TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Detexify: handwritten symbol recognition with HTML5

44 点作者 ysh4u超过 14 年前

5 条评论

sinc超过 14 年前
See also:<p><a href="http://news.ycombinator.com/item?id=700043" rel="nofollow">http://news.ycombinator.com/item?id=700043</a><p><a href="http://news.ycombinator.com/item?id=713743" rel="nofollow">http://news.ycombinator.com/item?id=713743</a><p><a href="http://news.ycombinator.com/item?id=1607964" rel="nofollow">http://news.ycombinator.com/item?id=1607964</a>
rflrob超过 14 年前
This works incredibly slowly for me (~30 seconds per symbol after I stop drawing), and doesn't work at all on my iOS devices (where I can actually draw reasonable looking characters, unlike with my mouse). Still, it's a really neat app.
评论 #1885207 未加载
评论 #1885159 未加载
chrishan超过 14 年前
Is it possible to extend the idea with equations (handwritten) as input, and produce the corresponding Latex source as output? That would save lots of time.
tomotomo超过 14 年前
As the interface is similar to Chinese character mouse input software (which is really fast), maybe the backends could be more similar..
zackattack超过 14 年前
this was where i first heard of the KNN algorithm (K nearest neighbors) - cool stuff.