Portable data collection device having optical character recognition

• US 6,000,612 A
• Filed: 10/10/1997
• Issued: 12/14/1999
• Est. Priority Date: 10/10/1997
• Status: Expired due to Term

• Current Assignee: Symbol Technologies, LLC (Zebra Technologies Corporation)
• Original Assignee: Metanetics Corporation
• Inventors: Xu, Jianhua
• Primary Examiner(s): Hajec, Donald
• Assistant Examiner(s): St. Cyr, Daniel
• Application Number:
  US08/949,073
• Time in Patent Office: 795 Days
• Field of Search: 235/454, 235/470, 235/469, 235/465, 235/462.11, 235/462.45, 235/472.01, 382/173, 382/176, 382/177
• US Class Current: 235/454
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06K 7/10722 Photodetector array or CCD scanning
• CPC Class Codes: G06V 30/10 Character recognition

Abstract

A portable data collection device providing for optical character recognition. A housing defines an internal region and includes a user handle that allows a user to position the housing relative to an indicia carrying target. An imaging assembly includes a two dimensional imaging array supported within the internal region of the housing. The imaging assembly includes a capture circuit that generates a video signal representative of an image of a target zone. An optics assembly supported by the housing focuses an image of the target area onto the photosensor array. A character recognition processing circuit receives the video signal and categorizes the indicia on the target into a set of predefined characters. The character recognition processing circuit includes a discriminator for identifying a text region of the target and identifying individual character regions within the text region and a categorizer for identifying a character from a set of possible characters for an individual character region. The categorizer performs one or more tests based on pixel data within the individual character region.

Claims

1. Portable data collection apparatus comprising:

a) a housing that defines an internal region and includes a user handle that allows a user to position the housing relative to an indicia carrying target;

b) an imaging assembly including a two dimensional imaging array supported within the internal region of the housing, the imaging assembly including a capture circuit that generates a video signal representative of an image of a target zone;

c) an optics assembly supported by the housing for focusing an image of the target area onto the imaging array; and

d) the imaging assembly operable in a selected one of a dataform reading mode and an imaging mode, the imaging assembly including image processing circuitry for interpreting the imaged indicia in the target zone as a dataform when the imaging assembly is operated in the dataform reading mode and character recognition processing circuitry for receiving the video signal and converting imaged indicia in the target zone into a set of predefined characters when the imaging assembly is operated in the imaging mode, the character recognition processing circuitry including;

i) a discriminator for identifying a text region of the image of the target and identifying individual character regions within the text region; and

ii) a categorizer for identifying a character from a set of possible characters for an individual character region, said categorizer performing one or more tests based on pixel data within the individual character region.

2. The apparatus of claim 1 wherein the imaging assembly further includes selection circuitry that includes a dataform reading switch selectively actuated by a user of the apparatus to operate the imaging assembly in the dataform reading mode and initiate a dataform recognition function and an imaging switch selectively actuated by a user of the apparatus to operate the imaging assembly in the imaging mode and initiate a text recognition function.

3. The apparatus of claim 2 wherein, upon actuation of the imaging switch the capture circuit determines a text frame within an image frame.

4. The apparatus of claim 1 wherein the character recognition processing circuitry implements a tree classifier for assigning character values to image regions based on the picture element content of the image regions.

5. The apparatus of claim 4 wherein the tree classifier is defined by multiple nodes that discriminate between different characters based upon one or more feature lists.

6. A method for recognizing characters within a region of a two dimensional captured image frame generated by a two dimension image array comprising the steps of:

a) receiving a video signal representative of the captured image frame and generating greyscale representations of image picture elements of the captured image frame;

b) identifying a text region within the image frame based upon a contrast value assigned to different areas that combine to make up the image;

c) converting greyscale representations for each picture element within the text region into a binary representation for such picture element;

d) identifying a subregion within a text region of said image frame as a bounding box for a character;

e) evaluating the picture elements within the bounding box based on an initial functional test that forms a partial classification of a character based on pixel data within the bounding box;

f) repeating one or more additional functional tests that are determined based upon the partial classification of the initial functional test to completely classify a character within the bounding box; and

g) identifying and classifying characters contained within other bounding boxes within the text region.

