Skip to content

Commit 4f109d5

Browse files
authored
Update README.md
1 parent 8140234 commit 4f109d5

File tree

1 file changed

+36
-29
lines changed

1 file changed

+36
-29
lines changed

README.md

Lines changed: 36 additions & 29 deletions
Original file line numberDiff line numberDiff line change
@@ -27,25 +27,18 @@ Suggested distros for running FEET-GUI in Raspberry PI 4 (top being the most sug
2727
For installing FEET-GUI on Windows you need to have python 3.9 installed in your system. The easy way to achieve this is simply typing ```python```in your PowerShell or CMD. If you don't have python installed, an instance of the official Microsoft Store will be opened to install the latest available python core.
2828

2929
Additionally, you might want to install git on your machine from https://git-scm.com/downloads.
30-
After this, you are ready to run the native installation.
31-
Finally, you can launch FEET-GUI simply by lauching the ```feet-gui.bat```file.
30+
After this, you are ready to run the native installation simply by lauching the ```feet-gui.bat```file (you can skip native installation).
3231

3332
## 2.2 Native
3433

35-
First, choose the desired fork. If you are running ARM architectures (like raspberry pi), it is suggested to clone the ```no-tf``` branch, so you can avoid installing heavy libraries like ```tensorflow```
3634

3735
If you are using amd64 or x86 architecture, then start by simply cloning the repository into your desired directory. Type in terminal (or PowerShell in Windows):
3836

3937
```
4038
git clone https://github.com/blotero/FEET-GUI
4139
cd FEET-GUI
4240
```
43-
Otherwise, if you preffer the ligth version, then clone the ```no-tf``` *(no tensorflow)* repository:
4441

45-
```
46-
git clone https://github.com/blotero/FEET-GUI/tree/no-tf
47-
cd FEET-GUI
48-
```
4942
Install requirements (make sure you have latest version of ```pip``` by running ```pip install pip```).
5043

