EN/中文

產品資訊

嚴選代理產品的品質,完整的開發設備技術研究團隊與專業的整合技術,是我們最大的目標與堅持。

影像開發處理軟體 HALCON Progress 18.05

最新的 HALCON Progress 18.05

 

最新HALCON 18.05 版本於2018年5月22日發佈,並因應發布日期而命名為:HALCON 18.05

 

 

CPU Inference

 

With HALCON 18.05, customers will be able to perform deep learning inference on a CPU.

This CPU inference has been highly optimized for Intel®-compatible x86 CPUs. In tests, this resulted in a typical inference execution time on a standard Intel CPU (8 threads) that achieves performance similar to a midrange GPU.

Removing the need for a dedicated GPU greatly increases the operational flexibility. E.g., industrial PCs that usually are not designed for housing large and powerful GPUs can now easily be used for deep-learning-powered classification (inference).

Deep learning inference performing on CPUs

 

 

Improved Bar Code Reader

HALCON 18.05 features optimized edge detection, which improves the ability to reliably read bar codes with very small line widths as well as strongly blurred codes. Moreover, the quality of the bar codes is also verified in accordance with the most recent version of the ISO/IEC 15416 standard.

Bar code reading has been improved

 

 

Enhanced Deflectometry

 

The deflectometry functionality introduced in HALCON 17.12 now includes a new pattern type that improves the precision and robustness of error detection especially on partially specular surfaces like varnished metal sheets.

Enhanced deflectometry functionality

 

 

3D Improvements

 

The deflectometry functionality introduced in HALCON 17.12 now includes a new pattern type that improves the precision and robustness of error detection especially on partially specular surfaces like varnished metal sheets.

 

 

Automatic Handle Clearning


HALCON 18.05 also makes it much more comfortable to work with handles by clearing these automatically once they are no longer required. This significantly reduces the risk of creating memory leaks and makes writing "safe code" much simpler.

 

 

Support for Hypercentric Lenses

 

A new camera model within HALCON now allows the corrections of distortions in images that were recorded with hypercentric (also known as pericentric) camera lenses. These lenses can depict several sides of an object simultaneously, thus enabling a convergent view of the test object. With this technology, users only need a single camera system for inspection and identification tasks, e.g., the inspection of cylindrical objects.

 

HALCON supporting images recorded by hypercentric lenses

The object to be inspected and the image acquired with a hypercentric lense

 

 

 

HDevEngine Improvements


The HDevelop library export feature has been expanded: Developers can now access HDevelop procedures not just in C++, but also in .NET via an exported wrapper – as easily and intuitively as a native function. This significantly facilitates the development process.

 

 

 

最新的 HALCON Progress 17.12

 

深度學習 (Deep Learning)

 

HALCON 17.12-Progress 深度學習,使用者可透過CNN(Convolutional Neural Networks)分類器自行訓練,比起傳統MLP分類器效率高出約5-10%!

 

 

Training a CNN (Convolutional Neural Networks)

 

HALCON訓練CNN,需要提供足夠的數量標籤訓練來完成的圖片。例如,將區分顯示刮痕或污染的樣品,逶過提供良好的樣本,訓練所有三個種類的影像:影像顯示刮痕必須標記為“刮傷”,顯示某種污染的影像必須攜帶標籤

“污染”,顯示良好樣品的影像必須在”OK”類別中。然後,HALCON分析這些影像,並自動學習可以使用哪些功能,辨識缺陷和良好的樣品。與過去相比,這是一個極大的優勢的分類方法,這些功能必須由用戶“手工製作” - 過程較複雜,需要熟練視覺知識的工程師才能進行編程。

 

 

Using the Trained Network

 

一旦組織結構學會了區分給定的分類,例如: 告訴影像顯示有​​刮傷、污染或良好的樣品,組織結構就能立即運作。深度學習的典型應用領域包括缺陷分類(例如: 電路板、瓶口或藥丸)或物體分類(例如,識別植物的種類)。

 

 

HALCON 未來版本說明

 

從HALCON 17.12 開始,MVTec HALCON有兩種不同的軟體版本:

HALCON Progress 版本
HALCON Steady 版本

 

 

 

購買

採訂閱制(每年自動更新,授予對訂閱期間發布的所有版本的訪問權限);如購買後,需要停止購買時,請務必在到期日的三個月前通知我們! 標準購買

更新週期

約六個月更新一次 3年更新一次:定期維護更新可用

獲得新的功能

每六個月更新一次,獲得新的HALCON功能 每3年更新一次,獲得新的HALCON功能

產品品質

所有功能的高端品質

支援

在訂閱期間 長期支援

HDevEngine

兩者皆有 HDevEngine 開發方式

HDevelop

兩者皆有 HDevelop IDE 開發介面

Runtime licenses

無限制

Runtime license 升級

購買後,最多2年 -

開發許可

有效期僅限於訂閱期限 無限制

 

 

最新版本 - HALCON 17.12

 

要了解更多關於我們最新版本HALCON 13的眾多功能和改進,請點擊這裡

目前無檔案可供下載