Percorrer por autor "Pinto, Cristina M."
A mostrar 1 - 4 de 4
Resultados por página
Opções de ordenação
- Deep learning recognition of a large number of pollen grain typesPublication . Monteiro, Fernando C.; Pinto, Cristina M.; Rufino, JoséPollen in honey reflects its botanical origin and melissopalynology is used to identify origin, type and quantities of pollen grains of the botanical species visited by bees. Automatic pollen counting and classification can alleviate the problems of manual categorisation such as subjectivity and time constraints. Despite the efforts made during the last decades, the manual classification process is still predominant. One of the reasons for that is the small number of types usually used in previous studies. In this paper, we present a large study to automatically identify pollen grains using nine state-of-the-art CNN techniques applied to the recently published POLEN73S image dataset. We observe that existing published approaches used original images without study the possible biased recognition due to pollen’s background colour or using preprocessing techniques. Our proposal manages to classify up to 97.4% of the samples from the dataset with 73 different types of pollen. This result, which surpasses previous attempts in number and difficulty of pollen types under consideration, is an important step towards fully automatic pollen recognition, even with a large number of pollen grain types.
- Deep learning recognition of a large number of pollen grain typesPublication . Monteiro, Fernando C.; Pinto, Cristina M.; Rufino, JoséPollen in honey reflects its botanical origin and melissopalynology is used to identify origin, type and quantities of pollen grains of the botanical species visited by bees. Automatic pollen counting and classification can alleviate the problems of manual categorisation such as subjectivity and time constraints. Despite the efforts made during the last decades, the manual classification process is still predominant. One of the reasons for that is the small number of types usually used in previous studies. In this paper, we present a large study to automatically identify pollen grains using nine state-of-the-art CNN techniques applied to the recently published POLEN73S image dataset. We observe that existing published approaches used original images without study the possible biased recognition due to pollen’s background colour or using preprocessing techniques. Our proposal manages to classify up to 97.4 % of the samples from the dataset with 73 different types of pollen. This result, which surpasses previous attempts in number and difficulty of pollen types under consideration, is an important step towards fully automatic pollen recognition, even with a large number of pollen grain types.
- The role of background colour in pollen recognition task using CNNPublication . Monteiro, Fernando C.; Pinto, Cristina M.; Rufino, JoséPollen recognition is a crucial but challenging task in addressing a variety of questions like pollination or palaeobotany, but also for other fields of research, e.g., allergology, melissopalynology or forensics. State-of-the-art methods mainly use deep learning CNNs for pollen recognition, however, we observe that existing published approaches use original images without study the possible biased recognition due to pollen’s background colour. In this paper, we evaluate the DenseNet model trained with original images and with segmented images (remove background) and analyse network’s predictive performance under these conditions using a cross evaluation approach. An accuracy of 97.4% was achieved that represents one of the best successes rate when weighted with the number of taxa of any attempt at automated pollen analysis currently documented in the literature. From these results, we confirm the existence of background specific influence in the recognition task.
- Towards precise recognition of pollen bearing bees by convolutional neural networksPublication . Monteiro, Fernando C.; Pinto, Cristina M.; Rufino, JoséAutomatic recognition of pollen bearing bees can provide important information both for pollination monitoring and for assessing the health and strength of bee colonies, with the consequent impact on people's lives, due to the role of bees in the pollination of many plant species. In this paper, we analyse some of the Convolutional Neural Networks (CNN) methods for detection of pollen bearing bees in images obtained at hive entrance. In order to show the in uence of colour we preprocessed the dataset images. Studying the results of nine state-of-the-art CNNs, we provide a baseline for pollen bearing bees recognition based in deep learning. For some CNNs the best results were achieved with the original images. However, our experiments showed evidence that DarkNet53 and VGG16 have superior performance against the other CNNs tested, with unsharp masking preprocessed images, achieving accuracy results of 99:1% and 98:6%, respectively.