Human Body Shape Classification Based on a Single Image
This addresses the need for body shape classification in fashion recommender systems, though it appears incremental as it builds on existing segmentation and keypoint methods.
The paper tackles the problem of classifying human body shape from a single image to support online fashion recommendations, achieving this through instance segmentation and keypoint estimation without requiring 3D body recreation or historical user data.
There is high demand for online fashion recommender systems that incorporate the needs of the consumer's body shape. As such, we present a methodology to classify human body shape from a single image. This is achieved through the use of instance segmentation and keypoint estimation models, trained only on open-source benchmarking datasets. The system is capable of performing in noisy environments owing to to robust background subtraction. The proposed methodology does not require 3D body recreation as a result of classification based on estimated keypoints, nor requires historical information about a user to operate - calculating all required measurements at the point of use. We evaluate our methodology both qualitatively against existing body shape classifiers and quantitatively against a novel dataset of images, which we provide for use to the community. The resultant body shape classification can be utilised in a variety of downstream tasks, such as input to size and fit recommendation or virtual try-on systems.