Classification of fashion item attributes, such as neckline types, graphic patterns, sleeve lengths, hem types/length, etc., plays an essential role in the fashion item recommender systems by means of providing precise categorization and recommendations. With recent advances in Artificial Intelligence, many online retailers have adopted deep learning models to detect and classify the attributes of their product images effectively. However, these deep learning models require large and diverse datasets with labels to achieve an acceptable accuracy, which takes time and effort to collect and annotate. Another challenge of deep learning is its limited generalization capability to a new type of sample data. We hypothesize that imbuing a neural classification model with a human’s cognitive capability, such as recognizing complex patterns by simple geometric shapes, can improve fashion attribute classification performance. This paper proposes a transfer learning-based image classification model that exploits synthetic examples of canonical shapes (e.g., circles, triangles, rectangles, etc.) from publicly available datasets and our examples created using simple graphic tools. We use these datasets of geometric shapes as a source domain to pre-train a model and fine-tune it with labeled images to solve the target problem (i.e., fashion attribute classification). Our proposed framework increases the accuracy of the neckline type and graphical pattern classifications of Resnet50 by 40.7% and 19.8%, from 49.4% and 54.8% to 90.1% and 74.6%, respectively.

As online retail services proliferate and are pervasive in modern lives, applications for classifying fashion apparel features from image data are becoming more indispensable. Online retailers, from leading companies to start-ups, can leverage such applications in order to increase profit margin and enhance the consumer experience. Many notable schemes have been proposed to classify fashion items, however, the majority of such schemes have focused upon classifying basic-level categories, such as T-shirts, pants, skirts, shoes, bags, and so forth. In contrast to most prior efforts, this paper aims to enable an in-depth classification of fashion item attributes within the same category. Beginning with a single dress, we seek to classify the type of dress hem, the hem length, and the sleeve length. The proposed scheme is comprised of three major stages: (a) localization of a target item from an input image using semantic segmentation, (b) detection of human key points (e.g., point of shoulder) using a pre-trained CNN and a bounding box, and (c) three-phase classification of the attributes using a combination of algorithmic approaches and deep neural networks. The experimental results demonstrate that the proposed scheme is highly effective, with all categories having average precision of above 93.02%, and outperforms existing Convolutional Neural Networks (CNNs)-based schemes.

This research proposes a case-based support system, the Designer's Associate, for facilitating software reuse. Two factors motivate this research. First, reuse promises to improve software quality and designer productivity. Second, achieving effective software reuse continues to be inordinately difficult. The Designer's Associate promotes software reuse by making design artifacts from previous development efforts both readily accessible and reusable. It provides tools to create, retrieve, reuse, adapt, and archive artifacts central to the software design process. An implementation of the Designer's Associate was constructed to demonstrate the concept and assess its merits

Design support for command and control software development represents a new, but interesting, aspect of the human-machine systems engineering problem. The design support approach described in this paper is rooted in a computer-based Designer’s Associate which facilitates learning at the organizational level via the collection and diffusion of domain-specific experience.

Supervisory control is a cooperative effort between operators, automated systems, and designers. For this reason, one can seek to address in part past and future supervisory control problems by explicitly supporting designers. This paper describes a computer-based decision support approach for design which is directed at facilitating recognition-primed decision making and at ensuring that designer decision-making is not bounded by personal experience, but at most by the experiences of the organization in which the designer works. The approach relies on an inter-linked base of knowledge which integrates information from multiple organizations, systems, and individuals

Command and control software design represents a new, but interesting, aspect of the human-machine systems engineering problem. This paper describes an architecture for a Designer's Associate that accumulates and disseminates information, and facilitates the construction of plausible solutions to design software design problems. The goal of this research effort is to formulate, demonstrate, and evaluate concepts which assist a designer in unfamiliar, yet commonly occurring, domain-specific design situations