Method for recognizing object images and learning method for neural networks
First Claim
1. A method for recognizing an object image, which comprises the steps of:
- i) extracting a candidate for a predetermined object image from an overall image, andii) making a judgment as to whether the extracted candidate for the predetermined object image is or is not the predetermined object image,wherein said extracting step comprises;
a) causing the center point of a view window, which has a predetermined size, physically to travel on said overall image to the position of said candidate for the predetermined object image, such that the portion of the overall image within the view window varies, said causing step comprising the steps of;
composing a first travel vector relating to a detected contour line of said candidate;
composing a second travel vector related to an object image exhibiting a movement different from background movement of the overall image;
composing a third travel vector related to a region which approximately coincides in color with said candidate; and
composing a composite travel vector from said first, second and third travel vectors, said composite travel vector being used to cause the center point of the view window to travel over the overall image to the position of said candidate; and
b) determining an extraction area in accordance with predetermined characteristics of said candidate for the predetermined object image while using the center point of said view window as a reference.
2 Assignments
0 Petitions
Accused Products
Abstract
A method for recognizing an object image comprises the steps of extracting a candidate for mineda predetermined object image from an overall image, and making a judgment as to whether the extracted candidate for the predetermined object image is or is not the predetermined object image. The candidate for the predetermined object image is extracted by causing the center point of a view window, which has a predetermined size, to travel to the position of the candidate for the predetermined object image, and determining an extraction area in accordance with the size and/or the shape of the candidate for the predetermined object image, the center point of the view window being taken as a reference during the determination of the extraction area. A learning method for a neural network comprises the steps of extracting a target object image, for which learning operations are to be carried out, from an image, feeding a signal, which represents the extracted target object image, into a neural network, and carrying out the learning operations of the neural network in accordance with the input target object image.
104 Citations
45 Claims
-
1. A method for recognizing an object image, which comprises the steps of:
-
i) extracting a candidate for a predetermined object image from an overall image, and ii) making a judgment as to whether the extracted candidate for the predetermined object image is or is not the predetermined object image, wherein said extracting step comprises; a) causing the center point of a view window, which has a predetermined size, physically to travel on said overall image to the position of said candidate for the predetermined object image, such that the portion of the overall image within the view window varies, said causing step comprising the steps of;
composing a first travel vector relating to a detected contour line of said candidate;
composing a second travel vector related to an object image exhibiting a movement different from background movement of the overall image;
composing a third travel vector related to a region which approximately coincides in color with said candidate; and
composing a composite travel vector from said first, second and third travel vectors, said composite travel vector being used to cause the center point of the view window to travel over the overall image to the position of said candidate; andb) determining an extraction area in accordance with predetermined characteristics of said candidate for the predetermined object image while using the center point of said view window as a reference. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 42, 43)
-
-
15. A method for recognizing an object image, which comprises the steps of:
-
i) extracting a candidate for a predetermined object image from an overall image, and ii) making a judgment as to whether the extracted candidate for the predetermined object image is or is not the predetermined object image, said extraction step comprising; a) setting a view window, which has a predetermined size, on said overall image, said overall image being an image including a movement, cutting out a plurality of cut-out images, which fall in a region inside of said view window, at a plurality of times having a predetermined time difference therebetween, and detecting a contour line of said candidate for the predetermined object image, which line extends in a predetermined direction, from one of the plurality of said cut-out images, b) extracting all components of said detected contour line, which are tilted at a predetermined angle with respect to circumferential directions of concentric circles surrounding the center point of said view window, from said detected contour line of said candidate for the predetermined object image, c) detecting azimuths and intensities of said extracted components with respect to the center point of said view window, the azimuths and the intensities being detected as first azimuth vectors, d) composing, from said first azimuth vectors, a first travel vector, e) detecting contour lines of object images, which are embedded in the plurality of said cut-out images, calculating the difference between contour lines of said cut-out images, and detecting a movement of said overall image in an in-plane parallel direction in the region inside of said view window, the movement being detected from said calculated difference, f) detecting contour lines of object images, which are embedded in the plurality of said cut-out images, said contour lines extending in a radial direction with respect to the center point of said view window, calculating the difference between radial contour lines of said cut-out images, and detecting a movement of said overall image in an in-plane rotating direction in the region inside of said view window, the movement being detected from said calculated difference, g) detecting contour lines of said object images, which are embedded in the plurality of said cut-out images, said contour lines extending in an annular direction, calculating the difference between annular contour lines of said cut-out images, and detecting a movement of said overall image in the radial direction in the region inside of said view window, the movement being detected from said calculated difference, h) compensating for components of a movement of a background in said cut-out images, which fall in the region inside of said view window, in accordance with said detected movement of said overall image in the in-plane parallel direction, in the in-plane rotating direction, and in the radial direction, a plurality of compensated images, in which the components of the movement of the background have been compensated for, being thereby obtained, i) calculating the difference between the plurality of said compensated images, a contour line of an object, which shows a movement different from the movement of the background, being thereby detected, j) extracting all of components of said detected contour line of said object showing a movement different from the movement of the background, which are tilted at a predetermined angle with respect to circumferential directions of concentric circles surrounding the center point of said view window, from said detected contour line of said object showing a movement different from the movement of the background, k) detecting azimuths and intensities of said extracted components of said detected contour line of said object, which shows the movement different from the movement of the background, with respect to the center point of said view window, the azimuths and the intensities being detected as second azimuth vectors, l) composing, from said second azimuth vectors, a second travel vector, m) extracting a region, which approximately coincides in color with said candidate for the predetermined object image, from one of the plurality of said cut-out images, n) detecting an azimuth and a distance of said extracted region with respect to the center point of said view window, o) detecting said azimuth and said distance as a third travel vector, p) composing, from said first, second, and third travel vectors, a composite travel vector for said view window, q) causing the center point of said view window to travel on said overall image in accordance with said composite travel vector for said view window, and r) determining an extraction area in accordance with predetermined characteristics of said candidate for the predetermined object image while using the center point of said view window as a reference. - View Dependent Claims (16, 17)
