4907d0c0fb
Add and use saveNpArray
2024-04-25 15:59:26 +02:00
65708e4977
Correctly implement mean denoiser
...
Used to have:
```py
imageDenoisedNpArray = imageNpArray - means[color]
imageNoiseNpArray = imageNpArray - imageDenoisedNpArray
```
so:
```py
imageNoiseNpArray = means[color]
```
then we mean the mean...
While should have:
```py
imageDenoisedNpArray = means[color]
```
2024-04-25 15:58:24 +02:00
60a4f78fa6
Ease providing {min,max}Color
2024-04-25 15:30:23 +02:00
c642fa430e
Add commented code to crop image
...
It is commented as it does not seem to be finally what we are looking
for.
2024-04-25 14:37:08 +02:00
674ce8dabe
Use relative path for os.chdir in generate_histogram.py
2024-04-25 14:36:38 +02:00
807f586841
Remove no more relevant print in show_mean_noise.py
2024-04-25 14:28:36 +02:00
5c1f346f2e
Clean single image histogram
...
Source: https://www.codespeedy.com/plot-a-histogram-for-an-image-in-pil-python/
2024-04-25 14:16:58 +02:00
e2602347d4
Use a single figure to generate histogram
2024-04-25 12:39:24 +02:00
ec3ddd9c94
Add generate_histogram.py
2024-04-25 12:37:21 +02:00
Benjamin Loison
a78dcd6f99
Clean extract_noise.py
2024-04-24 14:10:22 +02:00
Benjamin Loison
c65b3642d8
Precise multiple_colors.png file name
2024-04-23 05:01:22 +02:00
be9d4f8f4b
Add denoiser mean possibility
2024-04-23 04:39:28 +02:00
a15b356e16
Add and use getImageNpArray
2024-04-23 04:38:40 +02:00
809aa7fb43
Correct Rafael images filtering
2024-04-23 04:37:46 +02:00
e3bbb2c63d
Precise possibilities for denoiser
2024-04-23 03:57:43 +02:00
fc0cc8808a
Add the missing import numpy as np in merge_single_color_channel_images_according_to_bayer_filter.py
2024-04-23 03:51:56 +02:00
Benjamin Loison
9f2334ceea
Precise imagesFolderPathFileName depending on sky or wall
2024-04-21 19:54:04 +02:00
Benjamin Loison
e2406071d4
Simplify specifying colors
2024-04-21 19:53:21 +02:00
Benjamin Loison
29f3acc479
Enable computing specific colors
...
For instance if have tested on one and do not want to waste its
computation.
2024-04-21 19:52:52 +02:00
9365b58d1d
#49 : Remove intermediary bias by not working on images but numpy arrays instead
2024-04-19 17:21:54 +02:00
675b01271a
#49 : Remove shift per color channel
2024-04-19 17:19:47 +02:00
77330e24d2
Make datasets/raise/merge_single_color_channel_images_according_to_bayer_filter.py production ready
2024-04-18 01:21:31 +02:00
0b52e781e3
First try to merge multiple single color channel images
2024-04-18 01:00:41 +02:00
6aca1126a1
Complete dict assignment
2024-04-18 00:53:15 +02:00
3636335b63
Add match statement
2024-04-18 00:52:08 +02:00
be91a07dd5
Add and use getImageFileNameByColor
2024-04-18 00:43:14 +02:00
fddb89c64a
Add datasets/raise/merge_single_color_channel_images_according_to_bayer_filter.py
2024-04-18 00:41:43 +02:00
Benjamin Loison
faaf3eb263
Ease support for single or multiple colors
2024-04-18 00:35:34 +02:00
Benjamin Loison
cca81927dd
Move Color Enum to utils.py
2024-04-18 00:19:01 +02:00
Benjamin Loison
eac2cf2174
Add a missing parameter
2024-04-18 00:18:20 +02:00
fb58d78fed
Name output file the same way as the input one
2024-04-18 00:13:21 +02:00
Benjamin Loison
8c9dfc2e41
Output an estimated PRNU per color channel
2024-04-17 20:25:14 +02:00
Benjamin Loison
f15af68bba
Add and use Color enumeration
2024-04-17 20:15:33 +02:00
Benjamin Loison
f4d8c028b2
Remove unnecessary spaces
...
