filtering, Object Recognition & Features

Intensity-based template matching and feature-based template matching using SIFT algorithms for matching images are implemented. A Training dataset of images (icons) a Testing dataset (various combinations of icons) as shown in Figure 2 are used.

Project developed in collaboration with yissok.

The report can be read here.

Usage

Clone the repository (or download the zipped project): $ git clone https://github.com/Adamouization/Computer-Vision-Filtering-and-Object-Recognition-and-Features

Create a virtual environment for the project and activate it:

virtualenv ~/Environments/Computer-Vision-Filtering-and-Object-Recognition-and-Features
source Computer-Vision-Filtering-and-Object-Recognition-and-Features/bin/activate

Once you have the virtualenv activated and set up, cd into the project directory and install the requirements needed to run the app:

pip install -r requirements.txt

You can now run the app:

python main.py -m <model_type> --mode <mode> --debug

where:

• -m <model_type> corresponds to the matching technique to use e.g. convolution, intensity or sift.
• --mode <mode> corresponds to train or test.
• --d runs the program in debug mode with additional print statements.

Contact

• Email: [e-mail]
• LinkedIn: @adamjaamour