diff --git a/.DS_Store b/.DS_Store
index a1888eb..b9d3dc6 100644
Binary files a/.DS_Store and b/.DS_Store differ
diff --git a/bounding_box.py b/bounding_box.py
old mode 100644
new mode 100755
index 0f4c481..ff55ba7
--- a/bounding_box.py
+++ b/bounding_box.py
@@ -29,6 +29,6 @@ while True:
d+=1
except:
- logging.exception("message")
+ # logging.exception("message")
print("All pages must be ready!")
break
diff --git a/burstpdf.py b/burstpdf.py
deleted file mode 100755
index 32e0e9c..0000000
--- a/burstpdf.py
+++ /dev/null
@@ -1,43 +0,0 @@
-#Based in the code in https://iq.opengenus.org/pdf_to_image_in_python/
-
-import pdf2image
-from PIL import Image
-import time
-
-#DECLARE CONSTANTS
-PDF_PATH = ("scans/out.pdf")
-DPI = 72
-FIRST_PAGE = None
-LAST_PAGE = None
-FORMAT = 'jpg'
-THREAD_COUNT = 1
-USERPWD = None
-USE_CROPBOX = False
-STRICT = False
-
-def pdftopil():
- #This method reads a pdf and converts it into a sequence of images
- #PDF_PATH sets the path to the PDF file
- #dpi parameter assists in adjusting the resolution of the image
- #first_page parameter allows you to set a first page to be processed by pdftoppm
- #last_page parameter allows you to set a last page to be processed by pdftoppm
- #fmt parameter allows to set the format of pdftoppm conversion (PpmImageFile, TIFF)
- #thread_count parameter allows you to set how many thread will be used for conversion.
- #userpw parameter allows you to set a password to unlock the converted PDF
- #use_cropbox parameter allows you to use the crop box instead of the media box when converting
- #strict parameter allows you to catch pdftoppm syntax error with a custom type PDFSyntaxError
-
- start_time = time.time()
- pil_images = pdf2image.convert_from_path(PDF_PATH, dpi=DPI, first_page=FIRST_PAGE, last_page=LAST_PAGE, fmt=FORMAT, thread_count=THREAD_COUNT, userpw=USERPWD, use_cropbox=USE_CROPBOX, strict=STRICT)
- print ("Time taken : " + str(time.time() - start_time))
- return pil_images
-
-def save_images(pil_images):
- d = 0
- for image in pil_images:
- image.save(("split/input%d"%d) + ".jpg")
- d += 1
-
-if __name__ == "__main__":
- pil_images = pdftopil()
- save_images(pil_images)
diff --git a/change_res.sh b/change_res.sh
new file mode 100755
index 0000000..0b1dd0e
--- /dev/null
+++ b/change_res.sh
@@ -0,0 +1,7 @@
+#!/bin/bash
+
+i=0
+for img in `ls scans/*.jpg`; do
+ convert $img -density 72 split/input$i.jpg
+ i=$((i+1));
+done
diff --git a/delete_and_start_over.sh b/delete_and_start_over.sh
new file mode 100755
index 0000000..6eda002
--- /dev/null
+++ b/delete_and_start_over.sh
@@ -0,0 +1,6 @@
+rm -R scans split rotated bounding_box ocred
+mkdir -p scans
+mv out.pdf $(date +%F-%H:%M).pdf && touch out.pdf
+sleep 2
+cp *.pdf ~/Desktop
+rm *.pdf
diff --git a/merge_scans.sh b/merge_scans.sh
deleted file mode 100755
index 21211f9..0000000
--- a/merge_scans.sh
+++ /dev/null
@@ -1,7 +0,0 @@
-#!/bin/bash
-#line 3 means here
-# cd "$(dirname "$0")"
-
-cd scans
-pwd
-convert *.jpg out.pdf
diff --git a/mirror_crop.py b/mirror_crop.py
old mode 100644
new mode 100755
diff --git a/readme.md b/readme.md
old mode 100644
new mode 100755
index a417292..ea9add1
--- a/readme.md
+++ b/readme.md
@@ -55,7 +55,7 @@ sudo pip3 install pdf2image Pillow opencv-python pytesseract
Make all the files executable.
```bash
-sudo chmod 777 merge_scans.sh workshop_stream.sh marge_files.sh
+sudo chmod 777 merge_scans.sh workshop_stream.sh rename_scans.sh change_res.sh delete_and_start_over.sh
```
In case you want to skip any of the scripts just comment out in the shell code, workshop_stream.sh.
@@ -116,15 +116,15 @@ mkdir bounding_box
mkdir cropped
```
###Merge the files in the directory scans
-All the scans will be appended to one pdf called out.pdf
+All the scans will be renamed
```bash
-./merge_scans.sh
+./rename_scans.sh
```
###Burst the pdf in scans
-Burst this pdf, renaming all the files so they can be iterated later.
+Change resolution of the scans so that it is lighter to process
```bash
-python3 burstpdf.py
+./change_res.sh
```
###Rotate the pdfs
@@ -140,7 +140,7 @@ python3 bounding_box.py
```
###Crop the mirror
-The pages are now cropped, but the mirror is still visible in the middle. I commented it out because if the cameras are positioned correctly there is no need for this step.
+The pages are now cropped, but the mirror may still be visible in the edge. This happens if the cameras are not adjusted properly. I commented it out because if the cameras are positioned correctly there is no need for this step.
```bash
python3 mirror_crop.py
```
@@ -156,6 +156,12 @@ python3 tesseract_ocr.py
```bash
./merge_files.sh
```
+
+##START OVER
+Just run delete_and_start_over.sh and start over
+```bash
+./delete_and_start_over.sh
+```
## License
The package is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).
diff --git a/remove.sh b/remove.sh
old mode 100644
new mode 100755
index 8c11f7b..7363bcb
--- a/remove.sh
+++ b/remove.sh
@@ -1,5 +1,4 @@
cd split
pwd
-rm page0.jpg
+rm input0.jpg
rm `ls *.jpg | tail -n 1`
-rm .DS_Store
diff --git a/rename_scans.sh b/rename_scans.sh
new file mode 100755
index 0000000..d509cc3
--- /dev/null
+++ b/rename_scans.sh
@@ -0,0 +1,7 @@
+#!/bin/bash
+
+i=0
+for img in `ls scans/*.jpg`; do
+ mv $img scans/input$i.jpg
+ i=$((i+1));
+done
diff --git a/rotation.py b/rotation.py
old mode 100644
new mode 100755
diff --git a/scans/.DS_Store b/scans/.DS_Store
deleted file mode 100644
index 5008ddf..0000000
Binary files a/scans/.DS_Store and /dev/null differ
diff --git a/workshop_stream.sh b/workshop_stream.sh
old mode 100644
new mode 100755
index b64026f..9cac6e5
--- a/workshop_stream.sh
+++ b/workshop_stream.sh
@@ -1,13 +1,13 @@
-./merge_scans.sh
+./rename_scans.sh
mkdir -p split
-python3 burstpdf.py
+./change_res.sh
+./remove.sh
mkdir -p rotated
python3 rotation.py
mkdir -p bounding_box
python3 bounding_box.py
-mkdir -p cropped
+# mkdir -p cropped
# python3 mirror_crop.py
mkdir -p ocred
python3 tesseract_ocr.py
-./remove.sh
./merge_files.sh