Presentation is loading. Please wait.

Presentation is loading. Please wait.

The Bayesian Image Retrieval System,PicHunter Theory, Implementation, and Psychophysical Experiments.

Similar presentations


Presentation on theme: "The Bayesian Image Retrieval System,PicHunter Theory, Implementation, and Psychophysical Experiments."— Presentation transcript:

1 The Bayesian Image Retrieval System,PicHunter Theory, Implementation, and Psychophysical Experiments

2 Introduction Relevance feedback —— users give additional information Main idea: With an explicit model of a user’s actions, assuming a desired goal, PicHunter uses Bayes’ rule to predict the goal image, given their actions

3 Nature of search Target-specific search (Target search) exact match Category search same category is ok Open-ended search (browsing)

4 Bayes’ formula F j – hypothesis (Target image is j) E – experiment (user’s response behavior) Show us how the correctness of a hypothesis change after carrying out an experiment How to model P(E|F j )?

5 Theoretical basis for PicHunter During each session a set D t of N D images, Action A t H t ----History of the session

6 User Model:Assessing Image similarity Key term: P(A t |T=T i,D t,U) U:specific user Purpose:update the probability of each T i being target

7 Relevance feedback e.g. 2AFC (two-alternative forced-choice) Given two image, user need to choose which one is similar to target P(E|F j )  P(A=1|X 1,X 2,T=T i ) 1 if d(X1,Ti) < d(X2,Ti) 0.5 if d(X1,Ti) = d(X2,Ti) 0 d(X1,Ti) > d(X2,Ti) Another one is relative distance

8 Relative distance measure using the pictorial features distance as the form of the probability When N D =2, A t =1 or 2 P sigmoid (A=1|X 1,X 2,T) =

9 Pictorial features HSV-HIST Hue, Saturation, Value histogram HSV-CORR RGB-CCV Color histogram

10 Display Updating Model Most-Probable Display Updating Model Give the most similar one for user to choose Most-informative Display Updating Model C[P(T)] Give both similar and dissimilar images for use to choose

11 Results Cox formulated an experiment XYZ X - with memory or with out Use all the response or just response in one iteration Y - with using relative / absolute distance measure Z – use pictorial or semantic measure Benchmark - how many images need to be displayed before target is found MRS is the best With memory, use relative distance and semantic measure


Download ppt "The Bayesian Image Retrieval System,PicHunter Theory, Implementation, and Psychophysical Experiments."

Similar presentations


Ads by Google