An Improved Transfer-Learning for Image-Based Species Classification of Protected Indonesians Birds

Yang, Chao-Lung; Harjoseputro, Yulius; Hu, Yu‐Chen; Chen, Yung-Yao

doi:10.32604/cmc.2022.031305

Cited by 8 publications

(4 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, two dense layers were placed after the flattening process, and the probability value used for evaluating the modified CNN architectures is p = 0.2 [ 43 ]. The dropout technique prevents overfitting problems due to limited datasets [ 17 , 44 ].…”

Section: Methodsmentioning

confidence: 99%

“…The transfer learning method is a better solution for image recognition compared to training a network with millions of parameters or developing new paradigms from scratch [ 11 ]. Several research works have recently applied transfer learning to some pretrained CNNs, such as VGG [ 12 , 13 , 14 ], Res-Net [ 15 ], GoogLeNet, Inception [ 16 ], MobileNet [ 17 ], AlexNet [ 18 , 19 , 20 ], and DenseNet [ 21 ]. Fine-tuning a pretrained model for a new task is an efficient transfer method to fill the various knowledge transfer gaps for CNN models [ 22 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Content-Based Image Retrieval for Traditional Indonesian Woven Fabric Images Using a Modified Convolutional Neural Network Method

Tena,

Hartanto,

Ardiyanto

2023

J. Imaging

View full text Add to dashboard Cite

A content-based image retrieval system, as an Indonesian traditional woven fabric knowledge base, can be useful for artisans and trade promotions. However, creating an effective and efficient retrieval system is difficult due to the lack of an Indonesian traditional woven fabric dataset, and unique characteristics are not considered simultaneously. One type of traditional Indonesian fabric is ikat woven fabric. Thus, this study collected images of this traditional Indonesian woven fabric to create the TenunIkatNet dataset. The dataset consists of 120 classes and 4800 images. The images were captured perpendicularly, and the ikat woven fabrics were placed on different backgrounds, hung, and worn on the body, according to the utilization patterns. The feature extraction method using a modified convolutional neural network (MCNN) learns the unique features of Indonesian traditional woven fabrics. The experimental results show that the modified CNN model outperforms other pretrained CNN models (i.e., ResNet101, VGG16, DenseNet201, InceptionV3, MobileNetV2, Xception, and InceptionResNetV2) in top-5, top-10, top-20, and top-50 accuracies with scores of 99.96%, 99.88%, 99.50%, and 97.60%, respectively.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Content-Based Image Retrieval for Traditional Indonesian Woven Fabric Images Using a Modified Convolutional Neural Network Method

Tena,

Hartanto,

Ardiyanto

2023

J. Imaging

View full text Add to dashboard Cite

show abstract

“…Yang et al [2] developed an enhanced transfer-learning bird classification model for attaining the accurate categorization of Protected Indonesia Birds (PIB) which has been detected as an endangered bird species. To detect the protected animals, it failed to detect the designed series of BNDFC layers.…”

Section: Related Workmentioning

confidence: 99%

Deep Convolutional Neural Network for Automated Bird Species Classification

Gavali,

Saira Banu

2024

View full text Add to dashboard Cite

Birds significantly contribute to ecosystem maintenance, involving seed dispersion, air oxygenation, contaminant conversion into nutrients, and climate regulation. However, with over ten thousand bird species described globally, accurate identification based solely on their appearances poses a challenge, even for experienced bird watchers, leading to potential discrepancies in species classification. This difficulty highlights the challenges that both human intelligence and artificial intelligence encounter when accurately identifying bird species. To address this challenge, we propose an automatic bird species classification system using deep learning techniques. Our study leverages the power of deep learning in computer vision to assist novice bird enthusiasts in accurately identifying the plethora of bird species they encounter. We gathered and utilized a diverse dataset of bird images to train a convolutional neural network (CNN) model. Our classification system, developed through training and careful evaluation has shown accuracy, in identifying different bird species using images. This system serves as a tool in real world situations allowing bird enthusiasts to gain an appreciation for the diverse range of avian species and actively contribute to conservation efforts. Our classification system, which has been extensively trained and thoroughly evaluated has proven to be highly accurate, in identifying bird species based on images. It provides a tool for bird enthusiasts to truly appreciate the range of avian species and contribute to conservation efforts. Our research introduces an efficient approach, based on learning for automatically classifying bird species from images. This addresses the challenges faced by both experts and non experts in identifying birds. Our designed deep convolutional neural network (DCNN) achieved an accuracy rate of 92% ensuring precise recognition of various species. This system plays a role in preserving and comprehending bird ecosystems emphasizing their contribution, to maintaining global landscapes and climate stability.

show abstract

“…Classification operates as a supervised learning procedure, relying on training sets derived from historical data. Key performance metrics in classification tasks encompass precision, recall, accuracy, and the F1-score [15]. It is defined as the fraction of true positives over the sum of true positives and false negatives.…”

Section: Performance Evaluationmentioning

confidence: 99%

Transforming Woven Ikat Fabric: Advanced Classification via Transfer Learning and Convolutional Neural Networks

Tena,

Dwiandiyanta

2023

JME

View full text Add to dashboard Cite

The woven ikat fabric from Nusa Tenggara Timur is a local wisdom that must be preserved. Due to its vast array of motifs, users often encounter challenges in its recognition. For this study, the TenunIkatNet dataset was employed. One prominent recognition method involves classification based on the motif type and geographical origin. The efficacy of the classification is heavily contingent upon the method of extraction employed. The Convolutional Neural Network (CNN) method is used for feature extraction and classification processes. This research compares the classification performance of the VGG16 baseline model and the proposed model. The proposed model modifies the baseline at the fully connected layer and the training process from the first convolution layer. Incorporating elements such as Global Average Pooling (GAP), Batch Bormalization (BN), and Dropout has proven instrumental in mitigating overfitting. The transfer learning strategy is used for feature extraction and classification because the model has been intelligently trained on a large dataset. The research findings unequivocally indicate that the performance of the modified model supersedes that of the baseline model. Based on the evaluation metrics, the proposed model is superior to the baseline model with precision, recall, accuracy, and F1-score, respectively 98.73%, 98.54%, 98.54%, and 98.53%

show abstract

An Improved Transfer-Learning for Image-Based Species Classification of Protected Indonesians Birds

Cited by 8 publications

References 60 publications

Content-Based Image Retrieval for Traditional Indonesian Woven Fabric Images Using a Modified Convolutional Neural Network Method

Content-Based Image Retrieval for Traditional Indonesian Woven Fabric Images Using a Modified Convolutional Neural Network Method

Deep Convolutional Neural Network for Automated Bird Species Classification

Transforming Woven Ikat Fabric: Advanced Classification via Transfer Learning and Convolutional Neural Networks

Contact Info

Product

Resources

About