초록 ▼

An image-based pattern recognizer and a method and apparatus for making such a pattern recognizer are disclosed. By employing positional coding, the meaning of any feature present in an image can be defined implicitly in space. The pattern recognizer can be a neural network including a plurality of

An image-based pattern recognizer and a method and apparatus for making such a pattern recognizer are disclosed. By employing positional coding, the meaning of any feature present in an image can be defined implicitly in space. The pattern recognizer can be a neural network including a plurality of stages of observers. The observers are configured to cooperate to identify the presence of features in the input image and to recognize a pattern in the input image based on the features. Each of the observers includes a plurality of neurons. The input image includes a plurality of units, and each of the observers is configured to generate a separate output set that includes zero or more coordinates of such units.

대표청구항 ▼

1. An apparatus comprising: a processor;a plurality of converters, functionally coupled to the processor, each converter to input an input image and to compute a potential as a measure of contrast in the input image for each of a plurality of units of the input image, each converter further to gener

1. An apparatus comprising: a processor;a plurality of converters, functionally coupled to the processor, each converter to input an input image and to compute a potential as a measure of contrast in the input image for each of a plurality of units of the input image, each converter further to generate an output set including a ranked set of coordinates, the ranked set of coordinates containing a coordinate of each unit in the input image whose potential exceeds a first threshold, the set of coordinates being ranked based on potential; anda first plurality of observers, each observer to process independently the output set of each of the converters, each of the observers configured to recognize a different type of feature in the input image when a coordinate of a feature of the corresponding type is present in the output set of one or more of the converters, wherein each observer of the first plurality of observers is configured to, for each coordinate in the output of each of the converters, integrate a corresponding potential over a range of time slices, andfor each said unit whose potential exceeds a second threshold after integration by the observer, including the coordinate of the unit in an output set of the observer. 2. An apparatus as recited in claim 1, further comprising a first plurality of pattern filters, each including a plurality of weight matrices, wherein each of the first plurality of observers is configured to use a different one of the pattern filters to recognize the corresponding type of feature in the input image. 3. An apparatus as recited in claim 2, wherein the first plurality of pattern filters are individually configured so that each observer of the first plurality of observers can recognize features at a different angular orientation in the input image. 4. An apparatus as recited in claim 1, further comprising: a second plurality of observers, each to process independently the output set of each of the first plurality of observers, each observer of the second plurality of observers configured to generate an output representing a relaxation of locality of a feature recognized in the input image. 5. An apparatus as recited in claim 4, each observer of the second plurality of observers further being configured to generate the output to represent a prioritizing of endpoints of feature recognized in the input image more highly than a mid-section of the feature. 6. An apparatus comprising: a processor; anda memory storing code which, when executed by the processor, instantiates a plurality of converters, each to input an input image and to compute a potential as a measure of contrast in the input image for each of a plurality of units of the input image, each converter further to generate as output a ranked set of coordinates containing a coordinate of each unit in the input image whose potential exceeds a first threshold, the set of coordinates being ranked based on potential;a first plurality of observers to process the outputs of the converters to recognize features in the input image that correspond to coordinates in the outputs of the converters, wherein each observer of the first plurality of observers is configured to, for each coordinate in the output of each of the converters, integrate a corresponding potential over a range of time slices, andfor each said unit whose potential exceeds a second threshold after integration by the observer, including the coordinate of the unit in an output set of the observer; anda first plurality of pattern filters, each operatively coupled between a different pair of a converter of the plurality of converters and an observer of the first plurality of observers, the first plurality of pattern filters being individually configured so that each observer of the first plurality of observers can recognize features at a different angular orientation in the input image. 7. An apparatus as recited in claim 6, wherein the memory further stores code which, when executed by the processor, instantiates: a second plurality of observers to process outputs of the first plurality of observers; anda second plurality of pattern filters, each operatively coupled between a different pair of an observer of the first plurality of observers and an observer of the second plurality of observers, the second plurality of pattern filters being individually configured so that each observer of the second plurality of observers generates an output representing a relaxation of locality of a feature recognized in the input image. 