You might also like

More about Contour and Texture for Visual Recognition of Object Categories

• Book details
• Synopsis
• Trending among others

You get 165 loyalty points

Book synopsis

The recognition of object categories has become a major topicin computer vision. Accurate automatic visual recognition iscentral to applications such as image search, robotics, and vehiclesafety systems. This book proposes new discriminative learningapproaches to three recognition tasks. \'Image classification\'aims to determine the presence of an object of a particularcategory in an image or video frame. \'Object detection\' furtheraims to localize these objects. And \'semantic segmentation\' aimsto partition an image into coherent regions of particularcategories. First, we show that a codebook of learned fragments ofobject contours is sufficient for accurate recognition. Second, wepropose new texture features that simultaneously exploit localappearance, approximate shape and appearance context. The efficacyof the new contour and texture features is tested on a variety ofchallenging image datasets. Finally, we show how a combination ofthese two largely orthogonal features improves recognition abovethat achieved by either feature alone.

Book details

Book category Books in English Computing & information technology Computer science Artificial intelligence

• Full title: Contour and Texture for Visual Recognition of Object Categories
• Subtitle: Automatic Object Recognition Using Learned Patterns of Contour and Texture
• Author: Jamie Shotton
• Language: English
• Binding: Paperback
• Number of pages: 152
• EAN: 9783639019704
• ISBN: 3639019709
• ID: 06811870
• Publisher: VDM Verlag Dr. Mueller E.K.
• Weight: 213 g
• Dimensions: 229 × 152 × 8 mm
• Date of publishing: 13. May 2008

Trending among others

---

---

---