Fine-grained visual categorization of butterfly specimens at sub-species level via a convolutional neural network with skip-connections

Lin, Zhongqi; Jia, Jingdun; Gao, Wanlin; Huang, Feng

doi:10.1016/j.neucom.2019.11.033

Cited by 25 publications

(10 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such issue can be observed from the required training time in Tables 5 and 8. Computation penalty is a common phenomenon, which many prior researches (e.g., LLRSE, 70 KCGT, 71 S‐CCNN, 72 and Q‐GAN 73 ) attempt to address. They cautiously sacrifice efficiency for the improvement of precision.…”

Section: Discussionmentioning

confidence: 99%

CapsNet meets ORB: A deformation‐tolerant baseline for recognizing distorted targets

Lin

Gao

Jia

et al. 2021

Int J of Intelligent Sys

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

CapsNet meets ORB: A deformation‐tolerant baseline for recognizing distorted targets

Lin

Gao

Jia

et al. 2021

Int J of Intelligent Sys

Self Cite

View full text Add to dashboard Cite

show abstract

“…Second, the butterfly images utilized in learning are pattern images with evident morphological characters rather than ecological images of butterflies in the wild [24]. Additionally, the evident disparities between two images make it difficult to combine research and manufacturing, and the accuracy rate is low [25]. Many optimization algorithms are also used to solve the various optimization problems [26][27][28][29][30][31][32][33][34][35][36][37][38].…”

Section: Introductionmentioning

confidence: 99%

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

Orban

Vadivel³

et al. 2022

Electronics

View full text Add to dashboard Cite

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.

show abstract

“…The fine-grained image classification method has been widely applied in various classification tasks with the same global structure (such as animals, product brands, and vehicles) [ 30 , 31 , 32 , 33 , 34 , 35 ]. Deconstruction and construction learning (DCL) [ 36 ] is a newly proposed fine-grained classification model and differs from traditional classification methods with significant differences between categories, which aim to extract discriminative features from similar global structures.…”

Section: Introductionmentioning

confidence: 99%

Tool Wear Monitoring in Milling Based on Fine-Grained Image Classification of Machined Surface Images

Yang

Duan

et al. 2022

Sensors

View full text Add to dashboard Cite

Cutting tool wear state assessment during the manufacturing process is extremely significant. The primary purpose of this study is to monitor tool wear to ensure timely tool change and avoid excessive tool wear or sudden tool breakage, which causes workpiece waste and could even damage the machine. Therefore, an intelligent system, that is efficient and precise, needs to be designed for addressing these problems. In our study, an end-to-end improved fine-grained image classification method is employed for workpiece surface-based tool wear monitoring, which is named efficient channel attention destruction and construction learning (ECADCL). The proposed method uses a feature extraction module to extract features from the input image and its corrupted images, and adversarial learning is used to avoid learning noise from corrupted images while extracting semantic features by reconstructing the corrupted images. Finally, a decision module predicts the label based on the learned features. Moreover, the feature extraction module combines a local cross-channel interaction attention mechanism without dimensionality reduction to characterize representative information. A milling dataset is conducted based on the machined surface images for monitoring tool wear conditions. The experimental results indicated that the proposed system can effectively assess the wear state of the tool.

show abstract

Fine-grained visual categorization of butterfly specimens at sub-species level via a convolutional neural network with skip-connections

Cited by 25 publications

References 29 publications

CapsNet meets ORB: A deformation‐tolerant baseline for recognizing distorted targets

CapsNet meets ORB: A deformation‐tolerant baseline for recognizing distorted targets

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

Tool Wear Monitoring in Milling Based on Fine-Grained Image Classification of Machined Surface Images

Contact Info

Product

Resources

About