In various implementations, one or more specific attributes found in an image can be modified utilizing one or more specific attributes found in another image. Machine learning, deep neural networks, and other computer vision techniques can be utilized to extract attributes of images, such as color, composition, font, style, and texture from one or more images. A user may modify at least one of these attributes in a first image based on the attribute(s) of another image and initiate a visual-based search using the modified image. In some embodiments, a selection of at least one negative attribute is received from the user. The negative attribute(s) is an attribute the user does not want the modified image to include.


    Access

    Download


    Export, share and cite



    Title :

    Modifying at least one attribute of an image with at least one attribute extracted from another image


    Publication date :

    2016-09-07


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    English



    WhittleSearch: Interactive Image Search with Relative Attribute Feedback

    Kovashka, A. / Parikh, D. / Grauman, K. | British Library Online Contents | 2015


    ATTRIBUTE ACQUISITION SYSTEM AND ATTRIBUTE ACQUISITION METHOD

    IMAI TOSHIMITSU | European Patent Office | 2017

    Free access

    Distributed adaptive attribute-based image retrieval [2606-34]

    Jung, G. S. / Gudivada, V. N. / SPIE | British Library Conference Proceedings | 1995


    ATTRIBUTE ESTIMATION APPARATUS AND ATTRIBUTE ESTIMATION METHOD

    NAKAMURA MASASHI / KASAI TETSUKO / YAMAMOTO TAKASHI | European Patent Office | 2023

    Free access

    A Noise Attribute Thresholding Method for Document Image Binarization

    Don, H.-S. | British Library Conference Proceedings | 1995