Fractal analysis of leaf-texture properties as a tool for taxonomic and identification purposes: a case study with species from Neotropical Melastomataceae (Miconieae tribe)

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Cynodon dactylon, Green Couch Grass, Bermuda Grass 'Grand Prix'

‘Grand Prix’ is a selection from a cross between ‘Wintergreen’ and ‘Couch 5’ (also designated C5). ‘Couch 5’ was a selection from an earlier series of crosses by the breeder between ‘Wintergreen’ and a number of Cynodon dactylon accessions, which were collected by the breeder from the Mornington Peninsula area of Victoria between 1986 and 1990. C5 was an experimental breeding line, and was not subsequently reserved as vegetative germplasm. Living material of C5 is no longer in existence. Following the crossing of ‘Couch 5’ and ‘Wintergreen’ in 1998, the resultant seed was germinated on moist blotting paper. Individual seedlings, a total of 150 in number, were planted into 150mm pots and these plants observed during 1998 and 1999. During the summer of 1999-2000, the majority of the seedling plants were culled on the basis of their shoot density, leaf texture, internode length, and colour. In the spring of 2000, the remaining 20 potted seedlings were planted individually into 4m2 plots at the Evergreen Turf farm at Pakenham (Victoria), and allowed to expand fully across these plots. The final selection of Seedling 12 (later designated DN12) in late 2002 was based on shoot density, leaf colour, turf quality, and reduced thatch accumulation as expressed in these plots. Propagation: the original plant has been multiplied through four (4) vegetative expansions prior to PBR application without showing any discernible off types. Breeder: David Nickson, Frankston, VIC. PBR Certificate Number 3133, Application Number 2005/291, granted 12 September 2006.

Cynodon dactylon, Green Couch Grass, Bermuda Grass 'Winter Gem'

‘Winter Gem’ is a selection from a cross between ‘Wintergreen’ and Couch 5 (also designated C5). Couch 5 was a selection from an earlier series of crosses by the breeder between ‘Wintergreen’ and a number of Cynodon dactylon accessions, which were collected by the breeder from the Mornington Peninsula area of Victoria between 1986 and 1990. C5 was an experimental breeding line, and was not subsequently reserved as vegetative germplasm. Living material of C5 is no longer in existence. Following the crossing of Couch 5 and ‘Wintergreen’ in 1998, the resultant seed was germinated on moist blotting paper. Individual seedlings, a total of 150 in number, were planted into 150mm pots and these plants observed during 1998 and 1999. During the summer of 1999-2000, the majority of the seedling plants were culled on the basis of their shoot density, leaf texture, internode length, and colour. In the spring of 2000, the remaining 20 potted seedlings were planted individually into 4m2 plots at the Evergreen Turf farm at Pakenham (Victoria), and allowed to expand fully across these plots. The final selection of Seedling 9 (later designated DN9) in late 2002 was based on shoot density, leaf texture, and retention of winter colour as expressed in these plots. Propagation: The original plant had been multiplied through four (4) vegetative expansions prior to PBR application without showing any discernible off types. Breeder: David Nickson, Frankston, VIC. PBR Certificate Number 3132, Application Number 2005/290, granted 11 September 2006.

Cynodon transvaalensis x Cynodon dactylon, Hybrid Green Couch Grass, Hybrid Bermuda Grass 'P18'

‘P18’ was first produced in 1992 and is a mutant genotype obtained from a hybrid Bermudagrass line believed to be ‘Tifdwarf’, which was grown in a greenhouse owned by H&H Seed Company in Yuma, Arizona. ‘P18’ was selected for its extremely fine leaf texture, its high shoot density under close mowing, its rapid growth rate, and its uniform dark green colour, and was subsequently evaluated for these traits and characteristics. Propagation: vegetative. Breeder: Howard E. Kaewer, Eden Prairie, MN, USA. PBR Application Number 2007/179, Certificate Number 3567, granted 13 August 2007.

Paspalum vaginatum Swartz, Seashore Paspalum 'SI98'

‘SI98’ was selected from a worldwide collection of 300 accessions of seashore paspalum collected by Dr Ronny R. Duncan, primarily from seashore paspalum plantings on golf courses as variants in growth habit, leaf texture, and level of salt tolerance, having potential for improved turf type selections. ‘SI98’ was selected as a finer textured genotype with a denser, more prostrate growth habit than the surrounding wild ecotype. The original samples were vegetatively propagated and evaluated first in the greenhouse at Griffin, GA, USA, and later expanded to field evaluations at Griffith under mowing heights ranging from 4.8 mm to 50 mm. Extensive further evaluations were undertaken between 2002 and 2007. Breeder: Dr Ronny R. Duncan, University of Georgia, Griffin, GA, USA. PBR Certificate Number 3648, Application Number 2008/073, granted 16 December 2008.

