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

TL;DR

This paper presents an SVM-based recognition algorithm for moths in trap images, utilizing a multi-scale descriptor that improves accuracy and robustness under real-world conditions.

Contribution

The paper introduces an adapted SVM classification method using the Histogram Of Curviness Saliency descriptor, achieving higher accuracy with fewer training images.

Findings

Classification accuracy of 95.8%

Robustness to illumination changes

Effective with small training sets

Abstract

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.