Variability of morphological traits in sunflower inbred lines

Except agronomic important traits, great diversity in sunflower is present in morphological traits which are very useful in breeding studies. The main objective of the paper was to determine genetic diversity among the 110 inbred lines in the collection of Institute of Field and Vegetable Crops Novi Sad (IFVCNS) by screening 34 morphological traits according to a list of descriptors of the International Union for the Protection of New Varieties of Plants (UPOV) as to conduct the Distinctness, Uniformity and Stability Test (DUS). The diversity of morphological traits was estimated by Shannon diversity index (H?) and the diversity of sunflower inbred lines was performed by homogeneity analysis (HOMALS) as well as discriminatory power of the traits. The values of the traits in Shannon diversity index were the highest (H?=0.99) for height of the tip of the blade compared to insertion of petiole and bract position, while branching, head shape and seed color showed low diversity (H?>0.1). The uniformity of inbred lines distribution determined discriminative power of descriptors. Disk flower anthocyanin coloration of stigma, hypocotyl anthocyanin coloration and intensity, leaf blistering, leaf serration, seed stripes on and between the margins showed the strongest discriminatory power. According to these six traits, the collection of inbred lines was divided into two main groups and three subgroups which better explained the relationships among the various inbred lines. Inbred lines showed the great variability of morphological traits in the whole collection and also among the inbred lines from the same type of use.

Flower Identification and Classification using Computer Vision and Machine Learning Techniques

Computer vision techniques plays an important role in extracting meaningful information from images. A process of extraction, analysis, and understanding of information from images may accomplished by an automated process using computer vision and machine learning techniques. The paper proposed a hybrid methodology using MKL – SVM with multi-label classification that is experimented on a dataset contained 25000 flower images of 102 different spices. Basic and morphology features including color, size, texture, petal type, petal count, disk flower, corona, aestivation of flower and flower class are extracted to increase the classification accuracy. Various classifiers are applied on extracted feature set and their performance are discussed. The result of MKL – SVM with multi-label classification is very promising with 76.92% as an accuracy rate. In brief, this paper attempts to explore a novel morphology for feature extraction and the applicability of symbolic representation schemes along with different classification strategies for effective multi-label classification of flower spices

Interrelationship of pollination conditions, fertilization and sunflower seed yield

Four commercially important sunflower hybrids (NS-H-45, NS-H-l 11, NS-H-702 and Velja) and their parental components (Ha-74B, Ha-98B, CMS-3-8B, Ha-26B, RHA-583, RHA-R-PI-2/1 and RHA-113N) were used over a period of two years to study the following traits: disk flower corolla length, nectar content, pollen viability, bee visitation, fertilization percentage and seed yield. Relations among the traits were determined by path coefficient analysis. The simple correlation coefficients showed that fertilization percentage and bee visitation had a highly significant influence on seed yield. The corolla length had a positive effect on nectar content, while nectar content had a significant negative influence on pollen viability. The highest significant direct influence on seed yield was that of fertilization percentage, while the effect on nectar content on seed yield was negative but not significant. The coefficient of determination was 0.8071.