7. The method of claim 6 wherein multiple functional subtests make up the initial and additional functional tests used in classifying a character within a bounding box.

8. The method of claim 7 wherein the initial and additional functional test make up a decision tree for classifying a character within a bounding box.

9. The method of claim 8 wherein the decision tree includes decision steps that branch based on how a particular character font depicts the characters of said font.

10. The method of claim 6 wherein the bounding box is made up of multiple pixels and the function tests involve statistical calculations for the multiple pixels that are chosen to classify characters within the bounding box.

11. The method of claim 6 additionally comprising a step of re-orienting the text region prior to beginning a process of optical character recognition.

12. A portable data collection device including a two dimensional imaging assembly operable in a selected one of a dataform reading mode to decode a dataform within a target area and a character reading mode to convert text within the target area into a set of predefined characters, the imaging assembly comprising:

a) the two dimensional imaging assembly including a two dimensional photosensor array supported within an interior region of a housing, the imaging assembly when actuated generating a composite video signal representative of successive frames of an image of the target area;

b) an optics assembly supported by the modular housing for focusing an image of the target area onto the photosensor array; and

c) the imaging assembly further including image processing circuitry receiving the composite video signal, the image processing circuitry including;

i ) an analog to digital converter for converting a portion of the composite video signal corresponding to an image frame into a set of digital data representative of an image of the target area;

ii) conversion circuitry for converting the digital data into a set of digital gray scale values;

iii) cell extraction circuitry receiving the set of digital gray scale values and generating a set of binary values, each binary value corresponding to a different set of one or more image pixels of the image frame;

iv) dataform recognition and decoding circuitry electrically actuable by a dataform reader switch to read a dataform within the target area including selecting a subset of binary values from the set of binary values corresponding to an image of the dataform within a portion of the image frame and decoding a representation of the image of the dataform generated from the selected subset of binary values to generate decoded dataform data; and

v) an optical character recognition circuit electrically actuable by an imaging switch to capture an image within the target area including selecting a subset of binary values from the set of binary values corresponding to a text area within a portion of the image frame and generating image data corresponding to the image of the text area, the imaged text area being bounded by a contrasting reflectivity border region.

13. The portable data collection device of claim 12 wherein selected binary values generated by the optical character recognition circuit are associated with a character to be recognized.

14. The portable data collection device of claim 12 wherein the optical character recognition circuit implements a classifier based upon multiple functions that discriminate between character shapes.

15. A portable data collection device comprising:

a) a modular camera assembly including a photosensor array having a two dimensional array of photosensors, the photosensors of the array of photosensors being read out after an exposure period to generate an analog video signal representative of an image of a target area, the target area including either text or a target dataform;

b) a camera assembly housing for supporting components of the modular camera assembly;

c) an optic assembly including a lens assembly supported within a shroud assembly and positioned to focus illumination reflected from the target area onto the array of photosensors, the optic assembly having a best focus position at a predetermined distance from an outwardly facing optic surface of an outermost lens which results in a clearest image of the target area being focused onto the array of photosensors;

d) an illumination assembly supported within the housing and directing illumination towards the target area and including a lens array having a plurality of optic surfaces for directing illumination generated by illumination sources toward an illumination area substantially congruent with the target area; and

e) analog to digital conversion circuitry for converting the analog video signal into a set of gray scale values, a magnitude of a given gray scale value proportional to an intensity of illumination incident on a given photosensor of the array of photosensors during the exposure period, the intensity of illumination incident on the given photosensor dependent upon a transmittivity of the filter element overlying the given photosensor;

f) binarization circuitry for generating a set of binary picture element values based on gray scale values of the picture elements; and

g) image processing and decoding circuitry receiving as input the binary picture elements operable in a selected one of a dataform reading mode and an imaging mode, in the dataform reading mode, the image processing and decoding circuitry decoding an image of the target dataform, in the imaging mode, the image processing and decoding converting an image of text into a set of predefined characters.