From 02d30e167c8b15e447694ce75d70f7340aa6de7d Mon Sep 17 00:00:00 2001
From: matakshay <45757787+matakshay@users.noreply.github.com>
Date: Tue, 20 Aug 2019 18:12:47 +0530
Subject: [PATCH] Update README.md

---
 README.md | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index 20185d9..0bf1761 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,8 @@
 # digit_recognition
 Recognise and Classify handwritten digits from the MNIST Database using kNN Algorithm
 
-The MNIST Database contains 70,000 handwritten images of different digits. 60,000 of these images are input to the algorithm, along with their correct corresponding digit values. 
-Subsequent to this, any image from the remaining 10,000 can be input as a test case. Using a conventional k Nearest Neighbours Algorithm, the model tries to identify the digit in the image. 
-This prediction is compared with the acutal correct value. Also the value of k (i.e. number of nearest neighbours to be considered), can be set to an appropriate value so as to have good accuracy while also having a small execution time.
+The MNIST Database contains around 70,000 images of handwritten digits. 60,000 of these images are fed to the algorithm, along with their correct corresponding digit values. 
+
+Subsequent to this, any image from the remaining 10,000 can be input as a test case. Using the conventional k-Nearest Neighbours Algorithm, the model identifies the digit in the image. 
+
+This prediction is compared with the acutal correct value. Also the value of k (i.e. number of nearest neighbours to be considered), can be set to an appropriate value so as to have optimal accuracy, while simultaneously having a small execution time.