Download presentation
Presentation is loading. Please wait.
Published byStephanie Wade Modified over 9 years ago
1
Botany Image Retrieval Haibin Ling University of Maryland, College Park
2
Content 1.Problems 2.Related works 3.Our Experiments 4.Summary: difficulties and future works
3
Problems Reduce botany image retrieval to leaf image retrieval One-One classification relatively easy One-Many classification More difficult Segmentation and/or detection Query Image Prototype database Query Query Image An example from specimen database Query
4
Works at other groups Related works and publications Linkoping Univ & Swedish Museum of Natural History : Classification of Leaves from Swedish Trees. Linkoping Univ & Swedish Museum of Natural History: Classification of Leaves from Swedish Trees. A master thesis by Oskar J O S ö derkvist Oregon State Univ: Image Retrieval from Plant Database A master thesis by Ashit Gandhi (supervised by Lead by Thomas Dietterich) National Institute for Agricultural Botany (UK) : Chrysanthemum Leaf Classification National Institute for Agricultural Botany (UK) : Chrysanthemum Leaf Classification A conference paper by Abbasi, Mokhtarian and Kittler Summary All the works are contour based Their result are at beginning stages
5
Classification of Leaves from Swedish Trees (Linkoping Univ.) 15 tree classes, 50 test images per class Simple ANN + nine features (area, eccentricity, moment, etc.) Average correct ratio is 82% Some classes have rather low correct ratios: ulmus carpinifolia 52% sorbus hybrida 36% from www.isy.liu.se/cvl/Projects/Sweleaf/samplepage.htmlwww.isy.liu.se/cvl/Projects/Sweleaf/samplepage.html
6
Content-Based Image Retrieval from Plant Database (OSU) Six species, two kinds of data: isolated leaves & herbarium specimen Method: match contours by dynamic programming Good for isolated leaves, average correct ratio: 96.8% Not so good for herbarium leaves, either as query image (correct ratio 59%) or as templates (61%). Image from http://web.engr.oregonstate.edu/~tgd/leaves/dataset.htmhttp://web.engr.oregonstate.edu/~tgd/leaves/dataset.htm
7
Chrysanthemum Leaf Classification - National Institute for Agricultural Botany (UK) Farzin Mokhtarian et al. 400 leaves from 40 varieties. Method: curvature scale space contours + eccentricity, circularity and aspect ratio Result: the correct ratio (among the top 5 choices) is over 95%
8
Experiments at UMD (1) D. Jacobs, H. Ling, I.J. Chu, started on March, 2003 http://www.cs.umd.edu/~hbling/Research/Botany/bota ny.htm http://www.cs.umd.edu/~hbling/Research/Botany/bota ny.htm Image preprocessing: Contour extraction and simplification Background subtraction Contour based classification for isolated leaves Model based leaf detection Contour extraction
9
Experiments at UMD (2) -- Isolated Leaves Contour based classification for isolated leaves (nearest neighbor), using the Swedish leave data Fourier descriptor, average correct ratio 90% Shape context, average correct ratio 88% Benefit: Invariant to scaling, translation and rotation Problems: Both are “ global ” descriptors, difficult to handle occlusion or overlay The leaves need to be segmented first.
10
Experiments at UMD (3) -- Model-Based Leaf Detection Goal: extract leaves from specimen images, which may contain more than one leaf Hough transform (weighted by matching cost) Shortest path (grouping edge segments) modelspecimen leaf detection current result, no elimination yet
11
Summary - Difficulties Difficulties Detection/Segmentation Deformed leaf shapes Fresh vs. dry leaves (loss of color information, distortion, etc.) Left: 7 branches. Center: 9 branches, missing a stem. Right: dry specimen, no color and bad shape and texture.
12
Summary - Future works Possible future experiments includes: Composition system method and syntactic pattern recognition Appearance based model Texture analysis Eigenshape analysis
13
Suggestions and Thanks Thanks!
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.