Figure 5 - available via license: CC BY
Content may be subject to copyright.
Source publication
The digitization of the fashion industry diversified consumer segments, and consumers now have broader choices with shorter production cycles; digital technology in the fashion industry is attracting the attention of consumers. Therefore, a system that efficiently supports the searching and recommendation of a product is becoming increasingly impor...
Context in source publication
Context 1
... the profile data collected during the learning process, each user will have a separate learning model. Figure 5 shows the model overview of the whole process. Each user has a profile collected through the system as described in Section 2.2, and the system converts the top and bottom image in the profile to vector values using the Image2vec-based feature extraction model specified in Section 2.3. ...
Similar publications
Designing circular economy (CE) implies the adoption of a set of circular principles that support a society for the future. Understanding how CE principles influence attitudes to consume green products is a key factor aligned with consumer trends. This chapter aims to study how CE principles influence attitudes to consume green products in a partic...
Citations
... By using CNN to analyze the structure and performance of products, designers can optimize the shape more effectively and improve the functionality and performance of products [12][13] . Deep learning technology is widely used in intelligent user interface design, providing users with personalized product experience by analyzing user behavior and feedback [14] . ...
This study is devoted to exploring the strategy of automatic sketch generation and optimization of industrial design based on deep learning. By combining the Generative Adversarial Network (GAN) with the optimization algorithm, this paper proposes an innovative method to realize the automatic generation of high-quality and diverse industrial design sketches. In the experiment, this paper selects SketchyCAD and other public data sets, trains them through deep learning model, and introduces genetic algorithm(GA) and differential evolution algorithm to optimize the parameters. In terms of experimental results, we observed that the quality of generated sketches was significantly improved, and the design sketches generated by the mode (GAN+GA) were more realistic and innovative. The introduction of optimization strategy further improves the generation effect and intelligently adjusts the model parameters to adapt to different design styles. In this paper, the influence of hyperparameter tuning is analyzed in detail, and it is found that the adjustment of learning rate plays a key role in generating quality and diversity. However, the experiment also revealed some challenges and room for improvement. We noticed that the generated results may have the risk of over-fitting in the training process, and with the increase of training times, the diversity gradually decreased. This suggests that more complex model structure and richer data sets are needed to improve the generalization performance. Generally speaking, this study provides new ideas and methods for the integration of deep learning and industrial design. By innovatively combining generation model and optimization algorithm, this research has contributed beneficial research results to the development of industrial design automation. This research is of great significance to promote the intelligence and innovation in the field of industrial design.
... This approach facilitates market share expansion in East London for fashion brands while concurrently upholding their credibility. The consequential impact has been a favourable enhancement of overall productivity, marked by increased revenue levels (Jo et al., 2020). The proficiency of the online shopping system, encompassing digital marketing and user-friendly ordering platforms, has contributed to the industry's potential for optimizing profitability (Santy and Alfiana, 2021). ...
The advent of advanced technology has revolutionized online business, significantly impacting the luxury clothing market. Women of Bangladeshi heritage in East London, initially sceptical about online purchases, have embraced the convenience of upgraded technology. Past studies assert that a substantial portion of purchases is now conducted online. This shift is attributed to online shopping’s accessibility, flexibility, and features such as cash refunds, absent in physical stores. For the fashion industry, online business proves strategic, expanding growth and success. However, existing literature overlooks issues like transaction complexities and potential data compromises in online shopping. This case study investigates brand loyalty and customer satisfaction among East London’s immigrant women in online luxury clothing purchases. The findings reveal the strong influence of luxury brands on women, emphasizing the need for continuous innovation. Diversity in consumer perceptions necessitates brand attention for sustained growth. Women allocate more budget to luxury clothing, signalling an opportunity for brands to expand collections. Quality emerges as a key factor, urging brands to refine quality control. Strong brand loyalty among women suggests effective business strategies and enduring customer relationships. The study highlights the increasing preference for online shopping, driven by factors like diverse products and free delivery. These insights guide luxury brands in tailoring strategies for customer satisfaction and sustained success. The complex dynamics of women’s perceptions, preferences, and behaviours in the luxury fashion market offer nuanced insights for strategic adaptation. Continuous improvement, diversification, and targeted marketing on digital platforms are recommended for sustained brand success.
... Jo et.al. [28] presents a deep learning-based fashion product retrieval and recommendation model. The proposed model employs a convolutional neural network (CNN) to extract features from product images and a recurrent neural network (RNN) to capture the sequential order of user behavior data. ...
