wang, z., et al. presented by: kayla henneman october 27, 2014 who is here: location aware face...

17
Wang, Z., et al. Presented by: Kayla Henneman October 27, 2014 WHO IS HERE: LOCATION AWARE FACE RECOGNITION

Upload: maximilian-horton

Post on 24-Dec-2015

212 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Wang, Z., et al. Presented by: Kayla Henneman October 27, 2014 WHO IS HERE: LOCATION AWARE FACE RECOGNITION

Wang, Z., et al.Presented by: Kayla HennemanOctober 27, 2014

WHO IS HERE: LOCATION AWARE FACE RECOGNITION

Page 2: Wang, Z., et al. Presented by: Kayla Henneman October 27, 2014 WHO IS HERE: LOCATION AWARE FACE RECOGNITION

• Use location to narrow down search space• Increasing number of photos taken with

mobile devices• Use the location information associated

with the photo to narrow down the person in the photo

SOLUTION

• Many facial expressions

• Changes in appearance• Hair style• Cosmetics• With or without glasses• Illumination• Varying viewpoints

CHALLENGES

INTRODUCTION

Page 3: Wang, Z., et al. Presented by: Kayla Henneman October 27, 2014 WHO IS HERE: LOCATION AWARE FACE RECOGNITION

GIVEN:

• Training set—set of face images labeled with the person’s identity

• Testing set—set of unlabeled photos from the same group of people

GOAL:

• Identify each person in the testing photos

FACE RECOGNITION PROBLEM

Page 4: Wang, Z., et al. Presented by: Kayla Henneman October 27, 2014 WHO IS HERE: LOCATION AWARE FACE RECOGNITION

• User will have different probabilities of appearing in a photo based on the location• Example: Alice lives in Palo Alto, CA. Then pictures taken at Alice’s home have a high

probability of belonging to Alice, Alice’s family, or Alice’s friends. The pictures have a low probability of belonging to someone in Norfolk, VA

• When trying to identify someone in the photo, only compare photos which are taken at places the person usually appears

ASSUMPTIONS

Page 5: Wang, Z., et al. Presented by: Kayla Henneman October 27, 2014 WHO IS HERE: LOCATION AWARE FACE RECOGNITION

• Each face image is associated with a location

• The server creates clusters of locations from the training set• Each location cluster contains a set of users who have photos in that location, their

photos, and photos of their friends

• The client can take a photo and attach its location information, then send it to the server and query the person in the photo

• The server will answer the query and return the identification of the person in the photo

HOW IT WORKS

Page 6: Wang, Z., et al. Presented by: Kayla Henneman October 27, 2014 WHO IS HERE: LOCATION AWARE FACE RECOGNITION

• HOW TO FORM THE LOCATION CLUSTERS AND THE GRANULARITY FOR THE LOCATIONS

• How to process the photo and extract useful features

• How to search smartly in order to recognize the face and identify the person

• How to accelerate the entire process and avoid long response time on client side

CHALLENGES

Page 7: Wang, Z., et al. Presented by: Kayla Henneman October 27, 2014 WHO IS HERE: LOCATION AWARE FACE RECOGNITION

• Make use of the location information from mobile-taken photos and propose a face recognition algorithm which reduces the search space

• Build a hybrid face recognition algorithm

FIRST SEARCH AND MATCH PHOTOS WITHIN THE GIVEN LOCATION; IF THIS FAILS, SEARCH OVER ALL PHOTOS

MAIN CONTRIBUTIONS (1)

Page 8: Wang, Z., et al. Presented by: Kayla Henneman October 27, 2014 WHO IS HERE: LOCATION AWARE FACE RECOGNITION

• Take into account social network information• When a user appears frequently in a locations, the user’s friends also have a high

probability of showing up in that location

FRIENDS PHOTOS ARE USED TO TRAIN THE FACE CLASSIFIER FOR THE LOCATION

MAIN CONTRIBUTIONS (2)

Page 9: Wang, Z., et al. Presented by: Kayla Henneman October 27, 2014 WHO IS HERE: LOCATION AWARE FACE RECOGNITION

