GRASP-125: A Dataset for Greek Vascular Plant Recognition in Natural Environment

Abstract

Plant identification from images has become a rapidly developing research field in computer vision and is particularly challenging due to the morphological complexity of plants. The availability of large databases of plant images, and the research advancements in image processing, pattern recognition and machine learning, have resulted in a number of remarkably accurate and reliable image-based plant identification techniques, overcoming the time and expertise required for conventional plant identification, which is feasible only for expert botanists. In this paper, we introduce the GReek vAScular Plants (GRASP) dataset, a set of images composed of 125 classes of different species, for the automatic identification of vascular plants of Greece. In this context, we describe the methodology of data acquisition and dataset organization, along with the statistical features of the dataset. Furthermore, we present results of the application of popular deep learning architectures to the classification of the images in the dataset. Using transfer learning, we report 91% top-1 and 98% top-5 accuracy.

Sustainable Ecotourism through Cutting-Edge Technologies

“…The research for the creation of the vascular-plants digital resource for the mountains of Oiti and Parnassus resulted in a new image dataset that was published under the name GRASP-125 [35]. The GRASP-125 dataset (The Greek Vascular Plants GRASP-125 dataset, http://advent.athenarc.gr/grasp/, accessed on 20 December 2021) was composed of 125 classes of different species of vascular plants.…”

“…Several popular Convolutional Neural Network (CNN) architectures were used for the task, using the transfer learning approach. [35] reported in detail on the performance of each of the tested architectures and on the explainability of the outcomes, using SmoothGrad [41] and Grad-CAM++ [42]. The attained performance results for the classification of the GRASP-125 dataset are summarised to a 92% top-1 and 98% top-5 accuracy.…”

Leveraging Positive-Unlabeled Learning for Enhanced Black Spot Accident Identification on Greek Road Networks

“…As Industry 4.0 progresses, there is a growing reliance on automated systems for inspection to ensure defects are identified instantly, guaranteeing that only the finest quality products reach the consumers [62]. Nevertheless, the acquisition of extensive labeled datasets to train defect detection models that are precise poses a substantial hurdle [63]. The process of manually labeling is not only tedious and costly [64][65][66] but inaccuracies in labeling can also severely impact the performance of the resulting model [67,68].…”

FTIDB: a new flue-cured tobacco leaf image database

“…The database classified the images into six different groups based on their status: healthy leaves, early leaf spot, late leaf spot, nutrient deficiency, rust spot, and early rust spot 9 . Kosmas Kritsis et al introduced the Greek Vascular Plant database (GRASP), which consisted of images of 125 different species of Greek vascular plants for the automatic identification of Greek vascular plants 10 . By enhancing theoretical research, innovating image processing methods, and advancing the development of image processing techniques, the construction of image database will progress towards a more standardized and efficient direction.…”