POLLEN GRAINS CLASSIFICATION WITH A DEEP LEARNING SYSTEM GPU-TRAINED

Abstract : Traditional approaches to automatic classification of pollen grains consisted of classifiers working with feature extractors designed by experts, which modeled pollen grains aspects of special importance for biologists. Recently, a Deep Learning (DL) algorithm called Convolutional Neural Network (CNN) has shown a great improvement in performance in many computer vision tasks such as classification, due to this great performance the computational requirements have increased considerably; therefore, it is advisable to use new platforms such as the Graphics Processing Unit (GPU), which offer large computational resources for the development of new systems with CNN. This paper presents the GPU-Trained implementation of a DL system with the CNN algorithm, proposing a CNN model capable of running on a GPU in real-time for the automatic classification of 19 different pollen grains belonging to 14 different families, which are found in high concentrations in Mexico, and which are large interest in areas such as beekeeping, paleoecology, botany, allergology, agriculture among others. These areas seek to improve the collection of palynological data in terms of time and accuracy. In order to evaluate our model, evaluation tests were performed in the NVIDIA Jetson TX2 Developer Kit GPU. Experimental results achieves around 90% in CCR and Sensitivity in the proposed model. Additionally, the proposed model works at a processing speed of 6,826 Frames Per Second (FPS) and has approximately 50% fewer parameters than reported in related works
 EXISTING SYSTEM :
 ? In order to evaluate our model, evaluation tests were performed in the NVIDIA Jetson TX2 Developer Kit GPU. Experimental results achieves around 90% in CCR and Sensitivity in the proposed model. ? Additionally, the proposed model works at a processing speed of 6,826 Frames Per Second (FPS) and has approximately 50% fewer parameters than reported in related works
 DISADVANTAGE :
 ? Con el surgimiento de nuevos algoritmos como las CNN se satisfacen problemáticas de los enfoques tradicionales (dificultades de selección de características), teniendo en un mismo método y de forma automática las etapas de extracción de características y clasificación, consiguiendo así grandes niveles de representación de los datos, superando de este modo todo enfoque tradicional. ? Sin embargo, hay otra forma de abordar el problema de la clasificación de granos de polen, la cual consiste en extraer las características principales de las imágenes y clasificarlas de forma automática con grandes resultados, utilizando un sólo algoritmo, denominado CNN.
 PROPOSED SYSTEM :
 ? Como resultado, existe un gran interés en diversas áreas para desarrollar un sistema de clasificación de granos de polen automático, para incorporarlo en la práctica diaria de recolección de datos palinológicos y sea una herramienta de apoyo de gran velocidad y precisión. ? Los enfoques tradicionales dividen en dos etapas el problema de la clasificación de granos de polen, en su primera etapa aplican métodos discriminativos sobre conjuntos de imágenes, extrayendo características específicas (las características varían de acuerdo al descriptor, existen bancos de filtros que extraen características de forma, color, textura, etc.), en la segunda etapa se aplican métodos de clasificación a las características extraídas
 ADVANTAGE :
 ? it is advisable to use new platforms such as the Graphics Processing Unit (GPU), which offer large computational resources for the development of new systems with CNN. This paper presents the GPU-Trained implementation of a DL system with the CNN algorithm, proposing a CNN model capable of running on a GPU in real-time for the automatic classification of 19 different pollen grains belonging to 14 different families, which are found in high concentrations in Mexico, and which are large interest in areas such as beekeeping, paleoecology, botany, allergology, agriculture among others.
Download DOC Download PPT

We have more than 145000 Documents , PPT and Research Papers

Have a question ?

Mail us : info@nibode.com