More and more machine vision software companies have deployed deep learning technologies in their products. As these companies develop deep learning software and tools, and more users are successfully deployed in their applications, deep learning may become more popular and more popular in the market.

According to reports, ViDiSystems, which Cognex acquired in 2017, is one of them. ViDiSystems was founded in 2012 by RetoWyss, Ph.D. in computational science. The company developed software that uses artificial intelligence (AI) technology to improve image analysis in applications that train the system to distinguish between acceptable changes and defects. CognexViDiSuite consists of three different tools, including the fixture ViDiBlue, ViDiRed for segmentation and anomaly detection, and ViDiGreen for object and scene classification. Cognex's deep learning software is specifically designed for inspection applications. There have been many successful cases in the pharmaceutical, medical products, automotive, textile, printing and watch industries.

Cognex believes that deep learning complements traditional machine vision. Traditional geometric pattern discovery and edge detection are still the best methods for sub-pixel precision for robot guidance or other accurate measurements. Deep learning is most valuable in parts quality and other paradigm-based human judgments, and because it is trained by paradigms, it does not require the advanced visual skills required to check applications before.

South Korea's machine vision software company Sualab recently released SuaKIT inspection software. This is based on a database of actual image data from various industrial sites and classifies the main functions. The software's deep learning algorithm uses neural networks to automatically identify defect values ​​using new images of normal and defective products trained at speeds of up to 1,000 2,048&Times; 2,048 images within 30 minutes.

Even users who do not have much programming experience can use the software because it does not require code-by-instance coding but learns by collecting and entering defect data. SuaKIT can also use high-performance GPUs to process data at high speeds using NVIDIA's CUDA technology.

The Deputy Manager of Sualab Enterprise Group stated that using deep learning can significantly reduce errors in the testing process. Deep learning combined with CUDA technology enables SuaKIT to exhibit higher levels of performance even in high-speed manufacturing processes.

The German company MVTec also incorporated deep learning technology into its famous Halcon and Merlic machine vision software products. Since Halcon13, MVTec is providing deep-learning-based optical character recognition (OCR). The software now includes OCR classifiers based on deep learning technology that can be used with some pre-trained fonts, thus enabling higher reading rates than all previous classifications.

In addition, the latest version of Halcon allows users to perform Convolutional Neural Network (CNN) training based on deep learning algorithms. The trained network automatically classifies image data corresponding to a predetermined category. MVTecHalcon product manager said that customers can save a lot of time, effort and money by using Halcon's self-trained network.

For example, defect classes can be identified by referring to images, so there is no need for cumbersome programming. In the industrial machine vision environment, deep learning is mainly used for classification tasks that occur in many applications, such as inspection of industrial products or identification of parts.

Another company that develops deep learning software is CythSystems. Its NeuralVision is designed for product inspection and classification for users without machine vision experience. In a conventional machine vision system, a program designer selects an analysis algorithm to be applied to an image, such as hole detection, temperature analysis, or width measurement, to check the image and determine good or bad parts.

Because the system provides images of related objects and informs the appearance of unique parts, or if they see good or bad parts, the system uses millions of algorithms to learn to recognize what is seen. By showing the system various changes, such as lighting, shadows, and the environment, it will learn to understand where features are not important for identifying parts.

Intelligent Universal Circuit Breakers

Intelligent Universal Circuit Breakers,Frame Type Low Voltage Circuit Breaker,Low Voltage Vacuum Circuit Breaker,Low Voltage Power Circuit Breaker

TRANCHART Electrical and Machinery Co.,LTD , https://www.tranchart-electrical.com

Posted on