Computer vision for larval structures identification applied to forensic science.
Computer vision for larval structures identification applied to forensic science.
Author(s): OLIVEIRA, C. E.; LIMA, L. R. de; OLIVEIRA, G. R. A. de; GONÇALVES, A. B.; PISTORI, H.; KOLLER, W. W.
Summary: The diptera maggots are used in forensic entomology to estimate the post-mortem interval (PMI). Maggots have a wide range of morphological and structural features that aid in the identification. In order to assist in the necrophagous larvae identification, this research aims to develop a software using computer vision and machine learning to automate the classification process. Diptera maggots were collected in a dead pig at the capital of Mato Grosso do Sul state, Campo Grande. The maggots were identified and photographed at a light microscope (5x objective). Next, the images were processed, the features extraction was performed using an extractor in Python language. The classification of the images were tested with AdaBoost, Random Forest, Random Tree and SMO classifiers. The SMO the best performa.
Publication year: 2016
Types of publication: Paper in annals and proceedings
Unit: Embrapa Beef Cattle
Keywords: Computer vision, Entomology, Insect larvae
Observation
Some of Embrapa's publications are published as ePub files. To read them, use or download one of the following free software options to your computer or mobile device. Android: Google Play Books; IOS: iBooks; Windows and Linux: Calibre.
Access other publications
Access the Agricultural Research Database (BDPA) to consult Embrapa's full library collection and records.
Visit Embrapa Bookstore to purchase books and other publications sold by Embrapa.