https://github.com/rishi-jain2602/ai-image-analysis-pipeline
An AI Image Analysis Pipeline automates image processing by detecting objects, segmenting them, extracting features, and generating textual descriptions or structured data.
https://github.com/rishi-jain2602/ai-image-analysis-pipeline
bart bert-model blip huggingface-transformers python3 streamlit yolo
Last synced: 4 months ago
JSON representation
An AI Image Analysis Pipeline automates image processing by detecting objects, segmenting them, extracting features, and generating textual descriptions or structured data.
- Host: GitHub
- URL: https://github.com/rishi-jain2602/ai-image-analysis-pipeline
- Owner: Rishi-Jain2602
- Created: 2024-08-17T21:21:47.000Z (about 1 year ago)
- Default Branch: main
- Last Pushed: 2024-08-20T04:51:02.000Z (about 1 year ago)
- Last Synced: 2025-02-14T15:47:12.796Z (8 months ago)
- Topics: bart, bert-model, blip, huggingface-transformers, python3, streamlit, yolo
- Language: Jupyter Notebook
- Homepage:
- Size: 2.62 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# AI-Image-Analysis-Pipeline
An AI Image Analysis Pipeline automates image processing by detecting objects, segmenting them, extracting features, and generating textual descriptions or structured data.
*****
https://github.com/user-attachments/assets/2f57f3ae-50b9-4f8c-aea1-c2e4bcff63ed
## Installation
1. Clone the Repository
``` bash
git clone https://github.com/Rishi-Jain2602/AI-Image-Analysis-Pipeline.git
```
2. Create Virtual Environment
```bash
virtualenv venv
venv\Scripts\activate
```
3. Install the Project dependencies
```bash
pip install -r requirements.txt
```
4. To Run Streamlit app
```bash
cd streamlit_app
streamlit run app.py
```
****
This Jupyter Notebook link: [link](https://github.com/Rishi-Jain2602/AI-Image-Analysis-Pipeline/blob/main/Image-Analysis.ipynb)
This will provide detailed explanations for each step I took. If the Jupyter notebook doesn't work locally, try running it on Kaggle.
****
### Tools & Models Used:
**1. Image Segmentation:** Mask R-CNN
**2. Feature Extraction:** YOLO (Hugging Face Model: hustvl/yolos-tiny)
**3. Text/Data Extraction from Objects:** Hugging Face Model (Salesforce/blip-image-captioning-large)
**4. Summarization:** Hugging Face Model (facebook/bart-large-cnn)
### Pipeline Structure:
**1. Input:** Upload an image.
**2. Processing:** Detect, segment, extract features, and generate captions.
**3. Output:** Annotated image and summary table.
**Integration:** Streamlit app for seamless user interaction and review.
****
## Result
## Note
1. Make sure you have Python 3.x installed
2. It is recommended to use a virtual environment to avoid conflict with other projects.
3. If the Jupyter notebook doesn't work locally, try running it on Kaggle.
4. For deep learning, a laptop with a powerful GPU, a high-performance CPU, at least 8GB of RAM, a fast SSD, and an efficient cooling system is recommended.
5. If you encounter any issue during installation or usage please contact rishijainai262003@gmail.com or rj1016743@gmail.com