Presentation is loading. Please wait.

Presentation is loading. Please wait.

Change Blindness Images Li-Qian Ma 1, Kun Xu 1, Tien-Tsin Wong 2, Bi-Ye Jiang 1, Shi-Min Hu 1 1 Tsinghua University 2 The Chinese University of Hong Kong.

Similar presentations


Presentation on theme: "Change Blindness Images Li-Qian Ma 1, Kun Xu 1, Tien-Tsin Wong 2, Bi-Ye Jiang 1, Shi-Min Hu 1 1 Tsinghua University 2 The Chinese University of Hong Kong."— Presentation transcript:

1 Change Blindness Images Li-Qian Ma 1, Kun Xu 1, Tien-Tsin Wong 2, Bi-Ye Jiang 1, Shi-Min Hu 1 1 Tsinghua University 2 The Chinese University of Hong Kong

2 Spot-the-difference Game

3

4 Motivation These image pairs are mainly generated by artists manually The degree of recognition difficulty is controlled by artists empirically

5 Goal Given an image, automatically generate a counterpart of the image With a controlled degree of “difficulty”

6 Psychological background Change blindness –Widely studied in psychology is caused by failure to store visual information in our short-term memory –Factors influencing visual attention (saliency), object presentation –Mostly qualitative

7 The Metric We define a metric to measure the blindness of an image pair There is a single change between the image pair The change region and the operator are known in advance The change is limited to the following operators: –Insertion/Deletion –Replacement –Relocation –Scaling –Rotation –Color-shift

8 The Metric

9 Amount of Change Color Difference Texture Difference Spatial Difference

10 Saliency Visual attention is highly context-dependent No existing saliency model attempts to explicitly quantify background complexity

11 Context-Dependent Saliency Modulate saliency via spatially varying complexity Existing saliency model Spatially varying complexity Context-dependent saliency

12 Color Similarity Color similarity : Small color similarityLarge color similarity

13 Spatial varying Complexity Weighted sum of color similarities between all region pairs around

14 Spatial varying Complexity

15 Context-Dependent Saliency Input images Global contrast saliency Spatial varying complexity Context-dependent saliency

16 Context-Dependent Saliency Input image Global contrast saliencyLearning-based saliencyImage signature Itti modelAIM saliencyJudd modelContext-Dependent Saliency

17 Synthesis Optional user manually refinement Original Image

18 Synthesis Original ImageChanged Counterpart 1.Randomly pick a region and a change operator 2.Search in the parameter space of the change operator Move Measured Difficulty B = 10.70.5

19 More Results

20

21 Original Image Changed Counterpart

22 More Results

23 User Study Generate 100 image pairs 30 subjects Pearson’s correlation: 0.74

24 User Study ModelGlobal contrast Learning based Image signature Itti model Correlation0.440.380.340.42 ModelJudd model AIM model Context- Dependent Correlation0.430.420.74

25 Conclusion Computational model for change blindness Context-dependent saliency model Change blindness image synthesis with desired degree of blindness

26 Future Works Add high-level image features into the metric Improve the predictability using more sophisticated forms Improve the accuracy of the metric considering just-noticeable difference(JND)

27 Acknowledgement Anonymous TVCG reviewers Thank you for your attention.


Download ppt "Change Blindness Images Li-Qian Ma 1, Kun Xu 1, Tien-Tsin Wong 2, Bi-Ye Jiang 1, Shi-Min Hu 1 1 Tsinghua University 2 The Chinese University of Hong Kong."

Similar presentations


Ads by Google