-
-
18. A method for recognizing an object image, which comprises the steps of:
-
i) extracting a candidate for a predetermined object image from an overall image, and ii) making a judgment as to whether the extracted candidate for the predetermined object image is or is not the predetermined object image, said extraction step comprising; a) cutting out a first image, which falls in a region inside of a view window having a predetermined size, from said overall image, b) detecting a contour line of an object, which is embedded in said cut-out first image, c) after a predetermined time has elapsed, cutting out a second image, which falls in the region inside of said view window, from said overall image, d) detecting a contour line of an object, which is embedded in said cut-out second image, e) calculating the difference between said contour line, which has been detected from said first image, and said contour line, which has been detected from said second image, f) detecting a movement of a background from said calculated difference, g) subtracting said detected movement of said background from one of said cut-out first and second images, an object, which shows a movement different from the movement of said background, being thereby detected, h) recognizing said object, which shows a movement different from the movement of said background, as said candidate for the predetermined object image, i) detecting a vector directed towards said candidate for the predetermined object image as a first travel vector, j) detecting a contour line of said candidate for the predetermined object image, which line extends in a predetermined direction, from said cut-out first image, k) extracting all components of said detected contour line, which are tilted at a predetermined angle with respect to circumferential directions of concentric circles surrounding the center point of said view window, from said detected contour line of said candidate for the predetermined object image, l) detecting azimuths and intensities of said extracted components with respect to the center point of said view window, the azimuths and the intensities being detected as second azimuth vectors, m) composing, from said second azimuth vectors, a second travel vector, n) extracting a region, which approximately coincides in color with said candidate for the predetermined object image, from said cut-out first image, o) detecting an azimuth and a distance of said extracted region with respect to the center point of said view window, p) detecting said azimuth and said distance as a third travel vector, q) composing, from said first, second, and third travel vectors, a composite travel vector of said view window, r) causing the center point of said view window to travel on said overall image in accordance with said composite travel vector for said view window, and s) determining an extraction area in accordance with predetermined characteristics of said candidate for the predetermined object image while using the center point of said view window as a reference. - View Dependent Claims (19, 20)
-
-
21. A method for recognizing an object image, which comprises the steps of:
-
i) extracting a candidate for a predetermined object image from an overall image, and ii) making a judgment as to whether the extracted candidate for the predetermined object image is or is not the predetermined object image, wherein said extraction step comprises; a) creating a map of a potential field of the whole area of said overall image, and b) determining an extraction area in accordance with predetermined characteristics of said candidate for the predetermined object image while using a minimum point of the potential in said map as a reference. - View Dependent Claims (22, 23, 24, 25, 26, 27, 28, 29, 30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40)
-
-
41. A method for recognizing an object image, which comprises the steps of:
-
i) extracting a candidate for a predetermined object image from an overall image, and ii) making a judgment as to whether the extracted candidate for the predetermined object image is or is not the predetermined object image, said extraction step comprising; a) cutting out a first image, which falls in a region inside of a view window having a predetermined size, from said overall image, b) detecting a contour line of an object, which is embedded in said cut-out first image, c) after a predetermined time has elapsed, cutting out a second image, which falls in the region inside of said view window, from said overall image, d) detecting a contour line of an object, which is embedded in said cut-out second image, e) calculating the difference between said contour line, which has been detected from said first image, and said contour line, which has been detected from said second image, f) detecting a movement of a background from said calculated difference, g) subtracting said detected movement of said background from one of said cut-out first and second images, an object, which shows a movement different from the movement of said background, being thereby detected, h) recognizing said object, which shows a movement different from the movement of said background, as said candidate for the predetermined object image, i) detecting a vector directed towards said candidate for the predetermined object image as a first travel vector, j) detecting a contour line of said candidate for the predetermined object image, which line extends in a predetermined direction, from said cut-out first image, k) extracting all components of said detected contour line, which are tilted at a predetermined angle with respect to circumferential directions of concentric circles surrounding the center point of said view window, from said detected contour line of said candidate for the predetermined object image, l) detecting azimuths and intensities of said extracted components with respect to the center point of said view window, the azimuths and the intensities being detected as second azimuth vectors, m) composing, from said second azimuth vectors, a second travel vector, n) extracting a region, which approximately coincides in color with said candidate for the predetermined object image, from said cut-out first image, o) detecting an azimuth and a distance of said extracted region with respect to the center point of said view window, p) detecting said azimuth and said distance as a third travel vector, q) composing a composite travel vector from said first, second, and third travel vectors, the composite travel vector being taken as a gradient vector of a potential field in a Cartesian plane having its origin at the center point of said view window, r) scanning the whole area of said overall image with said view window, thereby calculating the gradient vectors of the potential field with respect to the whole area of said overall image, s) creating a map of the potential field of the whole area of said overall image from the gradient vectors of the potential field, which have been calculated with respect to the whole area of said overall image, and t) determining an extraction area in accordance with predetermined characteristics of said candidate for the predetermined object image while using a minimum point of the potential in said map as a reference. - View Dependent Claims (44, 45)
-
Specification