System and method to automatically discriminate between a signature and a bar code

Abstract

There is described a system and method for automatically discriminating between different types of data with an image reader. In brief overview of one embodiment, the automatic discrimination feature of the present image reader allows a human operator to aim a hand-held image reader at a target that can contain a dataform and/or a signature and actuate the image reader. An autodiscrimination module in the image reader in one embodiment analyzes image data representative of the target and determines a type of data represented in the image data.

1 . A method for automatically discriminating between a dataform and a signature, the method comprising:
 collecting image data from an object with a an image reader, wherein said image reader includes an area image engine;   analyzing the image data to automatically discriminate between a dataform and a signature; by   attempting to decode the dataform by executing one or more dataform decoding algorithms upon the dataform to yield a decoding result, said decoding result including decoded dataform data or an indication of a decoding error; and   in response to if an indication of a dataform is present and to said decoding result, performing a binarization step that includes transforming a grey scale level representation of said image data into a binary representation according to local thresholding and target image size normalization;   performing a line thinning step that includes transforming multi-pixel thick line segments into single pixel thick line segments; and   extracting one or more features of said image data by convolution of said image data in search for indications of a presence of a signature.   
   
   
       2 . The method of  claim 1  where said convolution step employs detector maps that are configured to indicate a presence of curved elements. 
   
   
       3 . The method of  claim 1  where said convolution step employs a neural network to indicate an orientation of a signature. 
   
   
       4 . The method of  claim 1  where histogram analysis is employed to indicate a boundary of a signature. 
   
   
       5 . The method of  claim 1  where one-dimensional slices of pixels relative to an orientation of said signature are represented by said histogram analysis.