Barcode recognition using data-driven classifier

• US 8,905,314 B2
• Filed: 10/23/2012
• Issued: 12/09/2014
• Est. Priority Date: 09/30/2010
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: van der Merwe, Rudolph, Noble, Samuel Gordon, Brunner, Ralph
• Primary Examiner(s): Marshall, Christle I
• Application Number:
  US13/658,765
• Publication Number:
  US 20130240628A1
• Time in Patent Office: 777 Days
• Field of Search: 23546201-46249, 382/103
• US Class Current: 235/462.15
• CPC Class Codes: G06K 7/10811 Focalisation
• CPC Class Codes: G06K 7/1443 locating of the code in an image
• CPC Class Codes: G06K 7/1447 extracting optical codes from image or text carrying said optical code

Abstract

A barcode decoding system and method are disclosed that use a data-driven classifier for transforming a potentially degraded barcode signal into a digit sequence. The disclosed implementations are robust to signal degradation through incorporation of a noise model into the classifier construction phase. The run-time computational cost is low, allowing for efficient implementations on portable devices. Implementations are disclosed for intelligent preview scaling, barcode-aware autofocus augmentation and multi-scale signal feature extraction.

Claims

1. A method comprising:

capturing a digital image of an object by a sensor of a device;

generating an image signal from the sensor;

calculating an envelope of the image signal at different spatial scales; and

filtering the envelope to extract object features,

where the method is performed by one or more processors.

2. The method of claim 1, where the object is a barcode and the object features are barcode symbol features.

3. The method of claim 1, further comprising:

training a learning based classifier using the object features.

4. The method of claim 3, where the learning based classifier is a neural network configured to provide a decoding quality metric.

5. The method of claim 4, where the decoding quality metric is used in the calculating of the envelope of the image signal at the differential spatial scales.

6. A system comprising:

one or more processors;

memory configured for storing instructions, which, when executed by the one or more processors, causes the one or more processors to perform operations comprising;

capturing a digital image of an object by a sensor of a device;

generating an image signal from the sensor;

calculating an envelope of the image signal at different spatial scales; and

filtering the envelope to extract object features.

7. The system of claim 6, where the object is a barcode and the object features are barcode symbol features.

8. The system of claim 6, further comprising:

training a learning based classifier using the object features.

9. The system of claim 8, where the learning based classifier is a neural network configured to provide a decoding quality metric.

10. The system of claim 9, where the decoding quality metric is used in the calculating of the envelope of the image signal at the differential spatial scales.