8. An apparatus as recited in claim 7, wherein the second plurality of pattern filters further are individually configured so that each observer of the second plurality of observers generates an output representing prioritizing endpoints of feature recognized in the input image more highly than a mid-section of the feature. 9. An apparatus as recited in claim 7, wherein each observer of the first plurality of observers is configured to for each coordinate in the output of each of the first plurality of observers, integrate a corresponding potential over a range of time slices, andfor each said unit whose potential exceeds a second threshold after integration by the observer, including the coordinate of the unit in an output set of the observer;and wherein each observer of the second plurality of observers is configured to, for each coordinate in the output of each of the first plurality of observers, integrate a corresponding potential over a range of time slices, andfor each said unit whose potential exceeds a third threshold after integration by the observer, including the coordinate of the unit in an output set of the observer. 10. A method comprising: using, by a processor in a physical machine, a plurality of contrast converters to identify a plurality of units of an input image as potentially representing a feature in the input image;using, by the processor, the plurality of contrast converters to generate a first output set of each of the contrast converters, wherein each said first output set contains a ranking of coordinates of the identified units of the input image, the ranking being based on potential, each said first output set containing a coordinate of each unit in the input image whose potential exceeds a first threshold;using, by the processor, a plurality of observers to attempt to recognize, in the input image, a feature from each of a first plurality of feature categories, based on the first output sets, by for each coordinate in each said first output set, integrating a corresponding potential over a range of time slices, andfor each said unit whose potential exceeds a second threshold after integration by the observer, including the coordinate of the unit in an output set of the observer; andusing, by the processor, the plurality of observers to generate a plurality of second output sets as results of attempting to recognize a feature from each of the first plurality of feature categories, each said second output set corresponding to a different one of the first plurality of feature categories. 11. A method as recited in claim 10, further comprising: automatically triggering a specified action in response to recognizing a pattern in the input image, based on the plurality of second output sets. 12. A method as recited in claim 10, wherein identifying a plurality of units of an input image as potentially representing a feature comprises, for each of the plurality of units: computing a measure of contrast for the unit; andidentifying the unit as potentially representing a feature based on the measure of contrast. 13. A method as recited in claim 12, wherein computing a measure of contrast for a unit comprises: computing a measure of positive contrast; andcomputing a measure of negative contrast. 14. A method as recited in claim 12, wherein the ranking of coordinates in the first output set is based on the measures of contrast of the corresponding units of the input image. 15. A method as recited in claim 10, wherein each of the first plurality of weight patterns corresponds to a different angular orientation in the input image. 16. A method as recited in claim 10, wherein using each of the first plurality of weight patterns to integrate a potential for each of the identified units comprises: applying a modulation factor to a weight, for each of a plurality of iterations of integration, to decode said ranking. 17. A method as recited in claim 10, further comprising: attempting to recognize, in the input image, a feature from a second feature category, based on one of the second output sets, by using a second weight pattern to integrate a potential for each unit whose coordinate is represented in said second output set, based on a ranking of coordinates in said second output set, and generating a third output set based thereon. 18. A method as recited in claim 17, further comprising: automatically triggering a specified action in response to recognizing a pattern represented by the third output set. 19. A method as recited in claim 18, further comprising: attempting to recognize, in the input image, a feature from each of a second plurality of feature categories, based on the second output set, by independently using a second plurality of weight patterns to integrate a potential for each unit whose coordinate is represented in the second output set, based on a ranking of coordinates in the second output set; andgenerating a plurality of third output sets, each said third output set corresponding to a different one of the second plurality of feature categories. 20. A method as recited in claim 10, wherein using the plurality of observers to attempt to recognize a feature from each of a first plurality of feature categories comprises independently using each of a first plurality of weight patterns to integrate a potential for each of the identified units, based on the rankings of coordinates in the first output sets.