CharacTell maintains the belief that it is possible to break technological barriers in the area of automated character recognition. We met this goal by developing Advanced Character Recognition™ (ACR™), our core technology that superseded capabilities existing technologies, while opening the door to new applications that previously had not been feasible.

CharacTell's mission is:To continue to demonstrate technical leadership in recognition by offering competitive ACR-based products that would satisfy real customer needs - developers and users alike - in existing and growth markets.

CharacTell Ltd was founded in 1998 by Mr. Ofer Comay and Dr. Eliyahu Comay with the goal of developing advanced character recognition technology that avoided many of the limitations that hindered the technologies of the time. In creating ACR, the pair - bringing expertise and many years of mathematical, technical and scientific experience to the effort - succeeded in not only improving recognition performance of hand-printed characters over existing products, but for the first time made recognizing hand-written characters practical and successful.

In 2001, Dr. Paz Kahana joined CharacTell and became its President and CEO. Dr. Kahana brings to CharacTell years of expertise in marketing and management, that are crucial for CharacTell’s continued growth and development.

Handwriting is one of the most common and natural ways for humans to communicate. This is true for what we do: notes we take, letters we write, and documents we produce. ACR uniquely identifies characters based on concepts equivalent to methods used to analyze the structure of the human genome. ACR has the ability to learn languages, fonts, and individual handwriting styles, quickly and completely, using smaller sample sets than any existing technology. It identifies characters with accuracy rates resembling the determinism generated when DNA analysis is used to pinpoint the identity of an unknown person. An important and strategic feature of ACR is that is learns and trains not only uniquely, but at a fraction of the time, sample size and cost that is needed elsewhere.