FormFix

Form Setup

• API support for setting up fields, form templates, and sets of form templates
• Flexible architecture for defining custom operations at any stage of processing
• Define OMR, text, image, or custom fields on each form
• Extensive support for form processing operations

Form Identification

• Match forms against previously defined unfilled templates and return confidence values
• Provide automatic identification without the need for registration marks, ID marks, or anchor marks
• Match forms that are rotated 90, 180, or 270 degrees from template image
• Match forms that have been scaled from 90% to 110% of the template size
• Match forms scanned with resolution of 50% to 150% of the template resolution
• Match forms that are skewed up to 20 degrees by pre-processing with the included ScanFix
• Identify thousands of different forms
• Limit a recognition operation to a subset of the available templates
• Set the level of effort expended in completing form matching
• Return Identification Certainty indicating confidence of form matching
• Accept a Minimum Certainty level for acceptance as a matched form
• Return up to 100 alternative form matches of lower certainty
• Quickly identify forms, even when using very large sets of template forms

Form Registration

• Automatically align a filled form to its master template based on image contents, to within one or two pixels of the blank template without requiring registration marks
• Analyze the master template form content and determine anchor points automatically
• Adjust alignment within a drop out zone to compensate for small differences between forms
• Support an alternate registration process using anchor marks in each corner
• Register forms even when the forms exhibit these characteristics:
  • Skew (up to 20 degrees)
  • Smaller or larger image size than the template (up to 10%)
  • Forms scanned at different resolutions (up to 50% greater and lesser) than the template resolution
  • Rotation (at 90, 180, and 270 degrees from the template)

SmartZone

Zone Definition & Processing

• Perform recognition on defined zones
• Perform image cleanup on defined zones

Optical Character Recognition (OCR)

• Recognize text using pre-defined character sets, including uppercase, lowercase, mixed case alphabetic, digits, currency symbols, combined currency and digits, arithmetic symbols and punctuation characters
• Limit recognition to customer defined subsets of supported character sets
• Return confidence values for each individual character, as well as the complete OCR result, to help manage the recognition process
• Return multiple character results with associated confidence values
• Specify the rejection character provided when recognition of a character fails
• Specify the confidence level below which the rejection character is returned
• Specify recognition segmentation parameters
• Support English characters only

Image Input, Image Output, and Image Handling

• SmartZone includes ImagXpress Standard for basic image conversion, image processing, and TWAIN scanning
• Support image data transfer with other components

Bitonal Image Cleanup

• SmartZone Professional and Standard editions include ScanFix Xpress Lite for bitonal image cleanup technology such as deskew, despeckle, rotate, mirror, flip and more

ScanFix Xpress

Image Input, Image Output, and Image Handling

• Provided through the included ImagXpress Professional .NET component and ActiveX/COM control
• Features include image viewing, compression, conversion, TWAIN scanning, annotation, printing, image processing, and more

Deskew

• Automatically straighten crooked images and report correction angle
• Deskew images in a fraction of a second
• Uses content of the images, not just the document
• User configurable High Quality vs. High Speed setting
• High Quality sets a higher number of places to check around the image, ultimately providing the highest level of deskew accuracy, but the image processing speed is slower
• High Speed sets a lower number of places to check around the image, ultimately providing the fastest image processing speed, but offers a slightly lower level of accuracy

Noise Removal

• Remove random specks or noise from images
• Configurable user specification of speck size, or use automatic settings
• Special Isolated Despeckle algorithm prevents removal of desired dots such as punctuation

Dot Shading Removal

• Automatically remove dot shading surrounding text for improved OCR accuracy
• Remove scanner noise caused by colored backgrounds (gray, blue, etc.)
• Reduce files sizes caused by additional pixels, without destroying text

ImagXpress Document

Document Image Processing and Editing

• Comprehensive set of over 80 image processing functions
• Automated 1 bpp image cleanup
• Configurable Binarization and Half Toning
• Anti-alias and scale to gray
• Advanced merging capabilities
• Autocrop
• Automatic Deskew - Automatically detect and remove skew from bitonal images. Detection focuses on the content of the image, such as text and drawings, rather than the border. You can also specify acceptable skew angle, quality, and confidence levels
• Despeckle - Use advanced technology to remove specks from bitonal images, including specification of speck size and reporting of number of specks removed
• Line Removal - Remove lines of defined size, thickness, and other specifications, from bitonal images. Report the number of lines removed
• Dilate - Add black pixels to extend objects vertically, horizontally, or diagonally
• Erode - Remove black pixels from objects in bitonal images vertically, horizontally, or diagonally
• Smooth Zoom - Enhance character clarity, using Smooth Zoom. Replace an image with a new image with width and height doubled and with pixels smoothed
• Shear - Apply rotation of bitonal images, along only the vertical or horizontal axis, by the specified angle in degrees. Allow the user to specify the color with which to pad the image
• Hole Punch & Blob Removal - Locate and remove all black blobs (e.g. hole punch marks) in bitonal images, within a defined search area, based on size or density. Detect and report the number of blobs found within the search area
• Blank Page Detection - Automatically determine that a page is blank within a set of bitonal images, by detecting if no objects are found to exceed the minimum object dimension. A border (top margin, left margin, right margin, bottom margin) within which to test for blank page, and minimum confidence, can be specified
• Border Crop - Remove the black border around a bitonal image
• "Preserve Dark" Detail Enhancement
• Ideal for enhancing thumbnail images or images that are zoomed out
• Preserve the dark pixels of an image when an image is scaled at ratios less than 1:1 (many pixels are averaged for the one displayed)
• Avoid losing details in fine lines or fine text
• Retention of image transparency
• Color anti-aliasing and smoothing for zoomed
• Adjust contrast, brightness, hue, saturation, gamma, and more (Display adjustment of contrast, brightness, and gamma)
• 24, 8, 4, and 1-bit color depth conversions with advanced palette control
• Area and region processing