Deep Learning Image Classification for Fashion Design

Vijayaraj, A.; Raj, P. T. Vasanth; Jebakumar, R.; Senthilvel, P. Gururama; Kumar, Nirmal P.; R, Suresh Kumar; Dhanagopal, R.

doi:10.1155/2022/7549397

Cited by 20 publications

(9 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We evaluate the proposed technique and compare it to other existing DL techniques to showcase its advantages based on various performance metrics. Our technique led to better performance with improved accuracy (3%), precision (1%),Fmeasure (1%), runtime (1.415SI), AUC (3.5%), recall (2%),TNR (2%),TPR (5%),FNR (15%), error rate (35%), and FPR (52%) as compared to the average performance of the existing deep learning detection techniques [29,30,31,49,51].…”

Section: Introductionmentioning

confidence: 90%

Gradient-Boosted Convolutional Neural Network Malware Detection Technique for Android Smartphones

Chimeleze

Jamil

Teh

et al. 2022

Preprint

View full text Add to dashboard Cite

Malware is malicious software designed to damage or infiltrate a computer system without the user's knowledge. Malware detection includes the process of detecting the presence of malware on the host system or determining whether the type of program is malicious or benign. Recently, machine learning (ML) algorithms have been used to detect malware effectively. Unfortunately, the core techniques require extensive feature learning, engineering and representation, which increases the computational time, error rate ratio and improves recall. The feature engineering phase of these methods can be alleviated by using more advanced ML approaches during the detection phase. In this article, we propose a gradient-boosted convolutional neural network (GB-CNN) to detect malware in Android smartphones. This proposed technique uses entropy-based feature selection technique to select relevant Android features and APKs. These selected features are fed to deep learning for classification. The classification results are then optimized by gradient boost machine learning. Comparative results show that GB-CNN outperforms other existing deep learning –based detection techniques, and is especially suitable for malware detection on Android devices, with improvements in terms of accuracy (3%), precision (1%) ,F-measure (1%), runtime (1.415SI), AUC (3.5%), recall (2%),TNR (2%),TPR (5%),FNR (15%), error rate (35%), and FPR (52%) on Android application sets. These improvements stem from optimizing the convolutional network with gradient boosting machine during the malware detection phase.

show abstract

Section: Introductionmentioning

confidence: 90%

Gradient-Boosted Convolutional Neural Network Malware Detection Technique for Android Smartphones

Chimeleze

Jamil

Teh

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Fashion has been a crucial aspect of our daily routines and holds significance in society (Vijayaraj et al, 2022). In the Kingdom of Saudi Arabia, the clothing heritage is diverse, representing various styles and customs that showcase the history of the land and the heritage of our ancestors.…”

Section: Research Statementmentioning

confidence: 99%

Classification of Saudi Traditional Costumes using Deep Learning Technique

Baalamash,

Debis,

Al-Barhamtoshy

2024

International Design Journal

View full text Add to dashboard Cite

to develop a system for classifying traditional clothing from the Kingdom of Saudi Arabia using convolutional neural networks. A dataset of 339 images across 3 categories was collected and preprocessed, including normalization, cropping, and blurring to enhance image quality. The proposed system accomplished classification through a two-step process: Dataset collection utilizing Artificial intelligence (AI) techniques to gather 339 labeled images of clothing from Saudi Arabia which served as the training foundation, and classification using the Inception v3 CNN model with transfer learning. Testing is achieved with an overall accuracy of 84.85% based on a confusion matrix, demonstrating the model's ability to correctly classify traditional clothing. Weighted Euclidean distance matching was also implemented to retrieve the top 5 similarity matches for query images. A graphical user interface allows practical implementation and end-user clothing classification. The promising results indicate deep learning is viable for this application. However, limitations include the small dataset size. Future work involves collecting a larger, more diverse set of traditional Saudi clothing images to further improve classification performance.

show abstract

“…This paper focuses mainly on optimizing model structure and learning rate. In addition, various studies (Medina et al, 2022;Ma et al, 2022;Vijayaraj et al, 2022), such as deep learning, recognition, and classification for fashion clothing images are currently being conducted.…”

Section: Related Workmentioning

confidence: 99%

A Novel Method for Fashion Clothing Image Classification Based on Deep Learning

Shin

Jo²,

Wang

2023

JICT

View full text Add to dashboard Cite

Image recognition and classification is a significant research topic in computational vision and widely used computer technology. Themethods often used in image classification and recognition tasks are based on deep learning, like Convolutional Neural Networks(CNNs), LeNet, and Long Short-Term Memory networks (LSTM). Unfortunately, the classification accuracy of these methods isunsatisfactory. In recent years, using large-scale deep learning networks to achieve image recognition and classification canimprove classification accuracy, such as VGG16 and Residual Network (ResNet). However, due to the deep network hierarchyand complex parameter settings, these models take more time in the training phase, especially when the sample number is small, which can easily lead to overfitting. This paper suggested a deep learning-based image classification technique based on a CNN model and improved convolutional and pooling layers. Furthermore, the study adopted the approximate dynamic learning rate update algorithm in the model training to realize the learning rate’s self-adaptation, ensure the model’s rapid convergence, and shorten the training time. Using the proposed model, an experiment was conducted on the Fashion-MNIST dataset, taking 6,000 images as the training dataset and 1,000 images as the testing dataset. In actual experiments, the classification accuracy of the suggested method was 93 percent, 4.6 percent higher than that of the basic CNN model. Simultaneously, the study compared the influence of the batch size of model training on classification accuracy. Experimental outcomes showed this model is very generalized in fashion clothing image classification tasks.

show abstract

Deep Learning Image Classification for Fashion Design

Cited by 20 publications

References 14 publications

Gradient-Boosted Convolutional Neural Network Malware Detection Technique for Android Smartphones

Gradient-Boosted Convolutional Neural Network Malware Detection Technique for Android Smartphones

Classification of Saudi Traditional Costumes using Deep Learning Technique

A Novel Method for Fashion Clothing Image Classification Based on Deep Learning

Contact Info

Product

Resources

About