• Resumo

    Comparação de Técnicas para Representação Vetorial de Imagens com Redes Neurais para Aplicações de Recuperação de Produtos do Varejo

    Data de publicação: 03/05/2023

    Product retrieval from images has multiple applications ranging
    from providing information and recommentations for customers
    in supermarkets to automatic invoice generation in smart stores.
    However, this task present important challenges such as the large
    number of products, the scarcity of images of items, differences
    between real and iconic images of the products, and the constant
    changes in the portfolio due to the addition or removal of products.
    Hence, this work investigates ways of generating vector representations
    of images using deep neural networks such that these
    representations can be used for product retrieval even in face of
    these challenges. Experimental analysis evaluated the effect that
    network architecture, data augmentation techniques and objective
    functions used during training have on representation quality. The
    best configuration was achieved by fine-tuning a VGG-16 model
    in the task of classifying products using a mix of Randaugment
    and Augmix data augmentations and a hierarchical triplet loss as a
    regularization function. The representations built using this model
    led to a top-1 accuracy of 80,38% and top-5 accuracy of 92.62% in
    the Grocery Products dataset.

Anais do Computer on the Beach

O Computer on the Beach é um evento técnico-científico que visa reunir profissionais, pesquisadores e acadêmicos da área de Computação, a fim de discutir as tendências de pesquisa e mercado da computação em suas mais diversas áreas.

Access journal