Automatic detection of individual and touching moths from trap images by combining contour‐based and region‐based segmentation. Issue 2 (8th November 2017)

• Record Type: Journal Article
• Authors: Bakkay, Mohamed Chafik; Chambon, Sylvie; Rashwan, Hatem A.; Lubat, Christian; Barsotti, Sébastien
• Is Part Of: IET computer vision. Volume 12:Issue 2(2018)
• Page Start: 138
• Page End: 145
• Publication Date: 2017-11-08
• Subjects: image segmentation -- biometrics (access control) -- convex programming -- computer vision; automatic detection -- touching moths -- individual moths -- trap images -- region based segmentation -- insect detection -- biometric image processing -- touching insects -- contour convex hull -- merging algorithm; Computer vision -- Periodicals; Pattern recognition systems -- Periodicals; 006.37
• DOI: 10.1049/iet-cvi.2017.0086
• Languages: English
• ISSNs: 1751-9632

Abstract

Abstract : Insect detection is one of the most challenging problems of biometric image processing. This study focuses on developing a method to detect both individual insects and touching insects from trap images in extreme conditions. This method is able to combine recent approaches on contour‐based and region‐based segmentation. More precisely, the two contributions are: an adaptive k ‐means clustering approach by using the contour's convex hull and a new region merging algorithm. Quantitative evaluations show that the proposed method can detect insects with higher accuracy than that of the most used approaches.