This website works better with JavaScript.
Home
Issues
Pull Requests
Milestones
AI流水线
Repositories
Datasets
Forum
实训
竞赛
大数据
Register
Sign In
hummingbird
/
HyperLPR
Not watched
Unwatch
Watch all
Watch but not notify
2
Star
0
Fork
0
Code
Releases
0
Wiki
Activity
Issues
0
Pull Requests
0
Datasets
Model
Cloudbrain
Browse Source
Update README.md
pull/1/MERGE
syan
GitHub
7 years ago
parent
4caf4ec1e1
commit
93d7a1a8e3
1 changed files
with
1 additions
and
1 deletions
Split View
Diff Options
Show Stats
Download Patch File
Download Diff File
+1
-1
README.md
+ 1
- 1
README.md
View File
@@ -10,7 +10,7 @@ HyperLPR是一个基于Python的使用深度学习针对对中文车牌识别的
### 特性
+ 单张720p图像,单核Intel 2.2G CPU 识别时间140ms左右,比EasyPR单核识别速度快近10倍的时间。
+ 识别率在EasyPR数据集上0-error达到
70.2% 1-error识别率达到 89.6
%
+ 识别率在EasyPR数据集上0-error达到
81.75%, 1-error识别率达到 94.1
%
+ 检测方法在实时性、召回率、准确率上都优于MSER方法,检测recall和easyPR持平。
+ 代码框架轻量,总代码不到1k行。
Write
Preview
Loading…
Cancel
Save