Study on recognition of black insects on dark background by computer vision
- 10.2991/iccia.2012.53How to use a DOI?
- black insect, extraction of insect, dark background, color-to-gray transformation, computer vision
Improved color channel comparison method (ICCCM) is an effective method to transform color images into gray-scale ones. Based on the ICCCM, black or white insects could be effectively extracted and recognized from the real color images with bright background. However it is difficult to use the ICCCM to extract and recognize the black insects from the real color image with dark background. In this paper, the ICCCM is modified to transform the color images into the gray ones, extracting and recognizing the black insects on the dark background. The ICCCM is modified as follows: (1) A threshold of the gray image is an average brightness value of red (R), green (G) and blue (B) in all the image pixels. (2) The bright pixels and the color pixels have the highest brightness value 255 in the gray image. (3) A pixel brightness value of the dark area in the gray image equals to a minimum of R, G and B in the pixel. (4) After deleted all the pixels with a brightness value of 255, a threshold of the binary image is determined by Otsu’s theory. The modified ICCCM more effectively extracts and recognizes the black insects from the real color images with dark background compared with the ICCCM.
- © 2013, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Sa Liu AU - Yan Yang AU - Xiaodong Zhu AU - Huaiwei Wang AU - Shibin Lian PY - 2014/05 DA - 2014/05 TI - Study on recognition of black insects on dark background by computer vision BT - Proceedings of the 2012 2nd International Conference on Computer and Information Application (ICCIA 2012) PB - Atlantis Press SP - 218 EP - 221 SN - 1951-6851 UR - https://doi.org/10.2991/iccia.2012.53 DO - 10.2991/iccia.2012.53 ID - Liu2014/05 ER -