330 likes | 448 Views
CrowdSearch : Exploiting Crowds for Accurate Real-time Image Search on Mobile Phones. Original work by Yan, Kumar & Ganesan Presented by Shibo Li & Jian Yu. Problem Definition. How to search information?. Problem Definition. Mobile-based search will become more important in the future.
E N D
CrowdSearch: Exploiting Crowds for Accurate Real-time Image Search on Mobile Phones Original work by Yan, Kumar & Ganesan Presented by Shibo Li & Jian Yu
Problem Definition • How to search information?
Problem Definition • Mobile-based search will become more important in the future. • More than 70% of smart phone users perform searches. • Expected to be more mobile searches than non-mobile searches soon • Text-based mobile searches are easy as well… • What about searching images?
Problem Definition • Image search using mobile phones
Problem Definition • Automatic searching
Idea • Image searching based on crowd source. CrowdSearch Algorithm
Challenges • Automatic image search: • Delay↓, Cost ↓, Accuracy ↓ • People validation image search: • Delay ↑, Cost ↑, Accuracy ↑
Challenge: Accuracy • Human validation improves accuracy 2-5 times. • Majority(5) can achieve the highest accuracy up to 95% • So we send each image to 5 people to get the majority feedback.
Challenge: Delay & Cost tradeoff • Parallel Scheme
Challenge: Delay & Cost tradeoff • Serial Scheme
CrowdSearch: compromised scheme • Prediction requires delay and accuracy models
Delay Model • Statistically, both of the delays follow the exponential distribution. • Overall delay distribution is the convolution of the acceptance and submission delay.
Power Consideration • Should some image processing occur on the local device or should it be outsourced to the server? • Use remoteprocessing when WiFi is available. • Use local processingwhen only 3G is available
Evaluation • Delay model meets the exponential distribution
CrowdSearch Performance • CrowdSearch optimized algorithm
Thoughts/Criticism • Only 1000 images in the backend database. • Would increasing the number of automated search images increase total task time in a significant way? • The evaluation only based on 4 categories. • Buildings, Books, Flowers and Faces • Suggestion: • Internet database • Let the user to choose the categories • Too many distractions in a single image
Thoughts/Criticism • Too many disturbances in a single image
Q&A Thank you!