bit of an off topic post, but this demo includes barcode recognition within digital photos from an iPad:
Wednesday, July 11, 2012
Friday, June 15, 2012
Sunday, June 10, 2012
OCR and SharePoint: What features do I need?
As many organizations go down the road to place scanned documents into SharePoint, there are several areas of key focus. A little planning will help to leverage OCR technology, and pre-OCR documents before they are placed in a SharePoint library as PDFs. So what is the true value of OCR in any SharePoint deployment? It all depends on what you are trying to achieve. The Scanning with SharePoint BLOG has a great post on what to evaluate before you start the scanning process: How do you want to find your documents in SharePoint? Below are some ways to utilize OCR, and some definitions of key types:
- Full Text OCR - Optical Character Recognition for SharePoint, or OCR is typically associated with conversion of an image to full text. When you scan a document, it is a pure image, and the text within is not searchable, nor can you copy and paste. The OCR process can give you pdfs that can be indexed by SharePoint Search. Is Full Text OCR Necessary? Read the link for some thoughts.
- Zone OCR - Zone OCR can be utilized to extract information from a specific location on a repeatable form. The information collected can be automatically entered into a SharePoint column. This is a huge time save if you need to automatically collect information from a large volume of forms, and Optical Character Recognition by zone can really help speed up the process.
- Advanced Data Extraction (ADE) - This is the ultimate in efficiency and automation, and only a few apps give you this OCR functionality without an exorbitant cost. In a nutshell, ADE provides pattern matching for information extraction. So if you are looking for a 6 digit number, it auto-extracts this information. During the OCR process, ADE adds to accuracy and speed by finding only what you need. inForm has a great product for SharePoint Capture and OCR that can provide a robust ADE engine.
- Point and Click OCR - Point and Click OCR allows you to use the mouse to choose what you want to throw into a SharePoint field. The images are pre-OCR'd or the process is performed real time to give you the desired information.
- Rubberband OCR - this method of OCR processing allows you to drag your mouse over an area of text and auto-enter the data into a SharePoint column. It is great for information that spans multiple lines, and can convert the text in the image quite easily.
Wednesday, June 6, 2012
Tuesday, May 15, 2012
In examining Optical Character Recognition (OCR) software, you need to examine your needs and determine what type you require.
Desktop OCR SoftwareFor day to day use, most users will utilize Desktop OCR software. It is appropriate for converting scanned documents to Word format, copying and pasting sections from documents, etc. Apps that fall into this category are OmniPage, PaperPort, etc.
Batch OCR and Capture SoftwareIf you are processing large volumes of documents, and need to enable a process or workflow with scanners in your company, typically you will utilize document capture software with enhanced OCR capabilities. This type of OCR Software takes processing to the next level and uses automation to extract information from the documents, as well as make them searchable PDF documents. An example of this type of software is inForm's iCapture.
Wednesday, May 9, 2012
So just how important is your PC hardware when looking to use OCR Software? Many of the desktop products do not take advantage of multi-core CPUs, and can have laggard performance numbers when it comes to Optical Character Recognition, Intelligent Character Recognition and Optical Mark Recognition. Currently, playing with PSI:Capture, which offers a number of OCR options, and they have single, dual and quad core enablement in their licensing. Dual core runs about 1.7 times the speed, and quad core gives a 2.7x improvement.