From caf29b656722896caf4c08139ad84762f26a4eed Mon Sep 17 00:00:00 2001
From: Sefik Ilkin Serengil <serengil@gmail.com>
Date: Mon, 23 Mar 2020 09:04:29 +0300
Subject: [PATCH] face recognition test

---
 README.md | 12 +-----------
 1 file changed, 1 insertion(+), 11 deletions(-)

diff --git a/README.md b/README.md
index b679854..f5de13b 100644
--- a/README.md
+++ b/README.md
@@ -17,17 +17,7 @@ result = DeepFace.verify("img1.jpg", "img2.jpg")
 print("Is verified: ", result["verified"])
 ```
 
-<p align="center"><img src="https://raw.githubusercontent.com/serengil/deepface/master/tests/dataset/test-case-2.jpg"  width="50%" height="50%"></p>
-
-```json
-{
-   "verified": true,
-   "distance": 0.25638097524642944,
-   "max_threshold_to_verify": 0.40,
-   "model": "VGG-Face",
-   "similarity_metric": "cosine"
-}
-```
+<p align="center"><img src="https://raw.githubusercontent.com/serengil/deepface/master/tests/dataset/test-case-4.jpg" width="95%" height="95%"></p>
 
 Each call of verification function builds a face recognition model from scratch and this is a costly operation. If you are going to verify multiple faces sequentially, then you should pass an array of faces to verification function to speed the operation up. In this way, complex face recognition models will be built once.