Support Vector Machine (SVM) Recognition Approach adapted to Individual and Touching Moths Counting in Trap Images

Mohamed Chafik Bakkay (1) , Sylvie Chambon (1, 2) , Hatem A. Rashwan (3) , Christian Lubat (4) , Sébastien Barsotti (4)

1 IRIT-REVA - Real Expression Artificial Life
2 Toulouse INP - Institut National Polytechnique (Toulouse)
3 IRIT-SC - Signal et Communications
4 SiConsult (FRANCE)

This paper aims at developing an automatic algorithm for moth recognition from trap images in real-world conditions. This method uses our previous work for detection [1] and introduces an adapted classification step. More precisely, SVM classifier is trained with a multi-scale descriptor, Histogram Of Curviness Saliency (HCS). This descriptor is robust to illumination changes and is able to detect and to describe the external and the internal contours of the target insect in multi-scale. The proposed classification method can be trained with a small set of images. Quantitative evaluations show that the proposed method is able to classify insects with higher accuracy (rate of 95.8%) than the state-of-the art approaches.

Mots clés: Detection; Segmentation; Moth; SVM; Curvature

Domaines: Vision par ordinateur et reconnaissance de formes [cs.CV]

Mohamed Chafik Bakkay, Sylvie Chambon, Hatem A. Rashwan, Christian Lubat, Sébastien Barsotti. Support Vector Machine (SVM) Recognition Approach adapted to Individual and Touching Moths Counting in Trap Images. Workshop on Visual observation and analysis of Vertebrate And Insect Behavior @ 24th International Conference on Pattern Recognition (VAIB @ IPCR2018), Aug 2018, Beijing, China. pp.1-4. ⟨hal-02498757⟩