This repository contains code for extracting features from images using the AlexNet deep convolutional neural network (D-CNN) 📸. Feature extraction is a crucial step in the field of computer vision, enabling the use of complex image data for machine learning models.

1. Set Up Your Environment: Ensure you have MATLAB and the AlexNet model installed.
2. Prepare Your Data: Load your images into the MATLAB image datastore.
3. Run Feature Extraction: Execute the provided scripts to preprocess your images and extract features from the FC7 layer of AlexNet.

• Data Preparation: The image datastore is read to bring your image dataset into the MATLAB environment.
• Image Preprocessing: All images are preprocessed to meet the input requirements of AlexNet.
• Model Selection: AlexNet is selected as the pre-trained D-CNN for this task.
• Layer Selection: Features are extracted from the "FC7" layer of AlexNet.
• Feature Extraction: The extracted features are stored in a variable for further use.

The code in this repository is designed to extract features from any image dataset using AlexNet 🌐. These extracted features can be used to train various machine learning classifiers, aiding in tasks such as image recognition, classification, and more.

• MATLAB: The primary environment for running the code.
• AlexNet: The pre-trained model used for feature extraction. Ensure you have the Deep Learning Toolbox installed in MATLAB to work with AlexNet.

1. Clone this repository to your local machine.
2. Open the scripts in MATLAB.
3. Adjust the path to your image dataset as necessary.
4. Run the scripts to begin feature extraction.

This code is part of research and development in the field of computer vision and machine learning. If you utilize this code in your projects or research, kindly reference the following articles:

1. Jamil, S.; Fawad; Rahman, M.; Ullah, A.; Badnava, S.; Forsat, M.; Mirjavadi, S.S. (2020). Malicious UAV Detection Using Integrated Audio and Visual Features for Public Safety Applications. Sensors, 20(14), 3923. https://doi.org/10.3390/s20143923.

2. Jamil, S.; Rahman, M.; Haider, A. (2021). Bag of Features (BoF) Based Deep Learning Framework for Bleached Corals Detection. Big Data Cogn. Comput., 5(4), 53. https://doi.org/10.3390/bdcc5040053.

This project is open source and available under the MIT License.

Feel free to open an issue or pull request if you have suggestions or contributions. For direct inquiries, contact [email protected].