... Customers and the business enterprise want the client to discover relevant fashion items when they are searching, and this is where recommender systems come into the picture [6]. In 2024, the size of the domestic fashion market will have grown by 8.8% compared to its size in 2020 [7][8][9]. Being one of the hottest study topics currently in progress at both the national and international levels, recommender systems are the ideal solution for suitable fashion discovery in e-commerce, and the recommender systems possess several strong points; nevertheless, recommender systems also possess some weaknesses in the accuracy of their results. However, content-based information retrieval (CBIR) has become one of the hotspot topics; it retrieves items based entirely on the image content, which decreases some of the weaknesses, especially in fashion, by computing similarities among items and users through a set of features associated with them [10]. ...
Many people wonder, when they look at fashion models on social media or on television, whether they could look like them by wearing similar products. Furthermore, many people suffer when they sometimes find fashion models in e-commerce, and they want to obtain similar products, but after clicking on the fashion model, they receive unwanted products or products for the opposite gender. To address these issues, in our work, we built a multi-task learning and gender-aware fashion recommendation system (MLGFRS). The proposed MLGFRS can increase the revenue of the e-commerce fashion market. Moreover, we realized that people are accustomed to clicking on that part of the fashion model, which includes the product they want to obtain. Therefore, we classified the query image into many cropped products to detect the user’s click. What makes this paper novel is that we contributed to improving the efficiency performance by detecting the gender from the query image to reduce the retrieving time. Second, we effectively improved the quality of results by retrieving similarities for each object in the query image to recommend the most relevant products. The MLGFRS consists of four components: gender detection, object detection, similarity generation, and recommendation results. The MLGFRS achieves better performance compared to the state-of-the-art baselines.
... Alia Madain asmadain@just.edu.jo 1 Department of Computer Science, Jordan University of Science and Technology, Irbid 22110, Jordan the fashion industry, the system evaluates customer fashion desires and seeks to meet them as rapidly as possible. As a result, the fashion industry's digital technology is catching the attention of consumers from a wide variety of demographics, who have a wider choice of options due to the reduced production cycle [4]. Furthermore, with over 10 million consumers using smart devices, these devices play a significant role as a new e-commerce platform [5]. ...
Online shopping experiences should be simplified by incorporating essential features such as virtual try-on clothing and recommending new items based on the customer’s preferences. This is necessary given the rapid growth of the fashion industry and the expansion of shopping technologies. In this paper, we propose a new approach integrating fashion image retrieval and recommendation with a 3D virtual try-on network. We aim to build an interactive attributes-preserving model that allows users to choose the favourite garments and virtually try them on after uploading a frontal image of the whole body. Several deep learning architectures are used to extract and learn the key attributes of garment image, by which each formulated image is subjected to effective human body segmentation and pose estimation procedures. Then, a 3D VTON network is used to generate a 3D image of the user wearing a specific garment, after which the fashion retrieval system recommends and ranks more relevant items. Extensive experiments on multi-domain fashion dataset demonstrate that the proposed framework outperforms the state-of-the-art methods in terms of fashion retrieval and attribute relevancy, achieving a top@30 accuracy of 80.02%, an NDCG@30 of 80.26%, and a top@30 mAP of 87.71%. Additionally, the generated generic image descriptors require very little memory space, enabling rapid online learning and retrieval of large-scale 3D images.
... Traditional garment sales channels such as brick-and-mortar stores have seen sales decline, whereas non-store retailers such as online and mobile merchants have seen sales increase at the fastest rate. When compared to previous years, the online f ashion market increased by 16 percent per year from 2011 to 2016, and from January to September 2017, the market increased by 20 percent over the previous year [4]. Eventually, it is expected to become a major channel in the fashion industry in the coming years. ...
... It is possible to generate images' latent properties using autoencoders and other visual search methods, for example. To further enhance the retrieval of image embedding features, deep neural network models that have already been trained can be applied to the problem [4][6] [7]. ...
... The UNIT architecture deals with the heterogeneous nature of clothing and sketches images, and also rich annotated dataset is not required. Jo, J. et al. [54] proposed a sketch-based fashion image retrieval model that takes a user sketch as input for the desired fashion item, i.e., up-sampled using a GAN architecture. After that, the properties of that up- ...
Content-based fashion image retrieval (CBFIR) has been widely used in our daily life for searching fashion images or items from online platforms. In e-commerce purchasing, the CBFIR system can retrieve fashion items or products with the same or comparable features when a consumer uploads a reference image, image with text, sketch or visual stream from their daily life. This lowers the CBFIR system reliance on text and allows for a more accurate and direct searching of the desired fashion product. Considering recent developments, CBFIR still has limits when it comes to visual searching in the real world due to the simultaneous availability of multiple fashion items, occlusion of fashion products, and shape deformation. This paper focuses on CBFIR methods with the guidance of images, images with text, sketches, and videos. Accordingly, we categorized CBFIR methods into four main categories, i.e., image-guided CBFIR (with the addition of attributes and styles), image and text-guided, sketch-guided, and video-guided CBFIR methods. The baseline methodologies have been thoroughly analyzed, and the most recent developments in CBFIR over the past six years (2017 to 2022) have been thoroughly examined. Finally, key issues are highlighted for CBFIR with promising directions for future research.
