1 / 60

以區域二元圖樣與部分比對為基礎之人臉辨識 Face Recognition with Local Binary Patterns and Partial Matching

以區域二元圖樣與部分比對為基礎之人臉辨識 Face Recognition with Local Binary Patterns and Partial Matching. Presenter : 施佩汝 Advisor : 歐陽明 教授. Outlines. Motivation Implementation Result Conclusion. Motivation. Motivation. Publication.

feo
Download Presentation

以區域二元圖樣與部分比對為基礎之人臉辨識 Face Recognition with Local Binary Patterns and Partial Matching

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. 以區域二元圖樣與部分比對為基礎之人臉辨識Face Recognition with Local Binary Patterns andPartial Matching Presenter: 施佩汝 Advisor: 歐陽明 教授

  2. Outlines • Motivation • Implementation • Result • Conclusion

  3. Motivation

  4. Motivation

  5. Publication • Che-Hua Yeh, Pei-Ruu Shih, Kuan-Ting Liu, Yin-Tzu Lin, Huang-Ming Chang, Ming Ouhyoung. A Comparison of Three Methods of Face Recognition for Home Photos. ACM Siggraph, poster, 2009.

  6. Problem Statement

  7. Main Contribution • Improve Local Binary Patterns by using Partial Matching Metric • Better Performance in Home Photos

  8. Implementation

  9. System Overview Images Descriptors Pre-Processing Build Descriptor Clustering Calculate LBP Build Descriptor

  10. System Overview Images Descriptors Pre-Processing Build Descriptor Clustering Calculate LBP Build Descriptor

  11. Pre-Processing

  12. System Overview Images Descriptors Pre-Processing Build Descriptor Clustering Calculate LBP Build Descriptor

  13. System Overview Images Descriptors Pre-Processing Build Descriptor Clustering Calculate LBP Build Descriptor

  14. Local Binary Patterns [PAMI2006] • An operator to encode the relationship of a pixel and its neighbors.

  15. Local Binary Patterns [PAMI2006] • An operator to encode the relationship of a pixel and its neighbors.

  16. Local Binary Patterns [PAMI2006] • An operator to encode the relationship of a pixel and its neighbors.

  17. Local Binary Patterns [PAMI2006] • An operator to encode the relationship of a pixel and its neighbors.

  18. Local Binary Patterns [PAMI2006] • An operator to encode the relationship of a pixel and its neighbors.

  19. Local Binary Patterns [PAMI2006] • An operator to encode the relationship of a pixel and its neighbors.

  20. Local Binary Patterns [PAMI2006] • An operator to encode the relationship of a pixel and its neighbors.

  21. Local Binary Patterns [PAMI2006] • An operator to encode the relationship of a pixel and its neighbors.

  22. Local Binary Patterns [PAMI2006] • An operator to encode the relationship of a pixel and its neighbors. LBP = 11010011

  23. System Overview Images Descriptors Prepared-Works Build Descriptor Clustering Calculate LBP Build Descriptor

  24. Facial Image Descriptor • They use Spatially Enhanced Histogram in original Local Binary Pattern. [PAMI2006]

  25. Local Patches • We sample a patch for every s pixels. • There are S patches for one image. s s

  26. Spatial Block [CVPR2007] • We use three concentric circles to describe a patch.

  27. Descriptor • Build a descriptor for one face.

  28. System Overview Images Descriptors Pre-Processing Build Descriptor Clustering Calculate LBP Build Descriptor

  29. System Overview Images Descriptors Pre-Processing Build Descriptor Complete-Linkage Clustering Calculate LBP Build Descriptor Compute all the similarities Clustering

  30. System Overview Images Descriptors Pre-Processing Build Descriptor Complete-Linkage Clustering Calculate LBP Build Descriptor Compute all the similarities Clustering

  31. Similarity • They use the weighted Chi-Square distance in original Local Binary Pattern. [PAMI2006]

  32. Partial Matching [ICCV2009] , • Step1: • Compute the similarity of each patch from one image with the nearby patches in another image. Image 1: I(1) Image 2: I(2)

  33. Partial Matching [ICCV2009] • Step2: • Sort the similarities of all patches. • dαSis the similarity of I(1) to I(2).

  34. Partial Matching [ICCV2009] • Step3: • Calculate the similarity of I(2) to I(1)

  35. Partial Matching [ICCV2009] • Step4: • Use the maximum of two similarity

  36. System Overview Images Descriptors Pre-Processing Build Descriptor Complete-Linkage Clustering Calculate LBP Build Descriptor Compute all the similarities Clustering

  37. Hierarchical Clustering • Build a tree-based hierarchical taxonomy (dendrogram) from a set of documents. Material Selected from Introduction to Information Retrieval, Christopher D. Manning, Prabhakar Raghavan and Hinrich Schütze, 2008.

  38. Hierarchical Clustering • Clustering obtained by cutting the dendrogram at a desired level: each connected connected component forms a cluster. Material Selected from Introduction to Information Retrieval, Christopher D. Manning, Prabhakar Raghavan and Hinrich Schütze, 2008.

  39. Hierarchical Complete-Linkage Clustering • Similarity of the “furthest” points. • Makes “tighter,” spherical clusters that are typically preferable. Material Selected from Introduction to Information Retrieval, Christopher D. Manning, Prabhakar Raghavan and Hinrich Schütze, 2008.

  40. Performance Optimization • 4 threads in Quad-Core system Images Descriptors Pre-Processing Build Descriptor Complete-Link Clustering Calculate LBP Build Descriptor Compute all the similarities Clustering

  41. Performance Optimization • 4 threads in Quad-Core system • 3 times faster than single thread. • 73 minutes to 24 minute for 309 images. Images Descriptors Pre-Processing Build Descriptor Complete-Link Clustering Calculate LBP Build Descriptor Compute all the similarities Clustering

  42. Result

  43. FERET Result • fa: gallery, 994 images • fb: alternative facial expression, 992 images • dup1: the photos taken after later, 736 images • dup2: the photos taken at least one year after the gallery, 228 images

  44. FERET Result ※ The time results are computed in multithreads version.

  45. Experiments • Home Photo Dataset I • 309 images, 5 subjects • Home Photo Dataset II • 838 images, 8 subjects

  46. Evaluation • Cluster Number • Unknown Number • Pair-wise Precision • Pair-wise Rand Index • Executing time

  47. Unknown Number • The number of clusters which contain only one component.

  48. Precision/Rand Index

  49. Dataset-I Result LBP: Local Binary Pattern, PM: Partial Matching, SB: Spatial Block ※ The time results are computed in multithreads version.

  50. Dataset-I Result LBP Our Result

More Related