---

 Inter Simple Sequence Repeat (ISSR) markers were used to assess the genetic diversity among 23 outcross and self pollinated populations of fennel collected from different geographical regions of Iran and some European countries. The experiment was carried out to determine the effect of self-pollination on morphological traits and genetic diversity in the next generation. Fifteen primers produced 248 polymorphic bands with an average of 16.53 fragments per primer in outcross populations, while 217 polymorphic fragments with an average of 14.46 fragments per primer were generated in self-pollinated populations. UPGMA dendrogram using Jaccard’s similarity coefficients placed outcross populations in five major groups. The maximum and minimum gene diversity over loci was observed in Albania (0.53) and Poland (0.42) populations, respectively. In general, European fennel populations revealed higher expected heterozygosity (0.47) in comparison with Iranian ones (0.35). Polymorphism Information Content (PIC) ranged from 0.37 to 0.49 in self-pollinated populations, while it varied from 0.39 to 0.46 in out-cross ones. The classification based on morphological data did not confirm the molecular ones in most cases. Self-pollination led to decline in plant height in most of the studied populations. In overall, plant height of the European populations (54-66.02 cm) was less than that of Iranian ones (55-109.54 cm). Self-pollination elevated the yield of essential oil in studied fennels through its influence on fruit set. In conclusion, Albania population had the highest oil content affected by self-pollination; hence, it can be introduced as one of the valued sources in fennel breeding programs aimed for oil yield improvement.

---

Micromorphological characteristics of seed sculpturing might be effective in circumscribing the infra-specific taxa in the genus Vicia. The present study was conducted to determine whether microstructural and seed coat texture data obtained from SEM images can serve as sufficient tools for delimiting Vicia genus. Other than visual inspections, a variety of texture-based methods, including the four conventional approaches of GLCM, LBP, LBGLCM, and SFTA, and the four pre-trained convolutional neural networks, namely, ResNet50, VGG16, VGG19, and Xception models were employed to extract features and to classify the species of Vicia genus using SEM images. In a subsequent step, the four unsupervised k-means, Mean-shift, agglomerative, and Gaussian mixture classification methods were used to group the identified Vicia spices based on the underlying features thus extracted. Moreover, the three supervised classifiers of Multilayer Perceptron Network (MLP), Support Vector Machine (SVM), and k-Nearest Neighbor (kNN) were compared in terms of capability in discriminating the different visually-identified classes. SEM results showed that three classes might be identified based on the micromorphological character-species connections and that the differences among the species in the Vicia genus and the validity of Vicia sativa could be confirmed. Regarding the performance of the classifiers, SFTA textural descriptor outperformed the GLCM, LBP, and LBGLCM algorithms, but yielded a decreased accuracy compared with deep learning models. The combined Xception model and a MLP classifier was successful to discriminate the species in the Vicia genus with the best classification performances of 99 and 96% in training and testing, respectively.