Image based object classification

Patent metadata

Field	Value
Publication number	US-10062008-B2
Application number	US-201314897916-A
Country	US
Kind code	B2
Filing date	Jun 13, 2013
Priority date	Jun 13, 2013
Publication date	Aug 28, 2018
Grant date	Aug 28, 2018

Abstract

A method for classifying an object in image data to one out of a set of classes using a classifier, said image data comprising an image of the object, each class indicating a property common to a group of objects, the method comprising the steps of obtaining said classifier used to estimate for an input feature vector a probability for each of the set of classes, one probability indicating whether the input feature vector belongs to one class; extracting a feature vector from said image data; using the obtained classifier to estimate the probabilities for the extracted feature vector; and evaluating the estimated probabilities for determining whether the object does not belong to any one of the set of classes based using a quality indicator.

First claim

The invention claimed is:

1. A method for classifying an object in image data to one out of a set of classes using a classifier, said image data comprising an image of the object, the method comprising:
extracting a feature vector from said image data;
separating template image data into learning image data and into test image data, and extracting feature vectors from the learning image data and from the test image data;
obtaining a classifier based on the feature vectors extracted from the learning image data;
using the obtained classifier to estimate probabilities for the extracted feature vector to belong to each class of the set of classes;
evaluating the estimated probabilities for determining whether the object does not belong to any one of the set of classes, wherein it is determined that the object does not belong to any one of the set of classes if all estimated probabilities lie below a threshold probability,
wherein the threshold probability is obtained from testing the classifier with the feature vectors extracted from the test image data, including calculating diagonal entries of a corresponding confusion matrix, and selecting a smallest of the calculated diagonal entries as the threshold probability.

2. The method of claim 1 , wherein the classifier is generated using a support vector machine.

3. The method of claim 1 , further comprising adding a new class to the set of classes if it is determined that the object does not belong to any one of the set of classes.

4. The method of claim 1 , further comprising counting a classified object.

5. The method of claim 1 , further comprising authenticating a classified object.

6. A device for classifying an object in image data, to one of a set of classes using a classifier, said image data comprising an image of the object, the device comprising a processor coupled to a memory configured to:
obtain said image data;
extracting a feature vector from said image data;
separate template image data into learning image data and into test image data, and extract feature vectors from the learning image data and from the test image data;
obtain a classifier based on the feature vectors extracted from the learning image data;
use the obtained classifier to estimate probabilities for the extracted feature vector to belong to each class of the set of classes;
evaluate the estimated probabilities for determining whether the object does not belong to any one of the set of classes, wherein it is determined that the object does not belong to any one of the set of classes if all estimated probabilities lie below a threshold probability,
wherein the threshold probability is obtained from testing the classifier with the feature vectors extracted from the test image data, including calculating diagonal entries of a corresponding confusion matrix, and selecting a smallest of the calculated diagonal entries as the threshold probability.

7. The device of claim 6 , wherein said processor is configured to implement a method that includes generating the classifier via a support vector machine.

8. The device of claim 6 , wherein the device further comprises an image acquiring device for acquiring said image data.

9. A computer program stored on a non-transitory computer-readable medium, comprising code executable by a computer processor to perform the method of claim 1 .

10. A computer program product comprising a tangible and non-transitory data carrier storing in a non-volatile manner the computer program of claim 9 .

11. A system comprising:
a conveyor line arranged for moving objects through a field of view;
the device of claim 6 ; and
an image acquiring device arranged for acquiring said image data comprising an image of said field of view.

12. The system of claim 11 , wherein the conveyor line is any one of a conveyor belt, conveyor chain, guiding rail, sliding track, and transport track.

Assignees

• Sicpa Holding Sa

Inventors

• Heusch Guillaume
• Pican Nicolas

Classifications

• G06T7/0004 Primary

  Industrial image inspection · CPC title

• G06V10/765

  using rules for classification or partitioning the feature space · CPC title

• G06F18/28

  Determining representative reference patterns, e.g. by averaging or distorting; Generating dictionaries · CPC title

• G06F18/24765

  Rule-based classification · CPC title

• G06F18/2415

  based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate · CPC title