Methods and apparatus to perform image classification based on pseudorandom features
View Patent ↗Example methods and apparatus to perform image classification based on pseudorandom features are disclosed. A disclosed example method includes generating first and second pseudorandom numbers, extracting a first feature of an image based on the first and second pseudorandom numbers, and determining a classification for the image based on the first extracted feature.
1. A method comprising:
generating first and second pseudorandom numbers;
extracting a first feature of an image based on the first and second pseudorandom numbers; and
determining a classification for the image based on the extracted first feature, wherein extracting the first feature of the image comprises:
identifying a location of a region of the image based on the first and second pseudorandom numbers; and
computing an average of pixels of the identified region.
2. A method as defined in claim 1 , wherein generating the first pseudorandom number comprises selecting the first pseudorandom numbers from a sequence of numbers approximating a random number property.
3. A method as defined in claim 1 , wherein extracting the first feature of the image further comprises:
computing at least one of an edge strength, an edge direction, or a color at the identified location.
4. A method as defined in claim 1 , wherein the first feature is extracted from the identified region.
5. A method as defined in claim 1 , further comprising deterministically extracting a second feature of the image, wherein determining the classification is based on the first and second features.
6. A method as defined in claim 5 , wherein the second, feature is at least one of a brightness, a color, a position, a feature size, an edge strength, or an edge direction.
7. A method as defined in claim 1 , wherein determining the classification for the image comprises:
providing the first extracted feature into a support vector machine; and
receiving the classification from the support vector machine.
8. A method as defined in claim 1 , further comprising:
receiving a second image and a second classification for the second image;
extracting a second feature of the second image based on the first and second pseudorandom numbers; and
training an image classifier based on the second feature and the second classification.
9. A method as defined in claim 1 , wherein generating the first pseudorandom number approximates a property of a random number.
10. A method as defined in claim 1 , wherein extracting the first feature of the image comprises:
generating third and fourth pseudorandom numbers; and
identifying the location of the region of the image based on the first, second, third and fourth pseudorandom numbers.
11. A method as defined in claim 1 , wherein extracting the first feature of the image comprises identifying an extent of the region.
12. A method as defined in claim 1 , wherein the region comprises a facial portion of the image.
13. A method as defined in claim 1 further comprising:
extracting a second feature of the image based on the first and second pseudorandom numbers; and
determining the classification of the image based on the first and second extracted features.
14. A method as defined in claim 1 further comprising setting a pseudorandom number generation state.
15. A method as defined in claim 1 , wherein the image comprises a representation of a person and the classification comprises a gender of the person.
16. An apparatus comprising:
a pseudorandom number generator to generate one or more pseudorandom numbers;
a feature extractor to extract a first feature of an image based on the one or more pseudorandom numbers by identifying a region of the image based on the one or more pseudorandom numbers and computing an average of pixels of the identified region; and
a classifier to determine a classification for the image based on the first extracted feature.
17. An apparatus as defined in claim 16 , wherein the number generator is to generate one or more additional pseudorandom numbers, and wherein the feature extractor is to identify the region of the image based on the one or more pseudorandom numbers and the one or more additional pseudorandom numbers.
18. An apparatus as defined in claim 16 , wherein the first feature comprises at least one of an edge strength, an edge direction, or a color at the identified location.
19. An apparatus as defined in claim 16 , further comprising a second feature extractor to deterministically extract a second feature of the image, wherein the classifier is to determine the classification based on the first and second features.
20. An apparatus as defined in claim 19 , wherein the second feature is at least one of a brightness, a color, a position, a feature size, an edge strength, or an edge direction.
21. An apparatus as defined in claim 16 , wherein the classifier comprises a support vector machine.
22. An apparatus as defined in claim 16 , wherein the pseudorandom number generator comprises at least one of a linear congruential generator, a lagged Fibonacci generator, a linear feedback shift register, or a generalized feedback shift register.
23. A tangible computer readable storage comprising machine-readable instructions which, when executed, cause a machine to at least:
generate one or more pseudorandom numbers;
extract a first feature of an image by identifying a region of the image based on the one or more pseudorandom numbers and computing an average of pixels of the identified region; and
determine a classification for the image based on the first extracted feature.
24. A tangible computer readable storage as defined in claim 23 , wherein the instructions further cause the machine to:
generate additional pseudorandom numbers; and
identify the region of the image based on the one or more pseudorandom numbers and the additional pseudorandom numbers.
25. A tangible computer readable storage as defined in claim 23 , wherein the instructions further cause the machine to:
receive a second image and a second classification for the second image;
extract a second feature of the second image based on the one or more pseudorandom numbers; and
train an image classifier based, on the second feature and the second, classification.
26. A tangible computer readable storage as defined in claim 23 , wherein the first feature of the image comprises at least one of an edge strength, an edge direction, or a color at the identified location.