Automated pollen identification using microscopic imaging and texture analysis. (January 2015)

• Record Type: Journal Article
• Authors: Marcos, J. Víctor; Nava, Rodrigo; Cristóbal, Gabriel; Redondo, Rafael; Escalante-Ramírez, Boris; Bueno, Gloria; Déniz, Óscar; González-Porto, Amelia; Pardo, Cristina; Chung, François; Rodríguez, Tomás
• Is Part Of: Micron. Volume 68(2015:Jan.)
• Page Start: 36
• Page End: 46
• Publication Date: 2015-01
• Subjects: Texture analysis -- Pollen identification -- Gray-level co-occurrence matrix -- Log-Gabor filters -- Local binary patterns -- Discrete Tchebichef moments; Microscopy -- Periodicals; Electron Probe Microanalysis -- Periodicals; Microscopy -- Periodicals; Microscopie -- Périodiques; Microscopy; Periodicals; 502.82
• DOI: 10.1016/j.micron.2014.09.002
• Languages: English
• ISSNs: 0968-4328

Abstract

Abstract : Highlights: Pollen texture plays a crucial role in automatic identification of the taxon. A database with 1800 pollen samples from 15 taxa was analysed. The best texture descriptors were related to spectral properties of pollen images. The combination of uncorrelated texture features resulted in improved performance. A classification accuracy up to 95% was achieved from texture analysis of pollen. Abstract: Pollen identification is required in different scenarios such as prevention of allergic reactions, climate analysis or apiculture. However, it is a time-consuming task since experts are required to recognize each pollen grain through the microscope. In this study, we performed an exhaustive assessment on the utility of texture analysis for automated characterisation of pollen samples. A database composed of 1800 brightfield microscopy images of pollen grains from 15 different taxa was used for this purpose. A pattern recognition-based methodology was adopted to perform pollen classification. Four different methods were evaluated for texture feature extraction from the pollen image: Haralick's gray-level co-occurrence matrices (GLCM), log-Gabor filters (LGF), local binary patterns (LBP) and discrete Tchebichef moments (DTM). Fisher's discriminant analysis and k -nearest neighbour were subsequently applied to perform dimensionality reduction and multivariate classification, respectively. Our results reveal that LGF and DTM, which are based on the spectral properties of the image, outperformed GLCM and LBP in the proposed classification problem. Furthermore, we found that the combination of all the texture features resulted in the highest performance, yielding an accuracy of 95%. Therefore, thorough texture characterisation could be considered in further implementations of automatic pollen recognition systems based on image processing techniques.