With this release (download here), we are adressing one of the market's strongest demands: Exploiting the power of deep learning in machine vision software.
Enhanced OCR Based on Deep Learning Technology
In MERLIC 3, the technologies for optical character recognition (OCR) have been further improved. MERLIC now includes a new, deep-learning-based OCR classifier that can be applied to numerous different fonts. This machine learning technology allows MERLIC 3 to achieve higher-than-ever recognition rates of number and character combinations on workpieces for reliable identification and further processing. Another advantage resulting from these improvements: Dot-print fonts are now read more robustly.
Improved Bar and Data Code Reading
The reading of bar and data codes has also been improved in MERLIC 3: Blurry, over-exposed, distorted, or low-contrast QR codes are now read more robustly. In addition, MERLIC can now even read partly occluded bar codes as well as QR codes with inconsistent column width.