Wild boar Classification by Using a Fusion of Texture Analysis Methods

• Luís Sílva Júnior UFU
• Maricéia Pádua IEF
• Leonardo Ogusuku IEF
• Marcelo Albertini UFU
• Renato Pimentel UFU
• André R. Backes UFU

Resumo

In several countries the wild boar is an invasive species that remains widespread mainly due its adaptability and uncontrolled reproduction. The monitoring of populations of this pest by camera traps is a promising technique. These devices capture a large variety of animals, including native species that share similarities with the wild boar, therefore the precise identification of the animal species is essential to control the wild boars. To address this problem, we evaluated 18 different texture analysis methods on their ability to discriminate between two native ``bush pigs'' species of the Brazilian fauna, collared peccary (\textit{Pecari tajacu}) and white-lipped peccary (\textit{Tayassu pecari}), and one invasive species, wild boar (\textit{Sus scrofa}). Results show that species identification is a difficult task due to the similarities among classes, being the distinction between native and invasive species an easier task, and that combining of texture methods improves the accuracy while diminishes the number of false positives (i.e., native species classified as invasive).

Palavras-chave: Texture Analysis, Computer Vision, Wild boar