Butterfly Species Identification Using Convolutional Neural Network (CNN)

Arzar, Nur Nabila Kamaron; Sabri, Nurbaity; Johari, Nur Farahin Mohd; Shari, Anis Amilah; Noordin, Mohd Rahmat Mohd; Ibrahim, Shafaf

doi:10.1109/i2cacis.2019.8825031

Cited by 11 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While CNNs have been used in the past for purposes of butterfly species identification [18][19][20][21][22], they have not been used to identify specific wing patterns, such as spots and eyespots, regardless of species identity.…”

Section: Introductionmentioning

confidence: 99%

Detection and measurement of butterfly eyespot and spot patterns using convolutional neural networks

Cunha

Narotamo²,

Monteiro³

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

Butterflies are increasingly becoming model insects where basic questions surrounding the diversity of their color patterns are being investigated. Some of these color patterns consist of simple spots and eyespots. To accelerate the pace of research surrounding these discrete and circular pattern elements we trained distinct convolutional neural networks (CNNs) for detection and measurement of butterfly spots and eyespots on digital images of butterfly wings. We compared the automatically detected and segmented spot/eyespot areas with those manually annotated. These methods were able to identify and distinguish marginal eyespots from spots, as well as distinguish these patterns from less symmetrical patches of color. In addition, the measurements of an eyespot’s central area and surrounding rings were comparable with the manual measurements. These CNNs offer improvements of eyespot/spot detection and measurements relative to previous methods because it is not necessary to mathematically define the feature of interest. All that is needed is to point out the images that have those features to train the CNN.

show abstract

Section: Introductionmentioning

confidence: 99%

Detection and measurement of butterfly eyespot and spot patterns using convolutional neural networks

Cunha

Narotamo²,

Monteiro³

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…The overall performance of the CNN model achieved an accuracy of approximately 88%. Another study by [22] proposed the GoogleLeNet architecture to classify four types of butterflies. The researchers utilized a dataset comprising 600 butterfly images with dimensions of 224×224 pixels, dividing it into 80% for training and 20% for testing.…”

Section: Related Workmentioning

confidence: 99%

“…The performance of the proposed method appears to be the most superior, where it is 98.49% and 99.43%, respectively, for the recognition of 15 and 100 classes. Even though the advantages seem insignificant compared to models [22], [23] these two models each only recognize a small number of classes, namely 4 and 10. Whereas Model [13] and proposed Model 1 used 15 classes, and proposed Model 1 excelled at more than 4%.…”

Section: 𝐴𝑐𝑐𝑢𝑟𝑎𝑐𝑦 = 𝑇𝛲 + 𝑇𝛮 𝑇𝛲 + 𝐹𝛮 + 𝐹𝛲 + 𝑇𝛮mentioning

confidence: 99%

“…Conventionally, research on butterfly identification has predominantly focused on a limited number of classes. For instance, one study [22] proposed the GoogleLeNet architecture to classify four types of butterflies and obtained an accuracy of 97.5% based on the test results. Similarly, another study [23] proposed a VGG-16 CNN model to identify ten butterfly species and achieved a high accuracy of 97%.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Butterflies Recognition using Enhanced Transfer Learning and Data Augmentation

Adityawan,

Farroq,

Santosa

et al. 2023

J. Comput. Theor. Appl.

View full text Add to dashboard Cite

Butterflies’ recognition serves a crucial role as an environmental indicator and a key factor in plant pollination. The automation of this recognition process, facilitated by Convolutional Neural Networks (CNNs), can expedite this task. Several pre-trained CNN models, such as VGG, ResNet, and Inception, have been widely used for this purpose. However, the scope of previous research has been somewhat constrained, focusing only on a maximum of 15 classes. This study proposes to modify the CNN InceptionV3 model and combine it with three data augmentations to recognize up to 100 butterfly species. To curb overfitting, this study employs a series of data augmentation techniques. In parallel, we refine the InceptionV3 model by reducing the number of layers and integrating four new layers. The test results demonstrate that our proposed model achieves an impressive accuracy of 99.43% for 15 classes with only 10 epochs, exceeding prior models by approximately 5%. When extended to 100 classes, the model maintains a high accuracy rate of 98.49% with 50 epochs. The proposed model surpasses the performance of standard pre-trained models, including VGG16, ResNet50, and InceptionV3, illustrating its potential for broader application.

show abstract

“…CNNs are currently the most widely used deep learning algorithms for image analysis, having outperformed traditional algorithms in many image analysis problems like image classification, object detection or segmentation [16,17]. While CNNs have been used in the past for purposes of butterfly species identification [18][19][20][21][22], here we use them to identify specific wing patterns, regardless of species identity. The main advantage of CNNs over previous methods is their ability to automatically extract from the images the most relevant features of the patterns of our choice, in this case spots and eyespots, requiring no manual feature extraction.…”

Section: Introductionmentioning

confidence: 99%

Detection and measurement of butterfly eyespot and spot patterns using convolutional neural networks

Cunha

Monteiro

Silveira

2022

Preprint

View full text Add to dashboard Cite

Butterflies are increasingly becoming model insects where basic questions surrounding the diversity of their color patterns are being investigated. Some of these color patterns consist of simple spots and eyespots. To accelerate the pace of research surrounding these discrete and circular pattern elements we developed two distinct convolutional neural networks (CNNs) for detection and measurement of butterfly spots and eyespots on digital images of butterfly wings. We tested the accuracy of the detection and of the area measurements using manual identifications and measurements. These methods were able to identify and distinguish marginal eyespots from spots, as well as distinguish these patterns from less symmetrical patches of color. In addition, the measurements of an eyespot's central area and surrounding rings were highly accurate. These CNNs offer improvements of eyespot/spot detection and measurements relative to previous methods because it is not necessary to mathematically define the feature of interest. All that is needed is to point out the images that have those features to train the CNN.

show abstract

Butterfly Species Identification Using Convolutional Neural Network (CNN)

Cited by 11 publications

References 7 publications

Detection and measurement of butterfly eyespot and spot patterns using convolutional neural networks

Detection and measurement of butterfly eyespot and spot patterns using convolutional neural networks

Butterflies Recognition using Enhanced Transfer Learning and Data Augmentation

Detection and measurement of butterfly eyespot and spot patterns using convolutional neural networks

Contact Info

Product

Resources

About