... In [44], both deep learning and image processing techniques were applied to automatically recognize and classify logos, stripes, colors, and other features of clothing. An intelligent fashion technique based on deep learning for efficient fashion product searches and recommendations were proposed, including a sketch-product fashion retrieval model and a user preference fashion recommendation model [45]. In [46], CNN networks were used to train images of different fashion styles, in which the performance was validated using the Fashion-MNIST dataset. ...
With the rapid development of artificial intelligence, much more attention has been paid to deep learning. However, as the complexity of learning algorithms increases, the needs of computation power of hardware facilities become more crucial. Instead of the focus being on computing devices like GPU computers, a lightweight learning algorithm could be the answer for this problem. Cross-domain applications of deep learning have attracted great interest amongst researchers in academia and industries. For beginners who do not have enough support with software and hardware, an open-source development environment is very helpful. In this paper, a relatively lightweight algorithm YOLOv5s is addressed, and the Google Colab is used for model training and testing. Based on the developed environment, many state-of-art learning algorithms can be studied for performance comparisons. To highlight the benefits of one-stage object detection algorithms, the recognition of clothing styles is investigated. The image samples are selected from datasets of fashion clothes and the web crawling of online stores. The image data are categorized into five groups: plaid; plain; block; horizontal; and vertical. Average precison, mean average precison, recall, F1-score, model size, and frame per second are the metrics used for performance validations. From the experimental outcomes, it shows that YOLOv5s is better than other learning algorithms in the recognition accuracy and detection speed.
... Traditional garment sales channels such as brick-and-mortar stores have seen sales decline, whereas non-store retailers such as online and mobile merchants have seen sales increase at the fastest rate. When compared to previous years, the online fashion market increased by 16 percent per year from 2011 to 2016, and from January to September 2017, the market increased by 20 percent over the previous year [4]. Eventually, it is expected to become a major channel in the fashion industry in the coming years. ...
... It is possible to generate images' latent properties using autoencoders and other visual search methods, for example. To further enhance the retrieval of image embedding features, deep neural network models that have already been trained can be applied to the problem [4][6] [7]. ...
In recent years, the World Wide Web (WWW) has established itself as a popular source of information. Using an effective approach to investigate the vast amount of information available on the internet is essential if we are to make the most of the resources available. Visual data cannot be indexed using text-based indexing algorithms because it is significantly larger and more complex than text. Content-Based Image Retrieval, as a result, has gained widespread attention among the scientific community (CBIR). Input into a CBIR system that is dependent on visible features of the user's input image at a low level is difficult for the user to formulate, especially when the system is reliant on visible features at a low level because it is difficult for the user to formulate. In addition, the system does not produce adequate results. To improve task performance, the CBIR system heavily relies on research into effective feature representations and appropriate similarity measures, both of which are currently being conducted. In particular, the semantic chasm that exists between low-level pixels in images and high-level semantics as interpreted by humans has been identified as the root cause of the issue. There are two potentially difficult issues that the e-commerce industry is currently dealing with, and the study at hand addresses them. First, handling manual labeling of products as well as second uploading product photographs to the platform for sale are two issues that merchants must contend with. Consequently, it does not appear in the search results as a result of misclassifications. Moreover, customers who don't know the exact keywords but only have a general idea of what they want to buy may encounter a bottleneck when placing their orders. By allowing buyers to click on a picture of an object and search for related products without having to type anything in, an image-based search algorithm has the potential to unlock the full potential of e-commerce and allow it to reach its full potential. Inspired by the current success of deep learning methods for computer vision applications, we set out to test a cutting-edge deep learning method known as the Convolutional Neural Network (CNN) for investigating feature representations and similarity measures. We were motivated to do so by the current success of deep learning methods for computer vision applications (CV). According to the experimental results presented in this study, a deep machine learning approach can be used to address these issues effectively. In this study, a proposed Deep Fashion Convolution Neural Network (DFCNN) model that takes advantage of transfer learning features is used to classify fashion products and predict their performance. The experimental results for image-based search reveal improved performance for the performance parameters that were evaluated.
... Research on algorithm implementation was carried out in [1][2][3]. Yang et al. propose two deep neural networks based on the attention mechanism to improve a sequence-topoint learning model. Their results show that the proposed mechanisms effectively improve performance. ...
Recently, systems have become more flexible and smarter in their implementation and functions [...]
