diff --git a/README.md b/README.md
new file mode 100644
index 0000000..5c6e992
--- /dev/null
+++ b/README.md
@@ -0,0 +1,14 @@
+# 人脸识别匹配
+
+## 1.实现步骤
+
+- 首先初始化摄像头然后，识别人脸，并抓拍十张照片
+
+- 如果没有可以创建数据库，如果数据库已经存在，会调用已经存在数据库
+
+- 抓拍的十张照片一次匹配，返回结果
+
+## 2.运行
+
+- 直接运行scanf_face.py文件即可
+- 添加人脸数据到数据库已经在scanf_face.py实现，调用即可
\ No newline at end of file
diff --git a/add_face.py b/add_face.py
deleted file mode 100644
index 6a1463f..0000000
--- a/add_face.py
+++ /dev/null
@@ -1,35 +0,0 @@
-import cv2
-import face_recognition
-import sqlite3
-import numpy as np
-
-from match_face import save_face_encoding
-
-
-def add_new_face(name):
-    cap = cv2.VideoCapture(0)
-
-    while True:
-        ret, frame = cap.read()
-        rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
-
-        face_locations = face_recognition.face_locations(rgb_frame)
-        face_encodings = face_recognition.face_encodings(rgb_frame, face_locations)
-
-        if face_encodings:
-            # 假设只处理第一张检测到的人脸
-            encoding = face_encodings[0]
-            save_face_encoding(name, encoding)
-            print(f"Face of {name} saved!")
-            break
-
-        cv2.imshow('Capture New Face', frame)
-        if cv2.waitKey(1) & 0xFF == ord('q'):
-            break
-
-    cap.release()
-    cv2.destroyAllWindows()
-
-
-# 示例用法
-add_new_face("John Doe")