5144
```
@@ -63,7 +56,7 @@ python3 main.py
6356
## 2.3 Virtual environment
6457

6558
One of the requirements for ```feet-gui``` is a module known as ```opencv-contrib-python-headless``` which has conflict with the traditional ```opencv-python``` package.
66-
The reason for using the contrib-headless version is due to conflicts with the original version with the PySide package, for both (opencv and PySide) packages, work on instantes with qt that are not compatible with each other.
59+
The reason for using the contrib-headless version is due to conflicts with the original version with the PySide package, for both (opencv and PySide2) packages, work on instantes with qt that are not compatible with each other.
6760

6861
For this reason, it is suggested to run feet-gui on a virtual environment (specially if you have installed other packages related to opencv or qt).
6962
This can be done in Linux as follows:
@@ -85,55 +78,69 @@ Once you have done this, your shell should be working in this venv. If you had n
8578
FEET-GUI is thought to be lightweight and minimal, yet intuitive for obstetrics healthcare environments.
8679
Out of the box you will have a main window,
8780

88-
![image](https://user-images.githubusercontent.com/43280129/121790986-b1a21380-cbaa-11eb-8cba-317c951ff241.png)
81+
![image](https://user-images.githubusercontent.com/43280129/130433628-d22f450a-4e74-41ba-b6e8-87b8f4e15ab0.png)
8982

83+
## 3.1 Import your models
84+
Feet-GUI is based on computer vision algorithms using different CNN architectures, which have been previously trained in with several architectures. All training process is avaliable in https://github.com/Rmejiaz/FEET_U-Net.
9085

91-
## 3.1 Import a patient folder
92-
First, stand in *Input* (entradas) tab, then, press ```Ctrl + O``` to open a directory to a whole patient session. This path will now be the new default directory for opening images, and for full session processing tools.
86+
You can get some example models in https://drive.google.com/file/d/1-KLtcwjRtwhcib5pHKFOETuMyRsnyJTN/view?usp=sharing. Unzip this file, and then load the directory from File>>Load models (or Ctrl + Shift + O).
9387

88+
![image](https://user-images.githubusercontent.com/43280129/130434004-b6f9c374-9ffb-492f-a9be-9261b57544fd.png)
9489

95-
![dialog](https://user-images.githubusercontent.com/43280129/121792260-321b4100-cbb8-11eb-8ee5-b319fa4ae136.gif)
90+
Once your models have been loaded, you should find them available in the right bottom side, where the *Segmentation model* combo box will display the found models.
91+
*Observation: the directory you pick for your models can only contain models, otherwise any other file will be read as a model and will not be valid as a tensorflow model.*
9692

93+
![image](https://user-images.githubusercontent.com/43280129/130434468-b9ac8233-b034-40e3-bb6a-8463a9b01159.png)
9794

95+
Finally, pick the model you want to test and press *Load model*, this might take a couple seconds depending on your hardware.
9896

99-
## 3.2 Import a single thermal image
100-
Press ```Ctrl + I``` and select the image file you want to work with (format must be png or jpg). If you previously made the *Import folder* action, the File Dialog shown should be in your established path, otherwise, cloned directory will be shown by default.
101-
*Note: by using this action, you can't use the tools for full session processing, like "full plot". This is only avaliable when your last opening action was opening a folder.*
97+
## 3.2 Import a patient folder
98+
Now, keep in *Input* (entradas) tab, then, press ```Ctrl + O``` to open a directory to a whole patient session (*or File>>Open Folder*). This path will now be the new default directory for opening images, and for full session processing tools. Make sure that images in this directory are ```jpg``` format and named as ```t#.jpg``` where # is the amount of minutes elapsed to the capture, for example, ```t15.jp``` if 15minutes elapsed. Feet-GUI will use this to automatically set times later.
10299

103100

104-
### 3.3 Apply AI segmentation
105-
Segmentation algorithm is based on U-Net neural network. All training process is avaliable in https://github.com/Rmejiaz/FEET_U-Net.
106-
By pressing *Segment* button or ```Ctrl + F``` to an already displaying image (loaded either with open folder or open image)), the AI model makes the predict segmentation.
101+
![image](https://user-images.githubusercontent.com/43280129/130434757-81ca6ca3-74c6-4f58-bd48-8d5207db3589.png)
102+
![image](https://user-images.githubusercontent.com/43280129/130434803-57a2fc27-717b-43e7-a6d7-cff4bcc994b0.png)
107103

108-
![segment](https://user-images.githubusercontent.com/43280129/121792635-385fec00-cbbd-11eb-87f4-840644c1e1b6.gif)
104+
Once the direcotory is loaded, you will see a preview of the earliest in time found image (according to the naming rules).
109105

106+
![image](https://user-images.githubusercontent.com/43280129/130435148-ef8aadf8-aa36-4ecb-b232-694e8b845abb.png)
110107

111108

112-
In case AI does not offer desired results, user can choose the *manual segmentation*. By pressing this button, a new Dialog Window will be opened for the user to make the segmentation area in two stages. *(More on this in future versions)*
109+
110+
## 3.3 Import a single thermal image
111+
If desired, you can import a single image instead of a whole session. Press ```Ctrl + I``` and select the image file you want to work with (format must be png or jpg). If you previously made the *Import folder* action, the File Dialog shown should be in your established path, otherwise, cloned directory will be shown by default.
112+
*Note: by using this action, you can't use the tools for full session processing, like "full plot". This is only avaliable when your last opening action was opening a folder.*
113113

114114

115+
### 3.4 Apply AI segmentation
116+
By pressing *Segment* button or ```Ctrl + F``` to an already displaying image (loaded either with open folder or open image)), the AI model predicts segmentation area.
115117

116-
### 3.4 Get temperature curves
118+
![image](https://user-images.githubusercontent.com/43280129/130435712-56671f89-83e7-4489-99f5-b69aa13a0e5a.png)
117119

118-
Once you have already imported a directory for patient, you can get the temperature curves. You can press ```Ctrl + T``` for this action. Inmediately, a window will appear, showint the temperature curves based on the input images. It is important to have imported a directory, not an image.
120+
### 3.5 Set temperature scale
121+
If you want to force scale values for highest and lowest intensities found in the image you can do so by changing the values in the *Temperature scale* frame and picking the custom mode, otherwise, these scale would be extracted automatically.
119122

123+
![image](https://user-images.githubusercontent.com/43280129/130436073-52e9b805-477c-487b-80d0-839da87e4316.png)
120124

121-
![temp](https://user-images.githubusercontent.com/43280129/122077755-9f4df280-cdc1-11eb-9dbb-879b14504842.gif)
125+
In case AI does not offer desired results, user can choose the *manual segmentation*. By pressing this button, a new Dialog Window will be opened for the user to make the segmentation area in two stages. *(More on this in future versions)*
122126

127+
### 3.6 Get mean temperatures and curves
128+
If everything has been set up corectly, now you can get the mean temperatures and, if the Plot checkbox is set, you will also get the curves. You can press ```Ctrl + T``` for this action. If ```Plot``` is enabled, inmediately, a window will appear, showing the temperature curves based on the input images. It is important to have imported a directory, not an image.
123129

130+
![image](https://user-images.githubusercontent.com/43280129/130436802-b96aa011-7b01-48cb-8cfe-4b5315def4c1.png)
124131

125-
### 3.5 Make full plot!
126-
By clicking the *patient full plot* button, a new dialog will open and show the entire sessions plot. This is only avaliable when a folder has been the last file opening action.
127132

133+
### 3.7 Make full plot!
134+
By clicking the *patient full plot* button, a new dialog will open and show the entire sessions plot for all zones. This is only avaliable when a folder has been the last file opening action. *(More on this in future versions)*
128135

129136

130-
### 3.6 Save report
137+
### 3.8 Save report
131138

132-
Once you have done all processing, you can save your report as a pdf file by clicking the button "Export report". This action will only make sense if you have imported a whole directory with the correctly named files. If you execute this action without making all processing previously, it will be done automatically by default.
139+
Once you have done all processing, you can save your report as a pdf file by clicking the button "Export report". This action will only make sense if you have imported a whole directory with the correctly named files. If you execute this action without making all processing previously, it will be done automatically by default. *(More on this in future versions)*
133140

134141
## 4. Design
135142

136-
FEET-GUI is developed in such a way that it can work as a
143+
FEET-GUI is developed in such a way that it can work as a research tool or a live tool in healthcare conditions.
137144

138145
### 4.1 Preloaded images
139146

0 commit comments

Comments
 (0)