Method of processing images in order automatically to detect key points situated on the contour of an object and device for implementing this method
First Claim
1. Method of processing images in order automatically to detect points situated on the contour of an object (LV) at predetermined structure, referred to as key pixels (K2, K3, K4), in an image referred to as the initial image (I0), this method comprising a first phase including steps of:
- storage in the initial image (I0) in the form of a two-dimensional matrix of pixels of the intensity values of each pixel (A0) labelled by its coordinates (x,y);
storage in the initial image (I0) of data of regions of the object (LV) which are referred to as classes (C1 to Cm) including classes which are referred to as corresponding classes (C2, C3, C4) respectively containing the key pixels (K2, K3, K4) to be detected;
selection of pixels of the initial image (I0) which are referred to as pixels of interest (PI), on the contour of and inside and outside the object (LV);
generation of a first vector of characteristics (E1 to Ek) for each of the pixels of interest (PI); and
classification of the pixels of interest (PI) into the said classes (C1 to Cm) of the object (LV) on the basis of their respective vector of characteristics (E1 to Ek).
1 Assignment
0 Petitions
Accused Products
Abstract
A method of processing images in order automatically to detect key pixels (K2, K3, K4) situated on the contour of an object (LV) in an initial image (I0), and a device for implementing this method in which there is storage, in the digitized initial image (I0), of the intensity of the pixels [A0 (x,y)] and of data of regions of the object (LV), classes (C1 Cm); selection of pixels of interest (PI), on the contour, inside and outside the object (LV); generation of characteristics (E1 Ek) for each of the pixels of interest (PI); classification of the pixels of interest (PI) into the classes (C1 Cm); and selection of the key pixels (K2, K3, K4) from corresponding classes (C2, C3, C4).
50 Citations
22 Claims
-
1. Method of processing images in order automatically to detect points situated on the contour of an object (LV) at predetermined structure, referred to as key pixels (K2, K3, K4), in an image referred to as the initial image (I0), this method comprising a first phase including steps of:
-
storage in the initial image (I0) in the form of a two-dimensional matrix of pixels of the intensity values of each pixel (A0) labelled by its coordinates (x,y); storage in the initial image (I0) of data of regions of the object (LV) which are referred to as classes (C1 to Cm) including classes which are referred to as corresponding classes (C2, C3, C4) respectively containing the key pixels (K2, K3, K4) to be detected; selection of pixels of the initial image (I0) which are referred to as pixels of interest (PI), on the contour of and inside and outside the object (LV); generation of a first vector of characteristics (E1 to Ek) for each of the pixels of interest (PI); and classification of the pixels of interest (PI) into the said classes (C1 to Cm) of the object (LV) on the basis of their respective vector of characteristics (E1 to Ek).
-
-
2. Method of processing images in order automatically to detect points situated on the contour of an object (LV), referred to as key pixels (K2, K3, K4), in an image referred to as the initial image (I0), this method comprising a first phase including steps of:
-
storage in the initial image (I0) in the form of a two-dimensional matrix of matrix of pixels of the intensity values of each pixel (A0) labelled by its coordinates (x, y); storage in the initial image (I0) of data of regions of the object (LV) which referred to as classes (C1 to Cm) including classes which are referred to as corresponding classes (C2, C3, C4) respectively containing the key pixels (K2, K3, K4) to be detected; selection of pixels of the initial image (I0) which are referred to as pixels of interest (PI), on the contour of and inside and outside the object (LV); generation of a first vector of characteristics (E1 to Ek) for each of the pixels of interest (PI); and classification of the pixels of interest (PI) into the said classes (C1 to Cm) of the object (LV) on the basis of their respective vector of characteristics (E1 to Ek); wherein the step of selection of the pixels of interest (PI), sub-steps of; filtering of the initial image (I0) in order to select pixels having a gradient of maximum intensity which are situated on the contour of the object (LV); and sampling of the initial image (I0) at a lower frequency, preferentially preserving the pixels having a gradient of maximum intensity. - View Dependent Claims (3, 4, 5, 6, 7)
-
-
8. Method of processing images in order automatically to detect points situated on the contour of an object (LV), referred to as key pixels (K2, K3, K4), in an image referred to as the initial image (I0), this method comprising a first phase including steps of:
-
storage in the initial image (I0) in the form of a two-dimensional matrix of pixels of the intensity values of each pixel (A0) labelled by its coordinates (x, y); storage in the initial image (I0) of data of regions of the object (LV) which are referred to as classes (C1 to Cm) including classes which are referred to as corresponding classes (C2, C3, C4) respectively containing;
the key pixels (K2, K3, K4) to be detected;selection of pixels of the initial image (I0) which are referred to as pixels of interest (PI), on the contour of and inside and outside the object (LV); generation of a first vector of characteristics (E1 to Ek) for each of the pixels of interest (PI); and classification of the pixels of interest (PI) into the said classes (C1 to Cm) of the object (LV) on the basis of their respective vector of characteristics (E1 to Ek); and furthermore comprising a second phase including a step of selection of each of the key pixels (K2, K3, K4) from the pixels of interest (PI) of the corresponding class (C2, C3, C4). - View Dependent Claims (9, 10, 11)
-
-
12. Device for processing images in order automatically to detect points situated on the contour of an object (LV), referred to as key pixels (K2, K3, K4) in an image referred to as the initial image (I0), this device comprising:
-
first storage means (MEM1) for storing, in the initial image (I0) in the form of a two-dimensional matrix of pixels, the intensity values of each pixel (A0) labelled by its coordinates (x, y), and data of regions of the object (LV), which are referred to as classes (C1 to Cm), including classes referred to as corresponding classes (C2, C3, C4) respectively containing the key pixels (K2, K3, K4) to be detected; means of selection of pixels of the initial image (I0), referred to as pixels of interest (PI), on the contour of and inside and outside the object (LV); first means of calculation (CP1), for generating a first vector of characteristics (E1 to Ek) for each of the pixels of interest (PI); a first neural network (NN1) for receiving at its inputs the first vector of characteristics and for performing a classification of the pixels of interest (PI) into said classes (C1 to CM) of the object (LV) on the basis of their respective vector of characteristics (E1 to Ek). - View Dependent Claims (13, 14, 15, 16, 17, 18, 19, 20, 21, 22)
-
Specification