Abstract
Deep learning has played a huge role in computer vision fields due to its ability to extract underlying and complex features of input images. Deep learning is applied to complex vision tasks to perform image recognition and classification. Recently, Apparel classification, is an application of computer vision, has been intensively explored and investigated. This paper proposes an effective framework, called DeepAutoDNN, based on deep learning algorithms for apparel classification. DeepAutoDNN framework combines a deep autoencoder with deep neural networks to extract the complex patterns and high-level features of fashion images in supervised manner. These features are utilized via categorical classifier to predict the given image to the right label. To evaluate the performance and investigate the efficiency of the proposed framework, several experiments have been conducted on the Fashion-MNIST dataset, which consists of 70000 images: 60000 and 10000 images for training and test, respectively. The results have shown that the proposed framework can achieve accuracy of 93.4%. In the future, this framework performance can be improved by utilizing generative adversarial networks and its variant.
Highlights
Conventional machine learning algorithms still used in the image processing and computer vision to perform data mining and feature extraction such as support vector machine (SVM)
The compared approaches were: Hierarchical Convolutional Neural based on VGG16 and VGG19 [1], VGG11 [12], Convolutional Neural Network with Support vector Machine [14], Convolutional Neural Network followed by Batch Normalization and Skip Connection [7], HitNet [17], Histogram of Oriented Gradient with Multiclass Support Vector Machine [18], Long-Short Term Memory [19], Unconditional and conditional Collaborative Neural Networks [20], Histogram of Oriented Gradient with Local Binary Pattern [21]
With rapid advancement in deep learning and computer vision techniques, many studies have been conducted on complex vision tasks due to the powerful representationlearning algorithms utilizing advance deep learning techniques
Summary
Conventional machine learning algorithms still used in the image processing and computer vision to perform data mining and feature extraction such as support vector machine (SVM). With the great advancement in deep learning techniques exploring and solving the most complicated computer vision tasks, many computer vision applications have gained a significant attention due to the available resources and large amount of data. Due to the complex pattern of fashion apparel, various fashion properties, and the performance of previous existing deep learning algorithms, we believe that applying a good representation learning technique to extract useful features would enhance the performance of the fashion apparel detection and classification. The main contribution of this study can be summarized as follows: 1) Propose a novel fashion classification framework based on deep learning techniques.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
