SPICE™

Spatial Pattern Intelligent Content Extraction, or SPICE, is Tangent's proprietary suite of ICR algorithms used to automatically extract character content from images while ignoring extraneous values. SPICE is ideal for unstructured forms or forms with those with several variations. SPICE recognition differs considerably from the approach used by most vendors, since no time-consuming form setup is required. It instead relies on sophisticated heuristics and spatial analysis to perform intelligent data capture.

Benefits

• Increased freedom in document layout and design
• No form setup required for document variations
• Reduced pre-sorting
• Reduced data entry

Features

• Image pre-processing: SPICE can deskew, despeckle, remove lines and even remove fixed-form overlay graphics from images
• Analyzes character data relative to the position of each character
• Multiple algorithms optimized for different situations
• Real-time codeline reads and/or background read of whole image
• Applies masks, ranges, table lookups, database queries and inter-field cross-checks to ensure the accuracy of the extracted data

Typical Applications

• Automatic correction of OCR and MICR lines
• B2B "wholesale" remittance applications: extract invoice numbers and amounts from customer-generated check stubs
• Fulfillment applications: locate and extract account and finder numbers
• Check-only transactions: reading account numbers printed on checks generated by payment services
• Retail lock-box applications: locate and extract Optical Character Recognition (OCR) information regardless of where it is located on the document