diff --git a/Baseline/README.md b/Baseline/README.md
index 3baf0e5..edfcf48 100644
--- a/Baseline/README.md
+++ b/Baseline/README.md
@@ -1,6 +1,6 @@
 Polygon-Faster-RCNN-3 (P3) and Polygon-Faster-RCNN-5 (P5) are two baselines we introduced in our latest [IJDAR paper](http://web.fsktm.um.edu.my/~cschan/doc/IJDAR2019.pdf). Both of them are designed based on the Faster-RCNN object detection framework. 
 
-The implemetation is based on the [Tensorflow Object detection API](https://github.com/tensorflow/models/tree/master/research/object_detection).
+The implementation is based on the [Tensorflow Object detection API](https://github.com/tensorflow/models/tree/master/research/object_detection).
 
 The major difference between P3 and P5 is that P3 produces 6-vertex polygon bounding region while P5 produces 10-vertex polygon bounding region.
 
diff --git a/Groundtruth/Text/README.md b/Groundtruth/Text/README.md
index 3f27552..7389bb7 100644
--- a/Groundtruth/Text/README.md
+++ b/Groundtruth/Text/README.md
@@ -5,14 +5,14 @@ New training groundtruth of Total-Text is now available, they are refined with t
 1) Polygon bounding region with fixed number of vertex (10 vertex),
 2) The first point of the polygon bounding region is annotated according to the reading sequence of the text (i.e., top left corner of the annotated text).
 
-However, therer is no need for a new version of the test set groundtruth because 
+However, there is no need for a new version of the test set groundtruth because 
 
        1) there is no need of standardising the length of the groundtruth vertices for testing purpose, it was proposed to facilitate training only, and
        2) a new version of groundtruth would make the previous benchmarks irrelevant.
 
 Do contact us if you think there is a valid reason to require the new groundtruth for the test set, we shall discuss about it.
 
-More information can be found in our [IJDAR journal](http://web.fsktm.um.edu.my/~cschan/doc/IJDAR2019.pdf) (as refered to in the main page). 
+More information can be found in our [IJDAR journal](http://web.fsktm.um.edu.my/~cschan/doc/IJDAR2019.pdf) (as referred to in the main page). 
 
 The groundtruth of the Total-Text dataset can be downloaded through the following links. 
 
diff --git a/README.md b/README.md
index 5f0f388..fd01419 100644
--- a/README.md
+++ b/README.md
@@ -51,7 +51,7 @@ Total-Text and SCUT-CTW1500 are now part of the training set of the largest curv
 ## Table Ranking
 
 - The results from recent papers on Total-Text dataset are listed below where P=Precision, R=Recall & F=F-score.
-- If your result is missing or incorrect, please do not hesisate to contact us.
+- If your result is missing or incorrect, please do not hesitate to contact us.
 - The baseline scores are based on our proposed <a href="http://cs-chan.com/doc/IJDAR2019.pdf">[Poly-FRCNN-3]</a> in [this folder](https://github.com/cs-chan/Total-Text-Dataset/tree/master/Baseline).
 - <sup>*</sup>Pascal VOC IoU metric; <a href="https://arxiv.org/abs/1712.02170"><sup>**</sup>Polygon Regression</a>