MORPHOLOGICAL DIVERSITY OF MANGO GERMPLASM FROM THE UPPER ATHI RIVER REGION OF EASTERN KENYA: AN ANALYSIS BASED ON NON- FRUIT DESCRIPTORS

Phenotypic variation in plants can be evaluated by morphological characterization using visual attributes. Fruits have been the major descriptors for identification of different varieties of fruit crops. However, even in their absence, farmers, breeders and interested stakeholders require to distinguish between different mango varieties. This study aimed at determining diversity in mango germplasm from the Upper Athi River (UAR) and providing useful alternative descriptors for the identification of different mango varieties in the absence of fruits. A total of 20 International Plant Genetic Resources Institute (IPGRI) descriptors for mango were selected for use in the visual assessment of 98 mango accessions from 15 sites of the UAR region of eastern Kenya. Purposive sampling was used to identify farmers growing diverse varieties of mangoes. Evaluation of the descriptors was performed on-site and the data collected were then subjected to multivariate analysis including Principal Component Analysis (PCA) and Cluster analysis, one- way analysis of variance (ANOVA) and Chi square tests. Results classified the accessions into two major groups corresponding to indigenous and exotic varieties. The PCA showed the first six principal components accounting for 75.12% of the total variance. A strong and highly significant correlation was observed between the color of fully grown leaves, leaf blade width, leaf blade length and petiole length and also between the leaf attitude, color of young leaf, stem circumference, tree height, leaf margin, growth habit and fragrance. Useful descriptors for morphological evaluation were 14 out of the selected 20; however, ANOVA and Chi square test revealed that diversity in the accessions was majorly as a result of variations in color of young leaves, leaf attitude, leaf texture, growth habit, leaf blade length, leaf blade width and petiole length traits. These results reveal that mango germplasm in the UAR has significant diversity and that other morphological traits apart from fruits can be useful in morphological characterization of mango.

Measuring and analyzing color and texture information in anatomical leaf cross sections: An approach using computer vision to aid plant species identification

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Combining Leaf Shape and Texture for Costa Rican Plant Species Identification

In the last decade, research in Computer Vision has developed several algorithms to help botanists and non-experts to classify plants based on images of their leaves. LeafSnap is a mobile application that uses a multiscale curvature model of the leaf margin to classify leaf images into species. It has achieved high levels of accuracy on 184 tree species from Northeast US. We extend the research that led to the development of LeafSnap along two lines. First, LeafSnap’s underlying algorithms are applied to a set of 66 tree species from Costa Rica. Then, texture is used as an additional criterion to measure the level of improvement achieved in the automatic identification of Costa Rica tree species. A 25.6% improvement was achieved for a Costa Rican clean image dataset and 42.5% for a Costa Rican noisy image dataset. In both cases, our results show this increment as statistically significant. Further statistical analysis of visual noise impact, best algorithm combinations per species, and best value of , the minimal cardinality of the set of candidate species that the tested algorithms render as best matches is also presented in this research

PLANT LEAF IDENTIFICATION BASED ON VOLUMETRIC FRACTAL DIMENSION

Texture is an important visual attribute used to describe the pixel organization in an image. As well as it being easily identified by humans, its analysis process demands a high level of sophistication and computer complexity. This paper presents a novel approach for texture analysis, based on analyzing the complexity of the surface generated from a texture, in order to describe and characterize it. The proposed method produces a texture signature which is able to efficiently characterize different texture classes. The paper also illustrates a novel method performance on an experiment using texture images of leaves. Leaf identification is a difficult and complex task due to the nature of plants, which presents a huge pattern variation. The high classification rate yielded shows the potential of the method, improving on traditional texture techniques, such as Gabor filters and Fourier analysis.

Plant Leaf Identification Using Gabor Wavelets

This article presents a novel method of plant classification using Gabor wavelet filters to extract texture filters in a foliar surface. The aim of this promising method is to add to the results obtained by other leaf attributes (such as shape, contour, color, among others), increasing, therefore, the percentage of classification of plant species. To corroborate the efficiency of the technique, an experiment using 20 species from Brazilian flora was done and discussed. The results are also compared with texture Fourier descriptors and cooccurrence matrices. (C) 2009 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 19, 236-243, 2009; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/ima.20201

A computer vision approach to quantify leaf anatomical plasticity: A case study on gochnatia polymorpha (less.) cabrera

Inferences about leaf anatomical characteristics had largely been made by manually measuring diverse leaf regions, such as cuticle, epidermis and parenchyma to evaluate differences caused by environmental variables. Here we tested an approach for data acquisition and analysis in ecological quantitative leaf anatomy studies based on computer vision and pattern recognition methods. A case study was conducted on Gochnatia polymorpha (Less.) Cabrera (Asteraceae), a Neotropical savanna tree species that has high phenotypic plasticity. We obtained digital images of cross-sections of its leaves developed under different light conditions (sun vs. shade), different seasons (dry vs. wet) and in different soil types (oxysoil vs. hydromorphic soil), and analyzed several visual attributes, such as color, texture and tissues thickness in a perpendicular plane from microscopic images. The experimental results demonstrated that computational analysis is capable of distinguishing anatomical alterations in microscope images obtained from individuals growing in different environmental conditions. The methods presented here offer an alternative way to determine leaf anatomical differences. © 2013 Elsevier B.V.

Texture for Script identification

The problem of determining the script and language of a document image has a number of important applications in the field of document analysis, such as indexing and sorting of large collections of such images, or as a precursor to optical character recognition (OCR). In this paper, we investigate the use of texture as a tool for determining the script of a document image, based on the observation that text has a distinct visual texture. An experimental evaluation of a number of commonly used texture features is conducted on a newly created script database, providing a qualitative measure of which features are most appropriate for this task. Strategies for improving classification results in situations with limited training data and multiple font types are also proposed.