Análisis Comparativo de las técnicas utilizadas en un Sistema de Reconocimiento de Hojas de Planta
[EN] The development of vision systems for identifying plants by leaves is an important challenge which has numerous applications ranging from food, medicine, industry and environment. Recently, several techniques have been proposed in the literature in order to identify plants in various fields of...
| Autores: | , , , , , |
|---|---|
| Tipo de recurso: | artículo |
| Fecha de publicación: | 2017 |
| País: | España |
| Institución: | Universitat Politècnica de València (UPV) |
| Repositorio: | RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia |
| Idioma: | español |
| OAI Identifier: | oai:riunet.upv.es:10251/143398 |
| Acceso en línea: | https://riunet.upv.es/handle/10251/143398 |
| Access Level: | acceso abierto |
| Palabra clave: | Classification Descriptors SVM Data Sets Clasificación Descriptores Conjuntos de Datos Características |
| Sumario: | [EN] The development of vision systems for identifying plants by leaves is an important challenge which has numerous applications ranging from food, medicine, industry and environment. Recently, several techniques have been proposed in the literature in order to identify plants in various fields of application. However, current techniques are restricted to the recognition and identification of plants using specific descriptors. In this paper, is accomplished a comparative analysis using different methods of feature extraction (textural, chromatic and geometric) and different methods of classification. The experiments are executed on very similar plants. Twelve sets of leaves with similar shape characteristics are studied using several classifiers. The performance of different combinations of classifiers-descriptors are analyzed in detail for each set. The results show that a combination of different feature extraction techniques is necessary in order to improve the performance. This combination of descriptors is more necessary when the leaves have similar characteristics. |
|---|