1 / 18

Spatial Pyramid Matching for Scene Recognition

This presentation discusses the Spatial Pyramid Matching technique for recognizing natural scene categories, focusing on key algorithm steps like interest point descriptors extraction and SVM training. The study delves into the construction of visual word dictionaries, spatial histograms, and intersection kernels to enhance scene recognition accuracy. A case study on Butterfly Classification using a dataset by Lazebnik, Schmid, and Ponce is presented, demonstrating the effectiveness of Spatial Pyramid techniques on varied features. The experiment showcases the impact of different spatial pyramid levels, showing improved results with increasing pyramid levels.

marsden-daniel
Download Presentation

Spatial Pyramid Matching for Scene Recognition

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. Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories Svetlana Lazebnik, Cordelia Schmid, Jean Ponce Presented by: Lubomir Bourdev Many of the slides by: Svetlana Lazebnik

  2. Key Idea • Pyramid Match Kernel (Grauman & Darrell) Pyramid in feature space, ignore location • Spatial Pyramid (this work) Pyramid in image space, quantize features

  3. Algorithm • Extract interest point descriptors (dense scan) • Construct visual word dictionary • Build spatial histograms • Create intersection kernels • Train an SVM

  4. Algorithm • Extract interest point descriptors (dense scan) • Construct visual word dictionary • Build spatial histograms • Create intersection kernels • Train an SVM OR Weak (edge orientations) Strong (SIFT)

  5. Algorithm • Extract interest point descriptors (dense scan) • Construct visual word dictionary • Build spatial histograms • Create intersection kernels • Train an SVM • Vector quantization • Usually K-means clustering • Vocabulary size (16 to 400)

  6. Algorithm • Extract interest point descriptors (dense scan) • Construct visual word dictionary • Build spatial histograms • Create intersection kernels • Train an SVM

  7. Algorithm • Extract interest point descriptors (dense scan) • Construct visual word dictionary • Build spatial histograms • Create intersection kernels • Train an SVM

  8. Algorithm • Extract interest point descriptors (dense scan) • Construct visual word dictionary • Build spatial histograms • Create intersection kernels • Train an SVM

  9. My experiment: Butterfly Classification Peacock Zebra

  10. Butterflies • Dataset from Lazebnik / Schmid / Ponce 70 train / 64 test 50 train / 41 test • Images centered on the butterfly • Significant background clutter • Large pose/viewpoint variations • Scale variations: up to x4

  11. Butterfly Results Spatial pyramid levels: 1 (No pyramid) Spatial pyramid levels: 4

More Related