README.md

# ai4hdr_backend

## "sliceImage.py" program:
Slices an image into even sized tiles. 
Note: if the slice size doesn't fit evenly into the size of 
      the original image, pixels will be lost.

## Command line arguments:
- arg1: name of image file used for slicing
- arg2: file name used as base for all slices
- arg3: width of new slices
- arg4: height of new slices
- arg5: directory to save slices 

## Example run:
```bash
python ./Scripts/sliceImage.py ./TestResults/Slice/GeoEye_Original.jpg GeoEye_Slice 512 512 ./TestResults/Slice/
```

## Example run result:
## Original Image: 1180x1180
![](TestResults/Slice/GeoEye_Original.jpg)

## Slice 1: 512x512
![](TestResults/Slice/GeoEye_Slice-0-0.jpg)

## Slice 2: 512x512
![](TestResults/Slice/GeoEye_Slice-0-512.jpg)

## Slice 3: 512x512
![](TestResults/Slice/GeoEye_Slice-512-0.jpg)

## Slice 4: 512x512
![](TestResults/Slice/GeoEye_Slice-512-512.jpg)


## "meanShiftSeg.py" program:
 - Uses the pymeanshift library to create a segmented images
 - Install pymeanshift: pip install git+git://github.com/fjean/pymeanshift.git

## Command line arguments:
 - arg1: image file used for segmentation
 - arg2: directory to save results
 - arg3: base name for results files
 - arg4: spatial radius for ms algo
 - arg5: range radius for ms algo
 - arg6: min density for ms algo

 ## Example run:
 ```bash
python ./Scripts/meanShiftSeg.py ./TestResults/MS/GeoEye_MS_Original.jpg ./TestResults/MS pyms 6 6 50
```

## "initDB.py" program:
 - Sets up the base file structure for an image database at a given location.

## Directory Visual with no data:
```
|-- ImageDatabase
│   |-- MeanShift
│   |-- Original
│   |-- Sliced
```

## Directory Visual with an image:
```
|-- ImageDatabase
│   |-- MeanShift
|   |   |--image_name-id    
|   |   |   |--128x128
|   |   |   |   |--image_name-128-smap-0-0.<ext>      <- segmented map
|   |   |   |   |--image_name-128-simage-0-0.<ext>    <- segmented image
|   |   |   |--256x256
|   |   |   |--512x512
│   |-- Original
|   |   |--image_name-id.<ext>     <- original image, id = auto increment integer
│   |-- Sliced
|   |   |--image_name-id
|   |   |   |--128x128
|   |   |   |   |--image_name-128-0-0.<ext>   <- sliced image
|   |   |   |--256x256
|   |   |   |--512x512
```

## Example run result:
## Original Image:
![](TestResults/MS/GeoEye_MS_Original.jpg)

## Segmentation Image:
![](TestResults/MS/pyms-color-seg.jpg)

## Labels Image:
![](TestResults/MS/pyms-labels-image.jpg)


## "meanShift3Channel.py" program:
Uses the mean shift algorithm to create a segmentation mask for an image.

## Command line arguments:
 - arg1: image file used for segmentation
 - arg2: file name to save segmentation

 ## Example run:
 ```bash
python ./Scripts/meanShift3Channel.py ./TestResults/MS/GeoEye_MS_Original.jpg ./TestResults/MS/three-channel-seg
```

 ## Example run result:
 ## Original Image:
 ![](TestResults/MS/GeoEye_MS_Original.jpg)

 ## Segmentation Image:
 ![](TestResults/MS/three-channel-seg.jpg)

 ## Program run time:
 This program takes roughly 20 seconds to run, tested on an AMD FX(tm)-4300 Quad-Core Processor