East Nusa Tenggara Weaving Image Retrieval Using Convolutional Neural Network

Tena, Silvester; Hartanto, Rudy; Ardiyanto, Igi

doi:10.1109/isriti54043.2021.9702843

“…These parameters were applied equally to both groups of pretrained CNN and modified CNN models. This experiment used a 6 bit hashing code to index image features [ 24 ]. In this experiment, the datasets are divided into a training set of 80% and a testing set of 20%.…”

Section: Resultsmentioning

confidence: 99%

“…In addition, the CNN architecture is based on the number of TenunIkatNet dataset categories. Several pretrained models have been evaluated for ikat woven fabric image retrieval without treatment with suboptimal results [ 24 ]. The pretrained models were trained on significantly different image datasets with different classes.…”

Section: Methodsmentioning

confidence: 99%

“…The model is then integrated with a new model for the target task, which can be learned with pretrained weights and fine-tuned on the target dataset [ 23 ]. Previous research has used transfer learning for ikat woven fabric image retrieval, but the top-5 and above accuracy is still low [ 24 ]. Research on the retrieval of ikat woven fabrics has been carried out by several researchers using handcrafted features.…”

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

Self Cite

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

“…Abdul Haris Rangkuti et al [4] used VGG19 as feature extractor, and used Manhattan, Euclid, Chebyshev and other distance measurement models to study 56 traditional styles, and the accuracy reached over 90% on the self-made fabric dataset. Silvester Tena et al [5] built a private fabric image dataset containing a large number of complex patterns, and conducted experiments with deep convolution neural networks such as ResNet101 and InceptionV3 and finally the recall of top5 reached 84.08%. It is effective to use CNN for fabric retrieval, but the high-dimensional output characteristics of networks such as ResNet101 slow down the retrieval speed.…”

Section: Introductionmentioning

confidence: 99%

An efficient network based on double constrained loss for fabric image retrieval

Gui,

Wu,

He

2023

SIViP

0

View full text Add to dashboard Cite

In order to efficiently retrieve the same or similar fabric samples, a fabric image retrieval model based on deep hashing is proposed. The model is improved on the basis of MobileNetV1, and the performance of the model is improved by combining the h-swish activation function and attention mechanism module. The hashing method is used to solve the problem of low feature matching speed caused by high dimensional feature output. By combining the label information and similarity information of the images, a new loss function is constructed, which solves the problem of low model accuracy caused by the large feature difference between similar samples and the small feature difference between heterogeneous samples in fabric images. The experimental results on self-built fabric image dataset showed that the feature extraction time of the proposed algorithm was 0.25ms, and the MAP reached 93.2%, which can take into account the fabric retrieval speed and improve retrieval accuracy at the same time, and has certain application prospects.

show abstract

An efficient network based on double constrained loss for fabric image retrieval

Gui

¹

,

Wu

²

2023

Preprint

0

View full text Add to dashboard Cite

In order to efficiently retrieve the same or similar fabric samples, a fabric image retrieval model based on deep hashing is proposed. The model is improved on the basis of MobileNetV1, and the performance of the model is improved by combining the h-swish activation function and attention mechanism module. The hashing method is used to solve the problem of low feature matching speed caused by high dimensional feature output. By combining the label information and similarity information of the images, a new loss function is constructed, which solves the problem of low model accuracy caused by the large feature difference between similar samples and the small feature difference between heterogeneous samples in fabric images. The experimental results on self-built fabric image dataset showed that the feature extraction time of the proposed algorithm was 0.25ms, and the MAP reached 93.2%, which can take into account the fabric retrieval speed and improve retrieval accuracy at the same time, and has certain application prospects.

show abstract

East Nusa Tenggara Weaving Image Retrieval Using Convolutional Neural Network

Cited by 3 publications

References 25 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

An efficient network based on double constrained loss for fabric image retrieval

An efficient network based on double constrained loss for fabric image retrieval

Contact Info

Product

Resources

About