认识Vidi(一)

这篇是vidi的宣传文档,勇哥引用至些,方便各位观看。

目前在网上,vidi的和谐版是机密,大量骗子打着销售此软件的名号骗钱,这从一个侧面证明这款软件的效果上的成功。

各路神仙都从这套视觉软件上面看到了商机,是因为实它在视觉处理方面效果是前无古人的。

使用vidi如同“像人脑一样识别”!


image.png

image.png

image.png

image.png

image.png

A revolution is now underway and why is it possible only now? It is thanks to the presence of those 3 elements simultaneously (Abundance of Data, Affordable computing power and deep learning theory)


Many companies have invested / are still investing in this field in order to develop product (for some we are using them almost every day)

Siri as a voice recognition

Google Sef-driving car

IBM Watson who won in 2011 the game Jeopardy

And many more such as … (automatic labeling of photos by Apple and Facebook) and also

ViDi Suite for the industrial World …

image.png

A place crowded with people, many of which are visual quality inspectors.


So, why are there so many inspectors with their pink jackets, standing next to magnifying glass lamps?


Because, contrary to what we think, there are many visual inspection tasks that are difficult, if not impossible, to automate today.


Bat that is going to change!

image.png

Our Software as A unique architecture and This image processing software is composed / has an architure composed by a core technology which can be use through different ways/ with different focuses:

1.To find an element/characteristics/feature within the image (what it is and where it is?) 2.To identify a region of an image (what is different from the norm ?) 3.To describe/analyse the image itself (what it is?)

image.png

ViDi blue:

reading characters punched into steel billets
counting medical ampules for process control and packaging
detecting, identifying and tracking of objects in movies (here dashboard camera)


ViDi red:

detecting anomalies/defects in textiles
detecting aesthetic defects on decorated surfaces of watch parts
segmenting bones for meat processing and robot guidance


ViDi green:

appearance based product identification (logistics)
vision based classification of welding spot quality based (non-destructive testing)

sorting of beer bottles according to vendor identity (recycling)

image.png

image.png

image.png



OCR(Optical Character Recognition)

识别率 > 98%

(with error correction)



image.png

OCR 案例

image.png

image.png

image.png

image.png

image.png

image.png

image.png

image.png


Google 街拍门牌号

image.png


钢铁的跟踪

image.png

image.png


零件的定位 

image.png

低照度下的定位

image.png


有遮挡物的定位

image.png

高反光材料的定位

image.png

工件定位

image.png


image.png

image.png

image.png




image.png

§像人一样定位 

§通过自学习的方式,无需编程,仅仅点击选择就可定位

§ 功能强大,解决了复杂环境下的跟踪和识别



本文出自勇哥的网站《少有人走的路》wwww.skcircle.com,转载请注明出处!讨论可扫码加群:

发表评论:

◎欢迎参与讨论,请在这里发表您的看法、交流您的观点。

会员中心
搜索
«    2024年3月    »
123
45678910
11121314151617
18192021222324
25262728293031
网站分类
标签列表
最新留言
    热门文章 | 热评文章 | 随机文章
文章归档
友情链接
  • 订阅本站的 RSS 2.0 新闻聚合
  • 扫描加本站机器视觉QQ群,验证答案为:halcon勇哥的机器视觉
  • 点击查阅微信群二维码
  • 扫描加勇哥的非标自动化群,验证答案:C#/C++/VB勇哥的非标自动化群
  • 扫描加站长微信:站长微信:abc496103864
  • 扫描加站长QQ:
  • 扫描赞赏本站:
  • 留言板:

Powered By Z-BlogPHP 1.7.2

Copyright Your skcircle.com Rights Reserved.

鄂ICP备18008319号


站长QQ:496103864 微信:abc496103864