Automatic recognition of flowers through color and edge based contour detection

Soon Won Hong, Lynn Choi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Citations (Scopus)

Abstract

Unlike simple images processed by the existing image-based search engines, flowers have wider and more irregular range of shapes and patterns. In this paper we present an automatic recognition system of flowers for smartphone users. After a user transmits a flower image to the server, the image processing and searching is performed only by the server, eliminating the user interaction from the recognition process. The server detects the contour of a flower image by using both color-based and edge-based contour detection. Then, we classify its color groups and contour shapes by using k-means clustering and history matching. After comparing the input image with the reference images stored on the server, the server sends the most similar image to the user. We also address the image recognition failure issue caused by the light and the camera angle by partial recognition and image recovery. We have obtained the success rate of 94.8 % for 500 images from 100 species.

Original languageEnglish
Title of host publication2012 3rd International Conference on Image Processing Theory, Tools and Applications, IPTA 2012
Pages141-146
Number of pages6
DOIs
Publication statusPublished - 2012 Dec 1
Event2012 3rd International Conference on Image Processing Theory, Tools and Applications, IPTA 2012 - Istanbul, Turkey
Duration: 2012 Oct 152012 Oct 18

Other

Other2012 3rd International Conference on Image Processing Theory, Tools and Applications, IPTA 2012
CountryTurkey
CityIstanbul
Period12/10/1512/10/18

Fingerprint

Servers
Color
Image recognition
Smartphones
Search engines
Image processing
Cameras
Recovery

Keywords

  • contour detection
  • flower recognition
  • histogram matching
  • search engines
  • smartphones

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Hong, S. W., & Choi, L. (2012). Automatic recognition of flowers through color and edge based contour detection. In 2012 3rd International Conference on Image Processing Theory, Tools and Applications, IPTA 2012 (pp. 141-146). [6469535] https://doi.org/10.1109/IPTA.2012.6469535

Automatic recognition of flowers through color and edge based contour detection. / Hong, Soon Won; Choi, Lynn.

2012 3rd International Conference on Image Processing Theory, Tools and Applications, IPTA 2012. 2012. p. 141-146 6469535.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hong, SW & Choi, L 2012, Automatic recognition of flowers through color and edge based contour detection. in 2012 3rd International Conference on Image Processing Theory, Tools and Applications, IPTA 2012., 6469535, pp. 141-146, 2012 3rd International Conference on Image Processing Theory, Tools and Applications, IPTA 2012, Istanbul, Turkey, 12/10/15. https://doi.org/10.1109/IPTA.2012.6469535
Hong SW, Choi L. Automatic recognition of flowers through color and edge based contour detection. In 2012 3rd International Conference on Image Processing Theory, Tools and Applications, IPTA 2012. 2012. p. 141-146. 6469535 https://doi.org/10.1109/IPTA.2012.6469535
Hong, Soon Won ; Choi, Lynn. / Automatic recognition of flowers through color and edge based contour detection. 2012 3rd International Conference on Image Processing Theory, Tools and Applications, IPTA 2012. 2012. pp. 141-146
@inproceedings{024f967ee243439ebdb5cac1c667dbbd,
title = "Automatic recognition of flowers through color and edge based contour detection",
abstract = "Unlike simple images processed by the existing image-based search engines, flowers have wider and more irregular range of shapes and patterns. In this paper we present an automatic recognition system of flowers for smartphone users. After a user transmits a flower image to the server, the image processing and searching is performed only by the server, eliminating the user interaction from the recognition process. The server detects the contour of a flower image by using both color-based and edge-based contour detection. Then, we classify its color groups and contour shapes by using k-means clustering and history matching. After comparing the input image with the reference images stored on the server, the server sends the most similar image to the user. We also address the image recognition failure issue caused by the light and the camera angle by partial recognition and image recovery. We have obtained the success rate of 94.8 {\%} for 500 images from 100 species.",
keywords = "contour detection, flower recognition, histogram matching, search engines, smartphones",
author = "Hong, {Soon Won} and Lynn Choi",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/IPTA.2012.6469535",
language = "English",
isbn = "9781467325837",
pages = "141--146",
booktitle = "2012 3rd International Conference on Image Processing Theory, Tools and Applications, IPTA 2012",

}

TY - GEN

T1 - Automatic recognition of flowers through color and edge based contour detection

AU - Hong, Soon Won

AU - Choi, Lynn

PY - 2012/12/1

Y1 - 2012/12/1

N2 - Unlike simple images processed by the existing image-based search engines, flowers have wider and more irregular range of shapes and patterns. In this paper we present an automatic recognition system of flowers for smartphone users. After a user transmits a flower image to the server, the image processing and searching is performed only by the server, eliminating the user interaction from the recognition process. The server detects the contour of a flower image by using both color-based and edge-based contour detection. Then, we classify its color groups and contour shapes by using k-means clustering and history matching. After comparing the input image with the reference images stored on the server, the server sends the most similar image to the user. We also address the image recognition failure issue caused by the light and the camera angle by partial recognition and image recovery. We have obtained the success rate of 94.8 % for 500 images from 100 species.

AB - Unlike simple images processed by the existing image-based search engines, flowers have wider and more irregular range of shapes and patterns. In this paper we present an automatic recognition system of flowers for smartphone users. After a user transmits a flower image to the server, the image processing and searching is performed only by the server, eliminating the user interaction from the recognition process. The server detects the contour of a flower image by using both color-based and edge-based contour detection. Then, we classify its color groups and contour shapes by using k-means clustering and history matching. After comparing the input image with the reference images stored on the server, the server sends the most similar image to the user. We also address the image recognition failure issue caused by the light and the camera angle by partial recognition and image recovery. We have obtained the success rate of 94.8 % for 500 images from 100 species.

KW - contour detection

KW - flower recognition

KW - histogram matching

KW - search engines

KW - smartphones

UR - http://www.scopus.com/inward/record.url?scp=84875870433&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84875870433&partnerID=8YFLogxK

U2 - 10.1109/IPTA.2012.6469535

DO - 10.1109/IPTA.2012.6469535

M3 - Conference contribution

AN - SCOPUS:84875870433

SN - 9781467325837

SP - 141

EP - 146

BT - 2012 3rd International Conference on Image Processing Theory, Tools and Applications, IPTA 2012

ER -