Automatic Identification of Ivorian Plants from Herbarium Specimens using Deep Learning

Abstract

— Plant identification is most often based on visual observations by botanists and systematists. Deep learning has become a tool that provides an alternative to automatic plant identification. Our study consists in implementing a method for plant recognition from herbarium specimens using deep learning classification methods. These methods were evaluated on the dataset of ten plant families from the national herbarium of Côte d'Ivoire. The proposed work uses CNN architectures such as DensNet-121, InceptionV3, VGG19, MobileNet, and ResNet101. The dataset contains 7543 images of herbarium specimens. The database is structured in three parts: training, testing, and validation. The accuracies obtained for the first scenario without preprocessing of herbarium specimen images are 76.94% for MobileNet, 77.77% for VGG19, and 77.96% for InceptionV3, 80.41% for ResNet101, and 83.47% for DensNet-121, respectively. The best performance was obtained with DensNet-121 with 83.47%. In the second scenario with preprocessing of herbarium specimens, the accuracies obtained were 82.80% for InceptionV3, 84.40% for VGG19, 85.53% for MobileNet, and 85.80% for ResNet101. The best accuracy was obtained with ResNet121 with 85.80%. From the analysis obtained, the results show that ResNet101 gives the best accuracy compared to the other architectures. In particular, the data preprocessing improves the prediction results, of the Convolutional Neural Network algorithms. Keywords— Deep learning, Herbarium specimens, image preprocessing, Convolutional Neural Network, Classification.

Cocoa Pods Diseases Detection by MobileNet Confluence and Classification Algorithms

“…MobileNet V2 has been designed for mobile devices such as smartphones and tablets. It can achieve performance comparable to larger models while being much lighter and more energy-efficient [24]. The bottleneck convolution block is a convolution block [25] that reduces the width and height of the input signal while retaining the depth.…”

An Adaptive Technique for Underwater Image Enhancement with CNN and Ensemble Classifier

“…To determine these issues, a sharp two-stage submerged picture convolutional neural net (CNN) along with structure decomposition is taken into account for submerged picture improvement. Specifically, the rough submerged picture is rotted into high-repeat and low-repeat reliant upon theoretical examination of the submerged imaging [4][5][6][7]. To additionally work on the brilliance and differentiation of submerged pictures, a histogram extending calculation in light of the red channel is given [9,13].…”