Update README.md
Browse files
README.md
CHANGED
|
@@ -1,57 +1,11 @@
|
|
| 1 |
---
|
| 2 |
-
title:
|
| 3 |
emoji: 👀
|
| 4 |
-
colorFrom:
|
| 5 |
colorTo: blue
|
| 6 |
sdk: gradio
|
| 7 |
-
sdk_version: 5.
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
-
short_description: '
|
| 11 |
-
---
|
| 12 |
-
|
| 13 |
-
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
|
| 14 |
-
|
| 15 |
-
# LaDeco - Landscape Environment Semantic Analysis Model
|
| 16 |
-
|
| 17 |
-
LaDeco is a tool that analyzes landscape images, performs semantic segmentation to identify different elements in the scene (sky, vegetation, buildings, etc.), and enables region-based color matching between images.
|
| 18 |
-
|
| 19 |
-
## Features
|
| 20 |
-
|
| 21 |
-
### Semantic Segmentation
|
| 22 |
-
- Analyzes landscape images and segments them into different semantic regions
|
| 23 |
-
- Provides area ratio analysis for each landscape element
|
| 24 |
-
|
| 25 |
-
### Region-Based Color Matching
|
| 26 |
-
- Matches colors between corresponding semantic regions of two images
|
| 27 |
-
- Shows visualization of which regions are being matched between images
|
| 28 |
-
- Offers multiple color matching algorithms:
|
| 29 |
-
- **adain**: Adaptive Instance Normalization - Matches mean and standard deviation of colors
|
| 30 |
-
- **mkl**: Monge-Kantorovich Linearization - Linear transformation of color statistics
|
| 31 |
-
- **reinhard**: Reinhard color transfer - Simple statistical approach that matches mean and standard deviation
|
| 32 |
-
- **mvgd**: Multi-Variate Gaussian Distribution - Uses color covariance matrices for more accurate matching
|
| 33 |
-
- **hm**: Histogram Matching - Matches the full color distribution histograms
|
| 34 |
-
- **hm-mvgd-hm**: Histogram + MVGD + Histogram compound method
|
| 35 |
-
- **hm-mkl-hm**: Histogram + MKL + Histogram compound method
|
| 36 |
-
|
| 37 |
-
## Installation
|
| 38 |
-
|
| 39 |
-
1. Clone this repository
|
| 40 |
-
2. Create a virtual environment: `python3 -m venv .venv`
|
| 41 |
-
3. Activate the virtual environment: `source .venv/bin/activate`
|
| 42 |
-
4. Install requirements: `pip install -r requirements.txt`
|
| 43 |
-
5. Run the application: `python app.py`
|
| 44 |
-
|
| 45 |
-
## Usage
|
| 46 |
-
|
| 47 |
-
1. Upload two landscape images - the first will be the color reference, the second will be color-matched to the first
|
| 48 |
-
2. Choose a color matching method from the dropdown menu
|
| 49 |
-
3. Click "Start Analysis" to process the images
|
| 50 |
-
4. View the results in the Segmentation and Color Matching tabs
|
| 51 |
-
- Segmentation tab shows the semantic segmentation and area ratios for both images
|
| 52 |
-
- Color Matching tab shows the matched regions visualization and the color matching result
|
| 53 |
-
|
| 54 |
-
## Reference
|
| 55 |
-
|
| 56 |
-
Li-Chih Ho (2023), LaDeco: A Tool to Analyze Visual Landscape Elements, Ecological Informatics, vol. 78.
|
| 57 |
-
https://www.sciencedirect.com/science/article/pii/S1574954123003187
|
|
|
|
| 1 |
---
|
| 2 |
+
title: SegMatch
|
| 3 |
emoji: 👀
|
| 4 |
+
colorFrom: indigo
|
| 5 |
colorTo: blue
|
| 6 |
sdk: gradio
|
| 7 |
+
sdk_version: 5.33.0
|
| 8 |
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
+
short_description: 'Zero Shot Segmentation-based color matching'
|
| 11 |
+
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|