IPC분류정보
국가/구분 |
United States(US) Patent
등록
|
국제특허분류(IPC7판) |
|
출원번호 |
UP-0312937
(2005-12-20)
|
등록번호 |
US-7835577
(2011-01-16)
|
발명자
/ 주소 |
|
출원인 / 주소 |
|
인용정보 |
피인용 횟수 :
4 인용 특허 :
8 |
초록
▼
A system and method for multi-label image segmentation is provided. The method comprises the steps of: receiving image data including a set of labeled image elements; mapping a change in image data to edge weights; determining potentials for each image element in the image data; and assigning a labe
A system and method for multi-label image segmentation is provided. The method comprises the steps of: receiving image data including a set of labeled image elements; mapping a change in image data to edge weights; determining potentials for each image element in the image data; and assigning a label, based upon the determined potentials, to each image element in the image data.
대표청구항
▼
What is claimed is: 1. A method for multi-label image segmentation, comprising: receiving image data including a set of labeled image elements; mapping a change in color space of the image data to edge weights, wherein said change in color space is mapped using the function: wij=exp(−β
What is claimed is: 1. A method for multi-label image segmentation, comprising: receiving image data including a set of labeled image elements; mapping a change in color space of the image data to edge weights, wherein said change in color space is mapped using the function: wij=exp(−β∥Ci−Cj∥) where Ci represents a vector of color values at image element i, represents a vector of color values at image element j, ∥•∥ indicates vector norm, and β is a free parameter; determining by a processor potentials for each image element in the image data, wherein the determined potentials represent the probability that a random walker starting at an image element in the image data first reaches a seed point in the image data when the probability of the seed point is set to unity; and assigning a label, based upon the determined potentials, to each image element in the image data. 2. The method of claim 1 wherein said image data is a digital photograph. 3. The method of claim 1, wherein the image data is marked by a user. 4. The method of claim 1, wherein the image elements are pixels. 5. The method of claim 1, wherein the image elements are voxels of a video sequence. 6. The method of claim 1, wherein the image data includes unlabeled image elements. 7. The method of claim 1, wherein said color space is correlated with human visual perception. 8. The method of claim 7 wherein said color space is CIE LUV color space. 9. The method of claim 1, wherein the change in color space of the image data to edge weights is mapped to represent the image data with random walker biases. 10. The method of claim 1, wherein the potentials for each image element in the image data are determined by LUX=−BM, where LU is a reduced Laplacian matrix, X is a set of probabilities for each image element in the image data, B is a joining block between labeled and unlabeled image elements in a Laplacian matrix and M is a set of indicator values for indicating values of the labeled image elements. 11. The method of claim 1, wherein the label assigned to each image element corresponds to maxs(xis), where maxs is to maximize over variable s which takes value from a set of labels and xir is the potential at an image element i corresponding to a label s. 12. The method of claim 1, further comprising: outputting the assigned label. 13. The method of claim 1, further comprising: acquiring the image data. 14. A system for multi-label image segmentation, comprising: a memory device for storing a program; a processor in communication with the memory device, the processor operated with the program to: receive image data including a set of labeled image elements; map a change in color space of the image data to edge weights, wherein said change in color space is mapped using the function: wijexp(−β∥CiCj∥) where Ci represents a vector of color values at image element i, Cj represents a vector of color values at image element j, ∥•∥ indicates vector norm, and β is a free parameter; determine potentials for each image element in the image data, wherein the determined potentials represent the probability that a random walker starting at an image element in the image data first reaches a seed point in the image data when the probability of the seed point is set to unity; and assign a label, based upon the determined potentials, to each image element in the image data. 15. The system of claim 14 wherein said image data is a digital photograph. 16. The system of claim 14, wherein the image data is marked by a user. 17. The system of claim 14, wherein the image elements are pixels. 18. The system of claim 14, wherein the image elements are voxels of a video sequence. 19. The system of claim 14, wherein the image data includes unlabeled image elements. 20. The system of claim 14, wherein said color space is correlated with human visual perception. 21. The system of claim 20 wherein said color space is CIE LUV color space. 22. The system of claim 14 wherein the change in color space of the image data to edge weights is mapped to represent the image with random walker biases. 23. The system of claim 22, wherein the random walker is biased to avoid crossing object boundaries. 24. The system of claim 14, wherein the potentials for each image element in the image data are determined by LUX=−BM, where LU is a reduced Laplacian matrix, X is a set of probabilities for each image element in the image data, B is a joining block between labeled and unlabeled image elements in a Laplacian matrix and M is a set of indicator values for indicating values of the labeled image elements. 25. The system of claim 14, wherein the label assigned to each image element corresponds to maxs(xis), where maxs is to maximize over variable s which takes value from a set of labels and xis is the potential at an image element i corresponding to a label s. 26. The system of claim 14, wherein the processor is further operative with the program code to: output the assigned label. 27. The system of claim 14, wherein the processor is further operative with the program code to: acquire the image data via a digital camera. 28. A computer readable medium having computer program logic recorded thereon for multi-label image segmentation, the computer program logic comprising: program code for receiving image data including a set of labeled image elements; program code for mapping a change in color space of the image data to edge weights, wherein said change in color space is mapped using the function: wij=exp(−β∥Ci−Cj∥) where Ci represents a vector of color values at image element i, Cj represents a vector of color values at image element j, ∥•∥ indicates vector norm, and β is a free parameter; program code for determining potentials for each image element in the image data, wherein the determined potentials represent the probability that a random walker starting at an image element in the image data first reaches a seed point in the image data when the probability of the seed point is set to unity; and program code for assigning a label, based upon the determined potentials, to each image element in the image data. 29. The computer readable medium of claim 28 wherein said image data represents a digital photograph. 30. The computer readable medium of claim 28 wherein said color space is correlated with human visual perception. 31. The computer readable medium of claim 30 wherein said color space is CIE LUV color space. 32. A system for multi-label image segmentation, comprising: means for receiving image data including a set of labeled image elements; means for mapping a change in color space of the image data to edge weights, wherein said change in color space is mapped using the function: wij=exp(−β∥Ci−Cj∥) where Ci represents a vector of color values at mage element i, Cj represents a vector of color values at image element j, ∥•∥ indicates vector norm, and β is a free parameter; means for determining potentials for each image element in the image data wherein the determined potentials represent the probability that a random walker starting at an image element in the image data first reaches a seed point in the image data when the probability of the seed point is set to unity; and means for assigning a label, based upon the determined potentials, to each image element in the image data. 33. The system of claim 32 wherein said image data represents a digital photograph. 34. The system of claim 32 wherein said color space is correlated with human visual perception. 35. The system of claim 34 wherein said color space is CIE LUV color space.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.