Project Description

Release Treasured Content Trapped in Historical Documents with IDA

The Challenge:

History resides in a predominately analog world; the future, however, is certainly headed in a digital direction. Making historical texts and archived information available is key to preserving their relevance. Many historical manuscripts and medieval books are written in a single-hand script or a historical font such as Blackletter and Gothic. They may also include different forms of the same letters as well as a large amount of superscribing, subscribing, and other hard-to-reproduce written formats. In an effort to save space, preserve documents, and make data more widely available, massive scanning and data capture projects have been initiated and are still ongoing. But scanning paper records is not the end of the preservation process; it is the beginning.

Planet AI’s Solution:

Indexing and classifying those records to make them available in the future is critical to the success of the conversion process. Manual capture from paper-based input is costly, error-prone, and inefficient.

The solution: IDA – Intelligent Document Analysis. Leveraging Planet AI’s proprietary, patented ATR (automatic text recognition) technology, rule- and template-based document processing belong to the past. IDA offers the most robust capturing capability that handles several use cases including historical fonts and scripts, hard-to-read text, and low-quality scans. Let IDA sort and categorize large volumes and extract relevant data afterward.

Customer Benefits:

IDA allows historians and researchers to automatically transcribe and further process old texts with remarkable speed and accuracy. Planet AI’s solution cost-effectively and efficiently converts large batches of historical text into digital format, making them accessible for the future. As an enterprise-grade solution, IDA supports the full spectrum of the processing chain, including capture, classification, data extraction, and validation. It is easily integrable into existing systems and scalable to support a variety of needs, from medium-sized to highvolume workflows.