Gusmão G, Machado Saulo C S, Rodrigues Marco A B
Polytechnic School of Pernambuco, University of Pernambuco, Recife, Brazil 50720-001.
Annu Int Conf IEEE Eng Med Biol Soc. 2009;2009:6714-7. doi: 10.1109/IEMBS.2009.5333759.
Dengue fever has become a major international public health concern in recent decades. As dengue fever not have available vaccine or specific treatment, the only known form to prevent the illness is by applying strategies to control its vector, the Aedes aegypti mosquito. Ovitraps, special traps to collect mosquito eggs, are used to detect Aedes aegypti presence and to approximate the gauge of the adult mosquitoes population in the environment by counting the number of eggs laid in an trap. This counting is usually performed in a manual, visual and non-automatic form. This work proposes a new automatic method to automatically count the number of eggs in digital images of ovitraps based on image processing techniques (color systems exploration) and k-Means clustering algorithm. The proposed method performs an improvement on the results when compared with previous studies.
近几十年来，登革热已成为一个重大的国际公共卫生问题。由于登革热没有可用的疫苗或特效治疗方法，唯一已知的预防该疾病的方式是采用控制其病媒埃及伊蚊的策略。诱蚊产卵器是用于收集蚊卵的特殊陷阱，通过计算放置在陷阱中的卵的数量来检测埃及伊蚊的存在，并估算环境中成年蚊子的数量。这种计数通常以手动、视觉且非自动的方式进行。这项工作提出了一种基于图像处理技术（颜色系统探索）和k均值聚类算法的新自动方法，用于自动计算诱蚊产卵器数字图像中的卵的数量。与先前的研究相比，该方法在结果上有改进。
