Automatic detection and classification of grains of pollen based on shape and texture

  title={Automatic detection and classification of grains of pollen based on shape and texture},
  author={Mar{\'i}a Rodr{\'i}guez Dami{\'a}n and Eva Cernadas and Arno Formella and Manuel Fern{\'a}ndez Delgado and Maria Pilar de S{\'a}-Otero},
  journal={IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews)},
Palynological data are used in a wide range of applications. Some studies describe the benefits of the development of a computer system to pollinic analysis. The system should involve the detection of the pollen grains on a slice, and their classification. This paper presents a system that realizes both tasks. The latter is based on the combination of shape and texture analysis. In relation to shape parameters, different ways to understand the contours are presented. The resulting system is… 

Figures and Tables from this paper

Development of an Automatic Pollen Classification System Using Shape, Texture and Aperture Features

An automatic process is developed which segments the particle contour and uses the extracted features for the classification process and streamlined the process into one code base, and developed multithreading functionality to decrease the processing time for large datasets.

Image Processing for Pollen Classification

Automatic recognition of pollen grains can overcome problems, producing purely objective results faster, and provide invaluable in the studies of flora, thanks to computer vision.

System detection and automatic classification of pollen grain applies technical digital imaging process

This paper show the current state of a computer system that will allow the recognition and taxonomic classification of pollen grains of some of the most important tropical honey plants in Costa Rica

Classification of Pollen Grain Images Based on an Ensemble of Classifiers

An automatic method for classification of pollen grain images based on a set of features and classifiers based on an ensemble rule of majority voting is developed and analyzed.

Features extraction for pollen recognition in honey using Gabor filters

The aim of the research is to investigate the features extraction from microscope images of pollens for classifying honey on the base of its botanical origin using a filter-bank of Gabor filters and the performance of the proposed algorithm was evaluated by simulations in MATLAB environment.

Pollen classification based on contour features

This work focuses on analysis and classification stages of pollen identification based on an HMM kernel, and the morphological details of the contour are proposed as pollen grains discriminative features.

Pollen Grains Contour Analysis on Verification Approach

A classification approach using binarization of pollen grain images, contour and feature extraction to locate the pollen grain objects within the images is being proposed.

Recognition of Optical Microscopy Images Based on Shape and Texture

Airborne pollen is the main cause of pollen allergy, so statistic of the amount and distribution of pollen in the air is important. This paper presents a method to identify airborne pollen grains in



A new approach to automated pollen analysis

Pollen texture identification using neural networks

A new technique, neural network analysis, is briefly introduced, and then applied to the determination of light microscope images of pollen grains, apparently superior to the statistical methods in three ways: high success rates, small number of samples needed for training, and simplicity of features.

Analysis of Irregularly Shaped Texture Regions

Four different texture classification methods are systematically compared and evaluated with respect to their performance in identifying textures from small and irregular samples, and the best performing method was the 1D sum and difference histogram-based method.

The needs and prospects for automation in palynology

Computer-aided identification of allergenic species of Urticaceae pollen

A computational system to discriminate between genera by using image analysis, based on the definition and computation of digital shape measures on pollen images taken by an optical microscope, which correctly classifies more than 86% of all experiments done.

Textural Features for Image Classification

These results indicate that the easily computable textural features based on gray-tone spatial dependancies probably have a general applicability for a wide variety of image-classification applications.

Object Recognition Using Shape-from-Shading

Investigates whether surface topography information extracted from intensity images using a shape-from-shading (SFS) algorithm can be used for the purposes of 3D object recognition and explores two contrasting object recognition strategies.

Particles shape analysis and classification using the wavelet transform

Application of shape analysis to mammographic calcifications

A set of shape factors to measure the roughness of contours of calcifications in mammograms and for use in their classification as malignant or benign as well as for classification as benign or benign are developed.