Search results for: Sivaram Annadurai

Authors: Virender Singh, Mathew Rees, Simon Hampton, Sivaram Annadurai

Abstract:

Plant identification is a challenging task that aims to identify the family, genus, and species according to plant morphological features. Automated deep learning-based computer vision algorithms are widely used for identifying plants and can help users narrow down the possibilities. However, numerous morphological similarities between and within species render correct classification difficult. In this paper, we tested custom convolution neural network (CNN) and vision transformer (ViT) based models using the PyTorch framework to classify plants. We used a large dataset of 88,000 provided by the Royal Horticultural Society (RHS) and a smaller dataset of 16,000 images from the PlantClef 2015 dataset for classifying plants at genus and species levels, respectively. Our results show that for classifying plants at the genus level, ViT models perform better compared to CNN-based models ResNet50 and ResNet-RS-420 and other state-of-the-art CNN-based models suggested in previous studies on a similar dataset. ViT model achieved top accuracy of 83.3% for classifying plants at the genus level. For classifying plants at the species level, ViT models perform better compared to CNN-based models ResNet50 and ResNet-RS-420, with a top accuracy of 92.5%. We show that the correct set of augmentation techniques plays an important role in classification success. In conclusion, these results could help end users, professionals and the general public alike in identifying plants quicker and with improved accuracy.

Keywords: plant identification, CNN, image processing, vision transformer, classification

Procedia PDF Downloads 60

Authors: Venkatesan Annadurai, Kannan Ethirajalu, Anu Roshini Ramakrishnan

Abstract:

Copper oxide (CuO) and zinc oxide (ZnO) based coaxial (CuO-ZnO nanorods) heterojunction has been the interest of various research communities for solar cells, light emitting diodes (LEDs) and photodetectors applications. Copper oxide (CuO) is a p-type material with the band gap of 1.5 eV and it is considered to be an attractive absorber material in solar cells applications due to its high absorption coefficient and long minority carrier diffusion length. Similarly, n-type ZnO nanorods possess many attractive advantages over thin films such as, the light trapping ability and photosensitivity owing to the presence of oxygen related hole-traps at the surface. Moreover, the abundant availability, non-toxicity, and inexpensiveness of these materials make them suitable for potentially cheap, large area, and stable photovoltaic applications. However, the efficiency of the CuO-ZnO nanorods heterojunction based devices is greatly affected by interface defects which generally lead to the poor performance. In spite of having much potential, not much work has been carried out to understand the interface quality and transport mechanism involved across the CuO-ZnO nanorods heterojunction. Therefore, a detailed investigation of CuO-ZnO heterojunction is needed to understand the interface which affects its photovoltaic performance. Herein, we have fabricated the CuO-ZnO nanorods based heterojunction by simple hydrothermal and electrodeposition technique and investigated its interface quality by carrying out temperature (300 –10 K) dependent current-voltage (I-V) measurements under dark and illumination of visible light. Activation energies extracted from the temperature dependent I-V characteristics reveals that recombination and tunneling mechanism across the interfacial barrier plays a significant role in the current flow.

Keywords: heterojunction, electrical transport, nanorods, solar cells

Procedia PDF Downloads 194