Garment Categorization Using Data Mining Techniques

Abstract

The apparel industry houses a huge amount and variety of data. At every step of the supply chain, data is collected and stored by each supply chain actor. This data, when used intelligently, can help with solving a good deal of problems for the industry. In this regard, this article is devoted to the application of data mining on the industry’s product data, i.e., data related to a garment, such as fabric, trim, print, shape, and form. The purpose of this article is to use data mining and symmetry-based learning techniques on product data to create a classification model that consists of two subsystems: (1) for predicting the garment category and (2) for predicting the garment sub-category. Classification techniques, such as Decision Trees, Naïve Bayes, Random Forest, and Bayesian Forest were applied to the ‘Deep Fashion’ open-source database. The data contain three garment categories, 50 garment sub-categories, and 1000 garment attributes. The two subsystems were first trained individually and then integrated using soft classification. It was observed that the performance of the random forest classifier was comparatively better, with an accuracy of 86%, 73%, 82%, and 90%, respectively, for the garment category, and sub-categories of upper body garment, lower body garment, and whole-body garment.

Developing a data-driven operational guide for the texturized yarn production process: data mining and intelligence approach

“…The breadth of this field is extensive, encompassing investigations such as establishing standardized clothing sizes (Jeyasingh et al ., 2012), identifying factors that influence the insulation properties of garments (Jeyasingh et al ., 2012; Lee et al ., 2019), pinpointing variables that contribute to minimizing waste in glove production (Seçkin et al ., 2019), predicting the types of garments (lower body, upper body, whole body) and their subsets (blouse, dress, etc.) (Jain and Kumar, 2020; Cheng et al ., 2022), crafting a recommender system to assist customers in selecting clothing tailored to their physical attributes and purchasing history (Zhang et al ., 2021), ranking woven fabric defects observed during textile manufacturing (Saeidi et al ., 2013), monitoring yarn quality within a textile firm (Ertuğrul and Aytaç, 2009), modeling an intelligent manufacturing process line, encompassing textile processes from yarn to fabrics and garments (He et al ., 2021a), and exploring fashion trends within the realm of clothing (Shi et al ., 2021); all of which have been cited as noteworthy contributions. Table 2 summarizes research employing data mining methods in the yarns, textiles and clothing industries.…”

Hybrid Computational Intelligence System for Fashion Design

“…To feel the fashion-related objects more effectively, augmented reality-based systems are also developed and discussed on social media platforms in the work of (Adilah & Alamsyah, 2019). An analytical based method for cloths recommendation is experimented by (Zhang Y., et al, 2017), (Jain & Kumar, 2020) and (M'Hallah & Bouziri, 2016) using a hierarchical analysis method along with other techniques.…”

The application of big data in fashion retailing: a narrative review

“…Narrative reviews are also useful for providing rationales for future research (Ferrari, 2015), and our article can motivate and guide researchers into exploiting the vast amounts of data generated by the fashion industry for improving its planning, production and decision-making capabilities. Recently, there have been some publications dealing with aspects of the use of Big Data in fashion (Madsen and Stenheim, 2016;Jain et al 2017;Jain & Kumar, 2020;Silva et al, 2019b) whilst the book by Marr (2016) describes and explains how some fashion companies (like Amazon and Ralph Lauren) have successfully adopted Big Data.…”