face detection and recognition for distributed systems meng lin and ermin hodžić 1

Post on 29-Dec-2015

212 Views

Category:

Documents

0 Downloads

Preview:

Click to see full reader

TRANSCRIPT

Face Detection And Recognition ForDistributed SystemsMeng Lin and Ermin Hodžić

1

Motivation

• Security systems•Digital cameras, adjustments• Social networks•Marketing

2

Face Detection

• Locating and extracting faces in images•Rectangles as output

3

Face Recognition

• Identifying person on image• Finding closest match

4

MapReduce model

•Parallel model• Framework for distributed systems•Hadoop local filesystem•Amazon Elastic MapReduce

5

Solution: Face Detection

6

Solution: Face Detection

7

Solution: Face Detection

•Partitions based on face scale

8

Solution: Face Recognition

•Distribution of recognizers•Recognizing in parallel•Reduce the most confident result

9

Solution: Face Recognition

10

Hadoop Image Handling

• Images as text•Collection of images in a big file•Utilize Hadoop default input format

11

Hadoop Image Handling

12

Evaluation

• Segmented Face Detection

•Raw OpenCV Face Detection

13

Evaluation

• Face recognition

•More nodes = slower• Input and data transfer overhead• Jobs computationally cheap

14

Conclusion

• Easily scalable parallel mode•Generalized framework• OpenCV just one sample tool

•A lot of communication• Low utilization of processors

15

16

top related