Morphological pattern recognition based controller system

Claim 3

The method according to claim 1, further comprising the steps of: generating a plurality of addressable domains from the image data, each of the domains representing a portion of the image information; subjecting a domain to one or more transforms selected from the group consisting of a null transformation, a predetermined rotation, an inversion, a predetermined scaling, and a predetermined frequency domain preprocessing; said selecting step comprising selecting, for each of the transformed domains, at least one of the mapped ranges which most closely corresponds according to predetermined criteria; and said matching step comprising selecting a template which most closely corresponds to the set of identifiers representing the image information.

Claim 4

The method according to claim 2 wherein the step of selecting the most closely corresponding one of the mapped ranges comprises the step of selecting, for each domain, the mapped range which is the most similar, by a method selected from at least one of the group consisting of selecting a minimum Hausdorff distance from the domain, selecting the highest cross-correlation with the domain and selecting the lowest mean square error of the difference between the mapped range and the domain.

Claim 5

The method according to claim 3 wherein the step of selecting the most closely corresponding one of mapped ranges includes the step of selecting, for each domain, the mapped range with the minimum modified Hausdorff distance calculated as D db,mrb!+D 1-db,1-mrb!, where D is a distance calculated between a pair of sets of data each representative of an image, db is a domain, mrb is a mapped range, 1-db is the inverse of a domain, and 1-mrb is an inverse of a mapped range.

Claim 6

The method according to claim 2, wherein the digital image data consists of a plurality of pixels each having one of a plurality of associated color map values, further comprising the steps of: optionally transforming the color map values of the pixels of each domain by a function including at least one scaling function for each axis of the color map, each of which may be the same or different, and selected to maximize the correspondence between the domains and ranges to which they are to be matched; selecting, for each of the domains, the one of the mapped ranges having color map pixel values which most closely correspond to the color map pixel values of the domain according to a predetermined criteria, wherein the step of representing the image color map information includes the substep of representing the image color map information as a set of values each including an identifier of the selected mapped range and the scaling functions; and selecting a most closely corresponding stored template, based on the identifier of the color map mapped range, the scaling functions and the set of identifiers representing the image information.

Claim 7

The method according to claim 2, further comprising the steps of: storing delayed image data, which represents an image of a moving object differing in time from the image data in the data processor; generating a plurality of addressable further domains from the stored delayed image data, each of the further domains representing a portion of the delayed image information, and corresponding to a domain; creating, from the stored delayed image data, a plurality of addressable mapped ranges corresponding to different subsets of the stored delayed image data; matching the further domain and the domain by subjecting a further domain to one or both of a corresponding transform selected from the group consisting of a null transform, a predetermined rotation, an inversion, a predetermined scaling, and a predetermined frequency domain preprocessing, which corresponds to a transform applied to a corresponding domain, and a noncorresponding transform selected from the group consisting of a predetermined rotation, an inversion, a predetermined scaling, a translation and a predetermined frequency domain preprocessing, which does not correspond to a transform applied to a corresponding domain; computing a motion vector between one of the domain and the further domain, or the set of identifiers representing the image information and the set of identifiers representing the delayed image information, and storing the motion vector; compensating the further domain with the motion vector and computing a difference between the compensated further domain and the domain; selecting, for each of the delayed domains, the one of the mapped ranges which most closely corresponds according to predetermined criteria; representing the(difference between the compensated further domain and the domain as a set of difference identifiers of a set of selected mapping ranges and an associated motion vector and representing the further domain as a set of identifiers of the selected mapping ranges; determining a complexity of the difference based on a density of representation; and when the difference has a complexity below a predetermined threshold, selecting, from the stored templates, a template which most closely corresponds to the set of identifiers of the image data and the set of identifiers of the delayed image data.

Claim 8

The method according to claim 1, wherein said representing step further comprises the steps of determining a feature of interest of the image data, selecting a mapped range corresponding to the feature of interest, storing the identifiers of the selected mapped range, selecting a further mapped range corresponding to a portion of image data having a predetermined relationship to the feature of interest and storing the identifiers of the further mapped range.

Claim 9

The method according to claim 1, wherein said image data comprises data having three associated dimensions obtained by a method selected from the group consisting of synthesizing a three dimensional representation based on a machine based prediction derived from two dimensional image data, synthesizing a three dimensional representation derived from a time series of pixel images, and synthesizing a three dimensional representation based on a image data representing a plurality of parallax views having at least two dimensions.

Claim 12

The method according to claim 9, wherein said processing step comprises modeling the extracted object in at least three independent dimensions.

Claim 13

The method according to claim 9, wherein said data relating to the plurality of image feature types comprise models each having at least three dimensions, said comparing step comprising projecting said exemplar into two dimensions.

Claim 14

The method according to claim 9, further comprising the steps of: inputting a search criteria relating to image morphology; comparing the attributes of the object to the search criteria; and selectively processing the representation of the image based on said comparison of the attributes of the object with the stored data relating to a plurality of image feature types and said comparison of the attributes of the object to the search criteria.

Claim 15

The method according to claim 12, further comprising the steps of: receiving a user input; predicting a most probable user intent based on said input; presenting to the user with a predicted instruction based on said predicted most probable user intent; and receiving feedback from the user to determine an agreement with said predicted instruction.

Claim 16

The method according to claim 13, wherein said predicting step is adaptive.

Claim 17

The method according to claim 12, wherein said search criteria is input as an image pattern.

Claim 18

The method according to claim 12, wherein said search criteria is an identifier of an object or an image.

Claim 19

The method according to claim 9, wherein said processing step further comprises deriving a mathematical expression relating to a self-similarity of at least a portion of the image of the object.

Claim 20

The method according to claim 9, further comprising the step of selectively storing a temporal sequence of images.

Claim 21

The method according to claim 9, further comprising the step of selectively processing a scene including the image from a stored sequence if images.

Claim 22

The method according to claim 9, wherein the representation of the image comprises a video signal, the morphological feature comprising a three-dimensional shape, further comprising the step of outputting the identified relation, and selectively processing the video signal based on the outputted identified relation.

Claim 23

The method according to claim 9, wherein the plurality of image feature types comprise human anatomical characteristics.

Claim 24

The method according to claim 9, wherein said processing the representation of the image to reduce a data storage requirement step comprises representing mathematical relationships of self-similar portions of the image.

Claim 27

The apparatus according to claim 23, wherein said means for processing comprises means for determining motion planes from a sequence of representations of the image.

Claim 28

The apparatus according to claim 23, wherein said received representation of an image comprises a video signal, further comprising means for selectively recording the video signal based on said identified relation.

Claim 29

The apparatus according to claim 23, wherein the plurality of image feature types comprise human anatomical characteristics.

Claim 30

The apparatus according to claim 23, wherein said means for processing the representation of the image to reduce a data storage requirement determines mathematical relationships of self-similar portions of the image.

Claim 31

The apparatus according to claim 23, further comprising an input for receiving a selected image feature type, and means for selectively processing the image based on the identified relation between the representation of the image and the input image feature type.

Claim 32

The apparatus according to claim 23, wherein the representation of the image is a motion-vector compressed digital video image stream, said means for processing modeling said significant object as a three dimensional construct, based on said motion-vector compressed digital video image stream.