Adding binarization support

Author: soumyadeep9

contrib/README.md

@@ -10,6 +10,7 @@ Each project should live in its own subdirectory ```/contrib/<project>``` and co
 |---|---|---|
 | [Crowd counting](crowd_counting) | Counting the number of people in low-crowd-density (e.g. less than 10 people) and high-crowd-density (e.g. thousands of people) scenarios. | [![Build Status](https://dev.azure.com/team-sharat/crowd-counting/_apis/build/status/lixzhang.cnt?branchName=lixzhang%2Fsubmodule-rev3)](https://dev.azure.com/team-sharat/crowd-counting/_build/latest?definitionId=49&branchName=lixzhang%2Fsubmodule-rev3)|
 | [Action Recognition with I3D](action_recognition) | Action recognition to identify video/webcam footage from what actions are performed (e.g. "running", "opening a bottle") and at what respective start/end times. Please note, that we also have a R(2+1)D implementation of action recognition that you can find under [scenarios](../sceanrios).| |
+| [Document Image Binarization](binarization) | Binarization is a technique to segment foreground from the background pixels. A simple technique for binarization is thresholding of gray-level or color document scanned images.| |
 
 ## Tools
 | Directory | Project description | Build status (optional) |

contrib/binarization/README.md

@@ -0,0 +1,17 @@
+# Binarization
+Binarization is a technique to segment foreground from the background pixels. A simple technique for binarization is thresholding of gray-level or color document scanned images.
+## At a glance
+
+This binarization technique is an improvement over Sauvola's binarization technique. In this work, we improve the existing Sauvola's binarization technique by preserving more foreground information in the binarized document-images. In order to achieve this, we introduce a confidence score for the background pixels. 
+
+### Input images
+
+<img src="./confidence_based_Sauvola_binarization/test_images/2.jpeg" width="33%"> </img>
+<img src="./confidence_based_Sauvola_binarization/test_images/10.jpeg" width="33%"> </img>
+<img src="./confidence_based_Sauvola_binarization/test_images/new1.jpg" width="33%"> </img>
+
+### Binary outputs
+
+<img src="./confidence_based_Sauvola_binarization/results/2_bin_new.png" width="33%"> </img>
+<img src="./confidence_based_Sauvola_binarization/results/10_bin_new.png" width="33%"> </img>
+<img src="./confidence_based_Sauvola_binarization/results/new1_bin_new.png" width="33%"> </img>

contrib/binarization/confidence_based_Sauvola_binarization/Modified-Sauvola_Binarization.ipynb

@@ -0,0 +1,64 @@
+'''
+@author: Soumyadeep Dey
+				email:Soumyadeep.Dey@microsoft.com
+				Date: October 2020
+				cite: https://drive.google.com/file/d/1D3CyI5vtodPJeZaD2UV5wdcaIMtkBbdZ/view?usp=sharing
+'''
+
+# importing required libraries
+import numpy as np
+import cv2
+from skimage.filters import threshold_sauvola
+
+
+def SauvolaModBinarization(image,n1=51,n2=51,k1=0.3,k2=0.3,default=True):
+    '''
+	 Binarization using Sauvola's algorithm
+		@name : SauvolaModBinarization
+	 parameters
+		@param image (numpy array of shape (3/1) of type np.uint8): color or gray scale image
+	 optional parameters
+		@param n1 (int) : window size for running sauvola during the first pass
+		@param n2 (int): window size for running sauvola during the second pass
+		@param k1 (float): k value corresponding to sauvola during the first pass
+		@param k2 (float): k value corresponding to sauvola during the second pass
+		@param default (bool) : bollean variable to set the above parameter as default. 
+
+			@param default is set to True : thus default values of the above optional parameters (n1,n2,k1,k2) are set to
+				n1 = 5 % of min(image height, image width)
+				n2 = 10 % of min(image height, image width)
+				k1 = 0.5
+				k2 = 0.5
+		Returns
+			@return A binary image of same size as @param image
+		
+		@cite https://drive.google.com/file/d/1D3CyI5vtodPJeZaD2UV5wdcaIMtkBbdZ/view?usp=sharing
+    '''
+
+    if(default):
+        n1 = int(0.05*min(image.shape[0],image.shape[1]))
+        if (n1%2==0):
+            n1 = n1+1
+        n2 = int(0.1*min(image.shape[0],image.shape[1]))
+        if (n2%2==0):
+            n2 = n2+1
+        k1 = 0.5
+        k2 = 0.5
+    if(image.ndim==3):
+        gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+    else:
+        gray = np.copy(image)
+    T1 = threshold_sauvola(gray, window_size=n1,k=k1)
+    max_val = np.amax(gray)
+    min_val = np.amin(gray)
+    C = np.copy(T1)
+    C = C.astype(np.float32)
+    C[gray > T1] = (gray[gray > T1] - T1[gray > T1])/(max_val - T1[gray > T1])
+    C[gray <= T1] = 0
+    C = C * 255.0
+    new_in = np.copy(C.astype(np.uint8))
+    T2 = threshold_sauvola(new_in, window_size=n2,k=k2)
+    binary = np.copy(gray)
+    binary[new_in <= T2] = 0
+    binary[new_in > T2] = 255
+    return binary

contrib/binarization/confidence_based_Sauvola_binarization/ModifiedSauvola.pdf

@@ -0,0 +1,43 @@
+# Binarization
+Binarization is a technique to segment foreground from the background pixels. A simple technique for binarization is thresholding of gray-level or color document scanned images.
+## At a glance
+
+This binarization technique is an improvement over Sauvola's binarization technique. In this work, we improve the existing Sauvola's binarization technique by preserving more foreground information in the binarized document-images. In order to achieve this, we introduce a confidence score for the background pixels. 
+
+### Input images
+
+<img src="./test_images/2.jpeg" width="33%"> </img>
+<img src="./test_images/10.jpeg" width="33%"> </img>
+<img src="./test_images/new1.jpg" width="33%"> </img>
+
+### Sauvola outputs
+
+<img src="./results/2_bin_old.png" width="33%"> </img>
+<img src="./results/10_bin_old.png" width="33%"> </img>
+<img src="./results/new1_bin_old.png" width="33%"> </img>
+
+### Confidence based Sauvola outputs
+
+<img src="./results/2_bin_new.png" width="33%"> </img>
+<img src="./results/10_bin_new.png" width="33%"> </img>
+<img src="./results/new1_bin_new.png" width="33%"> </img>
+
+## Reference
+
+For details refer to this [paper](./ModifiedSauvola.pdf) 
+
+
+
+
+## Setup
+
+### Dependencies
+- python 3.7
+- numpy 1.16
+- opencv 4.2
+- skimage 0.17
+
+
+### Example
+
+Sample example of the usage of the said binarization technique can be found in this [notebook](./Modified-Sauvola_Binarization.ipynb).