For Subscribers

Get the complete article now!

TWST: Can you give us a brief overview and history of Top Image Systems (NasdaqSC: TISA)?

Mr. Schechter: TiS is a public company that has traded on NASDAQ since 1996. We concentrate on data capture and data collection, providing our customers with a very unique technology that improves enterprises’ business processes by integrating information of different types and from multiple sources into corporate information systems. We have a platform solution called eFLOW, which can collect data from multiple sources such as paper, electronic, fax or from mobile personal devices and deliver this information to the main back-office systems of the organizations, i.e. their CRM, ERP, ECM or financial systems.

TWST: Is eFLOW your main product?

Mr. Schechter: Yes, it is the type of imaging handling solution that most of our clients require at the front-end. It connects to the organization’s workflow, and transfers the captured information into it. So we are the front-end solution for companies such as SAP, Documentum, Oracle and other similar companies. But if you look at it simply, we are basically reducing the data entry resources who are typing the information into the computer by 30-40 percent. We do it faster and more efficiently.

TWST: Who are you running up against competitively and what advantages do you bring to the space?

Mr. Schechter: Our main competitors are Captiva, a US company, and ReadSoft from Sweden, but there are several others, such as SER, Mitek, Cardiff and MTI. It is a pretty competitive niche market and each one of the competitors has different flavors to its products and solutions. All these companies have good technologies and are good competitors. We believe that we are best positioned towards the mid to high-end markets, the markets that need lots of forms to be processed daily and within a certain amount of time. For example, a typical Captiva customer will process a thousand forms per day and in the Indian census we are currently processing about 1.5 million forms a day. We can do this because our solution provides a very high recognition rate. We utilize many different engines to recognize the characters on the forms, and we employ a voting procedure to decide if there are two or more different readings across the engines. If, for example, two engines recognized a character as “9” and another engine recognizes it as “7”, then our eFLOW platform performs a voting procedure based on pre-defined rules and past performances of each engine. The high recognition rates our system provides is most definitely our main advantage. The systems that we develop for the high-end market that require large volumes and the fact that our technology is the most advanced in the market today, give us a clear edge.

TWST: What are some of the industry trends you are seeing in the data collection space?

Mr. Schechter: Over the last six months we have found out that the market is now moving towards the processing of semi-structured forms. Basically, there are three types of data that you can collect. One type is from forms such as census forms or applications for credit cards and mortgages. These are forms that are structured and predefined. The second type, which is the largest market now, is semi-structured forms. For example, take an invoice: when you and I look at the page, we can easily determine that it is an invoice. When your company is collecting over 100 invoices, obviously each one of them will be different, although they will basically contain the same type of information such as: account number, invoice number, date and amount. Utilizing our technology, which is based on artificial intelligence, we know how to read the form, to find out where the relevant fields are positioned and to process them. The third type of data you can collect is unstructured forms, which include emails and letters and we intend to approach this market in the near future.