Presentation is loading. Please wait.

Presentation is loading. Please wait.

Face Recognition using Parallel Associative Memory 2009/12/31 學生:羅國育.

Similar presentations


Presentation on theme: "Face Recognition using Parallel Associative Memory 2009/12/31 學生:羅國育."— Presentation transcript:

1 Face Recognition using Parallel Associative Memory 2009/12/31 學生:羅國育

2 Outline Introduction Auto-associative memory for face recognition Parallel associative memory for face recognition Face similarity measure for recognition Experimental Results Conclusion

3 Introduction This paper proposes parallelization of the auto- associative memory in order to apply it for recognition of high resolution face images. The Olivetti Research Laboratory (ORL) face database.

4 Auto-associative memory for face recognition (1/3) Associative memories mimic the capacity of human brain to recall information in a robust and associative access mode. Neural network.

5 Auto-associative memory for face recognition (2/3) The input-output relationship in a linear associative memory is described by M × N gray scale images. W is an (MN)×(MN) matrix. (1) (2)

6 Auto-associative memory for face recognition (3/3) Now substituting W from (2) we have (3)

7 Parallel associative memory for face recognition (1/4) The system mainly performs three tasks: (i) Information storage, (ii) information retrieval based on some input pattern and (iii) matching of the information.

8 Parallel associative memory for face recognition (2/4)

9 Parallel associative memory for face recognition (3/4)

10 Parallel associative memory for face recognition (4/4)

11 Face similarity measure for recognition (1/2)

12 Face similarity measure for recognition (2/2) Run length: 兩個 1 之間, 0 出現的次數分別是 3 、 9 、 3 、 2 的話,這些值就稱為 0 的 run length 。 Fig. 2. A grid structure to explain the concept of run length count

13 Experimental Results (1/4) The ORL database contains total 400 images of 40 individuals from various ethnicity and sex under various pose, light, scale and expression. One set is considered as training set and the remaining 39 sets are used as testing set.

14 Experimental Results (2/4) In this experiment values of N, n and Tr are set to 128, 16 and 6 respectively. It is found that the best suitable value of Th 1 and Th 2 are 40 (i.e, 65 % portion of input image) and 25 (i.e, 40 % portion of input image) respectively.

15 Experimental Results (3/4)

16 Experimental Results (4/4) False Rejection Ratio (FRR) is 1% and 5.2% respectively. For false accept experiments the system was tested with 40 randomly chosen face images which are not present in the database. The observed FAR is 3.1%.

17 Conclusion In this paper a parallel associative memory based efficient face recognition system has been proposed. The goal is to scale the associative memories to high resolution images. A novel run length count based measure of face similarity suited for parallel associative memory is also proposed.

18 2015/10/9 Thanks for your attention!


Download ppt "Face Recognition using Parallel Associative Memory 2009/12/31 學生:羅國育."

Similar presentations


Ads by Google