• Transmit the compressed face descriptor to the server for the query, rather than sending the original image

SAVES THE NETWORK TRAFFIC AND REDUCES RESPONSE TIME

MAIN CONTRIBUTIONS (3)

Page 10: Wang, Z., et al. Presented by: Kayla Henneman October 27, 2014 WHO IS HERE: LOCATION AWARE FACE RECOGNITION

• Client side:• User takes a photo of people on a

mobile phone and sends the recognition query to the server using wireless networks

• Face features and location information are transmitted to the server for recognition

• Server side:• Organize the face database by

locations• Maintain a backup classifier which is

obtained from all images in the database

• Sends back the identification result

FRAMEWORK

Page 11: Wang, Z., et al. Presented by: Kayla Henneman October 27, 2014 WHO IS HERE: LOCATION AWARE FACE RECOGNITION

GIVEN A COLLECTION OF LABELED PHOTOS WITH GEO-LOCATION INFORMATION, USE AGGLOMERATIVE CLUSTERING TO DISCOVER LOCATION CLUSTERS

• Consider each geo-location data, using longitude and latitude as a point in the two-dimensional space

• Initially, have n points and assign them to n clusters

• In each iteration, merge two clusters if the distance between two clusters is the minimum among all pairs of clusters

• Keep merging clusters until the minimum distance in each iteration is above a threshold or the number of clusters wanted is obtained

LOCATION CLUSTERING

Page 12: Wang, Z., et al. Presented by: Kayla Henneman October 27, 2014 WHO IS HERE: LOCATION AWARE FACE RECOGNITION

• Training a classifier for each location:• Convert photos associated with the location to feature descriptors

• Describing each face:• Adopt a local descriptor based face feature pipeline

• Detecting faces:• Viola-Jones face detector used to detect face patches• Nested nose detector applied• Face patches normalized to the same size

FACE FEATURE

Page 13: Wang, Z., et al. Presented by: Kayla Henneman October 27, 2014 WHO IS HERE: LOCATION AWARE FACE RECOGNITION

• Use algorithm to detect facial landmarks

• Align each face patch

• Remove effects of illumination

FROM EACH LANDMARK, TWO SIFT DESCRIPTORS OF DIFFERENT SCALES ARE EXTRACTED AND CONCATENATED TO FORM THE FACE FEATURE DESCRIPTOR

FACE FEATURE

Page 14: Wang, Z., et al. Presented by: Kayla Henneman October 27, 2014 WHO IS HERE: LOCATION AWARE FACE RECOGNITION

• Face descriptor computed using the pipeline

• Compresses the descriptor and sends to the server

MOBILE CLIENT

• Face descriptors are extracted from photos and trained by a Support Vector Machine (SVM) classifier• Each location has its own SVM classifier

and is represented by the coordinate of the cluster center

• When a query is received, it checks the location info and finds the nearest location in the database• This location is used for face recognition

• Confidence score is defined• If the confidence score is too low, use the

backup database

SERVER

SYSTEM

Page 15: Wang, Z., et al. Presented by: Kayla Henneman October 27, 2014 WHO IS HERE: LOCATION AWARE FACE RECOGNITION

• Dataset:• 2,001 images• 60 people• 6 locations

• Names and social network relations among the 60 people are known

EVALUATIONS

Page 16: Wang, Z., et al. Presented by: Kayla Henneman October 27, 2014 WHO IS HERE: LOCATION AWARE FACE RECOGNITION

• Compared with a baseline method, i.e. method without location

COMPARISON OF PERFORMANCE

• Accuracy of 5 tests at a particular location

• 80% of images used as training set; 20% used as testing set

EVALUATION SUMMARY

FACE RECOGNITION ACCURACY

Page 17: Wang, Z., et al. Presented by: Kayla Henneman October 27, 2014 WHO IS HERE: LOCATION AWARE FACE RECOGNITION

• Seems to improve accuracy

• Limitations:• Only supports finding people already in the dataset

• Future work:• Scalability—more locations will pose an issue• Increase training set incrementally through social network or crowd wisdom• Handling when people move from one location to another• Predict which locations a person will appear since one person can be in many locations

CONCLUSION