1 / 20

Computational and Biological Vision Course, Semester A, 2006 2.3.06

This project focuses on the development of a segmentation tool to divide images into components such as objects, text, shading, and colors. The goal is to imitate the process of human perception and apply it in computer systems. The tool is cross-platform, written in Java, and supports various actions and image formats. An experiment was conducted to analyze how different groups of people interpret and segment images.

bolivar
Télécharger la présentation

Computational and Biological Vision Course, Semester A, 2006 2.3.06

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Computational and Biological Vision Course, Semester A, 20062.3.06 Rinat Gotsulsky, 040371163 Roni Rabi, 037668118 Rinat & Roni Segment Painter

  2. Our Goal:Segmentation Painter Tool Rinat & Roni Segment Painter

  3. Background Rinat & Roni Segment Painter

  4. Perceptual Organization • The ability of people to perceive structure in images exists apart from both the perception of 3D and from the recognition of familiar objects. • The action of organize the data even when we have no idea about the picture meaning is important to the Computational Vision and can help to analyze models (known & unknown) • We focus on Segmentation- one of its issues. Rinat & Roni Segment Painter

  5. Segmentation • The approach is to divide a single picture into components, objects, text, shading, colors etc. • We are trying to imitate the evolution solution to this approach. • Splitting an image into segments can be an extremely hard problem. • There are no unique definition and one picture can be explicit in billions ways. Rinat & Roni Segment Painter

  6. Example: Rinat & Roni Segment Painter

  7. Where do we enter the picture? Rinat & Roni Segment Painter

  8. SegmentPainter Tool • We developed a toolkit enable people to separate picture to segments. • It enable us to learn about this process and later to apply this approach in computers systems. Rinat & Roni Segment Painter

  9. The SegmentPainter Tool Rinat & Roni Segment Painter

  10. The SegmentPainter Tool Rinat & Roni Segment Painter

  11. SegmentPainter Tool- technical details • The project is cross platform- written in Java language • More then 3000 code line • Support the following actions: File new, open, save, save as, close and exit. • Support in 4 recent files. • Support BMP, JPG, GIF and JPEG images • Support painting lines, curves and free hands (mouse motion) • Support 12 different colors Rinat & Roni Segment Painter

  12. Ashort experiment on how people interrupt pictures • Population: 3 groups of people: • Students who take this course. • Students who didn’t take and studding CS. • Other student (from other department). • Experiment: 6 people paint their segments interpretation of 3 pictures. Rinat & Roni Segment Painter

  13. Results Rinat & Roni Segment Painter

  14. 2 Cs students that take vision course 2 Cs students with on vision course 2 Cs students out “Teva” department Rinat & Roni Segment Painter

  15. 2 Cs students that take vision course 2 Cs students with on vision course 2 Cs students out “Teva” department Rinat & Roni Segment Painter

  16. 2 Cs students that take vision course 2 Cs students with on vision course 2 Cs students out “Teva” department Rinat & Roni Segment Painter

  17. Conclusions Rinat & Roni Segment Painter

  18. Segmentation : • In our small research there is no one explanation for a paint. • The segmentation was similar in all of the groups and maybe its from the fact that we see and investigate picture all the time and not because experience and learning of computational vision. • Its not obvious to segment picture – its not a well done algorithm. Rinat & Roni Segment Painter

  19. Program SegmentPainter : • There are few must features that need to be added to our toolkit. • The mousses in computers lab must be replaced to better ones (optics). • Segmentation is very difficult to draw. • The Segmentation take a long time. • Need a good qualificationsin painting to draw a segment picture. Rinat & Roni Segment Painter

  20. Thanks for interesting course Rinat & Roni Segment Painter

More Related