Thanks to:
```bash
sed -i 's/^ *$//g' extract_noise.py
```
2024-04-17 14:32:55 +02:00
Benjamin Loison
3760164622
Add and use colorRawImageVisible
2024-04-17 14:27:03 +02:00
Benjamin Loison
83a12f4e0a
Add and use SKY and WALL
2024-04-17 14:26:13 +02:00
Benjamin Loison
e080e841f5
Add and use raiseNotFlatFields
2024-04-17 14:10:11 +02:00
Benjamin Loison
a6ef3977dd
Add comment concerning printing {min,max}Color
2024-04-16 16:48:29 +02:00
Benjamin Loison
8ca1972ddb
Correct raise not flat-fields processing
2024-04-16 16:48:00 +02:00
Benjamin Loison
817c016815
Give a try to get image size with rawpy but it seems far slower
...
As got:
```
Filtering images: 0%|▏ | 21/8156 [00:11<1:17:28, 1.75it/s]
```
2024-04-16 04:06:49 +02:00
Benjamin Loison
04e0de4d33
Try making not flat-images compatible
2024-04-16 03:59:26 +02:00
Benjamin Loison
3a4f774e28
Make denoise arguments depend on denoiser
2024-04-16 03:27:26 +02:00
Benjamin Loison
caf7025504
Correct typos in previous commit
2024-04-16 03:15:53 +02:00
Benjamin Loison
d4e13ed123
Compute automatically extreme values
2024-04-16 03:11:38 +02:00
Benjamin Loison
a8fa053687
#49 : Get PRNU by using RAW images
2024-04-16 03:02:58 +02:00
Benjamin Loison
6251c487e2
Add temporarily maxGreen computation
...
And got:
```
Denoising images: 0%| | 0/100 [00:00<?, ?it/s]maxGreen=2275
Denoising images: 1%|▌ | 1/100 [00:00<01:11, 1.38it/s]maxGreen=2377
Denoising images: 2%|█▏ | 2/100 [00:01<01:18, 1.24it/s]maxGreen=3468
Denoising images: 19%|███████████▌ | 19/100 [00:11<00:46, 1.75it/s]maxGreen=4908
Denoising images: 100%|████████████████████████████████████████████████████████████| 100/100 [00:57<00:00, 1.74it/s]
```
2024-04-16 02:51:27 +02:00
Benjamin Loison
90df8a7cb9
Verify raw.raw_pattern as raw.color_desc does not seem enough
...
As got:
```bash
python3 extract_noise.py
```
```
Denoising images: 0%| | 0/8156 [00:00<?, ?it/s]/mnt/HDD0/raise/nef/ra2c888f8t.NEF
Denoising images: 0%| | 0/8156 [00:00<?, ?it/s]
Traceback (most recent call last):
File "/home/benjamin/robust_image_source_identification_on_modern_smartphones/datasets/raise/extract_noise.py", line 73, in <module>
treatImage(imageFileName)
File "/home/benjamin/robust_image_source_identification_on_modern_smartphones/datasets/raise/extract_noise.py", line 46, in treatImage
assert np.array_equal(raw.raw_pattern, np.array([[3, 2], [0, 1]], dtype = np.uint8))
AssertionError
```
2024-04-16 01:06:59 +02:00
Benjamin Loison
120eaf563f
WIP: Add .nef support
2024-04-15 23:39:47 +02:00
Benjamin Loison
a0b366e98a
Use shebang compatible with venv
...
See [Benjamin-Loison/cpython/issues/10](https://github.com/Benjamin-Loison/cpython/issues/10 ).
2024-04-15 23:17:04 +02:00
Benjamin Loison
bddfa4c8d5
Clean datasets/raise/extract_noise.py
2024-04-15 16:16:29 +02:00
