A Novel Method for the Classification of Butterfly Species Using Pre-Trained CNN Models

Abstract

In comparison to the competitors, engineers must provide quick, low-cost, and dependable solutions. The advancement of intelligence generated by machines and its application in almost every field has created a need to reduce the human role in image processing while also making time and labor profit. Lepidopterology is the discipline of entomology dedicated to the scientific analysis of caterpillars and the three butterfly superfamilies. Students studying lepidopterology must generally capture butterflies with nets and dissect them to discover the insect’s family types and shape. This research work aims to assist science students in correctly recognizing butterflies without harming the insects during their analysis. This paper discusses transfer-learning-based neural network models to identify butterfly species. The datasets are collected from the Kaggle website, which contains 10,035 images of 75 different species of butterflies. From the available dataset, 15 unusual species were selected, including various butterfly orientations, photography angles, butterfly lengths, occlusion, and backdrop complexity. When we analyzed the dataset, we found an imbalanced class distribution among the 15 identified classes, leading to overfitting. The proposed system performs data augmentation to prevent data scarcity and reduce overfitting. The augmented dataset is also used to improve the accuracy of the data models. This research work utilizes transfer learning based on various convolutional neural network architectures such as VGG16, VGG19, MobileNet, Xception, ResNet50, and InceptionV3 to classify the butterfly species into various categories. All the proposed models are evaluated using precision, recall, F-Measure, and accuracy. The investigation findings reveal that the InceptionV3 architecture provides an accuracy of 94.66%, superior to all other architectures.

New trends in detection of harmful insects and pests in modern agriculture using artificial neural networks. a review

“…Although there are several public databases illustrating and grouping various common classes of insect pests, most of the authors used their own datasets in solving the problems specific (Bhoi et al, 2021;Rajeena et al, 2022). Creating proprietary databases for insect pest detection or monitoring using NNs can help improve the accuracy and specificity of pest detection systems, while also providing flexibility and cost-effectiveness (Segalla et al, 2020;Hong et al, 2021).…”

“…Classification ACC: 75.3% -99.04% mAP: 71% (Ayan et al, 2020), (Fang et al, 2020), (Hansen et al, 2019), (Rajeena et al, 2022), (Sanghavi et al, 2022), (Singh et al, 2021), , (Liu et al, 2022) Inception ResNetv2 Detection ACC: 91.14% (Khanramaki et al, 2021), (Singh et al, 2021) LeNet et al, 2021), (Hong et al, 2021), (Nanni et al, 2022), (Rajeena et al, 2022), (Xing et al, 2019) (Ahmad et al, 2021), (Alsanea et al, 2022), (Butera et al, 2021), (Du et al, 2022), (Guo et al, 2021), (Hong et al, 2021), (Li et al, 2019), (Liu et al, 2019), (Wang et al, 2022), (Shi et (Butera et al, 2021), (De Cesaro Juńior et al, 2022), (Fang et al, 2020), (Dai et al, 2021), (Khanramaki et al, 2021), (Li et al, 2019), (Liu et al, 2019), (Liu et al, 2022), (Malathi and Gopinath, 2021), (Nanni et al, 2022), (Rajeena et al, 2022), (Sanghavi et al, 2022), , (Wang et al, 2022), (Xu et al, 2022) ResNet 53 Detection mAP: 77.29% (Lv et al, 2022) ResNet 101 Detection mAP: 85.53% -99.5%…”

“…(Segalla et al, 2020), (Wang et al, 2022), (Shi et al, 2020) VGG19 Classification ACC: 74.07% -99.02% (Ayan et al, 2020), (Fang et al, 2020), (Rajeena et al, 2022), (Singh et The graph of the evolution in the last three years of the most used neural networks.…”

ML-DDoSnet: IoT Intrusion Detection Based on Denial-of-Service Attacks Using Machine Learning Methods and NSL-KDD

“…Li et al [77] proposed a novel neural network architecture for encoding and synthesizing 3D shapes. The authors discussed transfer learning-based neural network models for the identification of butterfly species in Rajeena et al [78]. Ghayvat et al suggested a strategy that combines a blockchainbased nondisclosure method with a two-step authentication architecture and an elliptic curve cryptography-based cryptographic signature framework.…”

Investigation of Applying Machine Learning and Hyperparameter Tuned Deep Learning Approaches for Arrhythmia Detection in ECG Images

“…Image classification is the process of categorizing images into one of several predetermined categories. A single image can be classified into an endless number of categories [1]. Manually evaluating and classifying these images can be time-consuming, especially when there are a big number of them; therefore, automating the process using machine learning and deep learning techniques would be quite beneficial.…”