A mobile visual search application for content based image retrieval in the fashion domain

Nodari, Angelo; Ghiringhelli, Matteo; Zamberletti, Alessandro; Vanetti, Marco; Albertini, Simone; Gallo, Ignazio

doi:10.1109/cbmi.2012.6269838

Cited by 12 publications

(7 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We employed the Drezzy-46 1 dataset, composed by images representing clothing in the context of online shopping and firstly presented in [17]. The number of images per class varies from a minimum of 52, to a maximum of 227.…”

Section: Methodsmentioning

confidence: 99%

Classification of Segmented Objects through a Multi-net Approach

Zamberletti

Gallo

Albertini

et al. 2012

Artificial Neural Networks in Pattern Recognition

View full text Add to dashboard Cite

Abstract. We propose an algorithm for the classification of segmented objects based on a set of neural networks. The proposed model aims to extend the MNOD algorithm adding a new type of node specialized in the objects classification. For each potential object identified by the MNOD, a set of segments are generated using a min-cut based algorithm with different seeds configurations. The segments are classified by a suitable neural model and then the segment with higher value is chosen, in according to a proper energy function. The advantage leading by the proposed method is twofold because it allows to segment and classify the objects simultaneously. The results showed in the experiment section, highlight the potential and the cost of having unified segmentation and classification in a single model.

show abstract

Section: Methodsmentioning

confidence: 99%

Classification of Segmented Objects through a Multi-net Approach

Zamberletti

Gallo

Albertini

et al. 2012

Artificial Neural Networks in Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…If a pixel (x, y) is a skin color set to one or is not a skin set to zero. (1) Before feature extraction, we normalized size the bounding box of upper body to size m,n (128, 256) in all of image dataset.…”

Section: ) Skin Extractionmentioning

confidence: 99%

“…It represents the appearance and the shape of an object in the image. Nodari et al [1] and Cushen et al [2] implemented visual search applications for mobile devices. They used content-based image retrieval to search similar image of clothes.…”

Section: Introductionmentioning

confidence: 99%

Predicting types of clothing using SURF and LDP based on Bag of Features

Surakarin

Chongstitvatana

2015

2015 12th International Conference on Electrical Engineering/Electronics, Computer, Telecommunications and Information Technolo

View full text Add to dashboard Cite

The low-level feature, such as Local Directional Pattern (LDP) was used to describe textures and shapes in the image. The advantage of the LDP feature is its robustness under random noise and illumination/light changes. This paper proposed a new approach to classifying and recognizing types of clothing by using Speeded-Up Robust Features (SURF) and Local Directional Pattern (LDP) based on Bag of Features (BoF) model. The key processes of the proposed system are firstly, the human are located and segmented clothing in the image. Secondly, Speeded-Up Robust Features (SURF) is used for detecting the interesting points and LDP features are used to create a codebook. Finally, a support vector machine (SVM) is used to classify the types of clothing. The dataset consists of seven categories of clothing such as sweaters, suits and shirts. Our dataset consists of total 1131 images out of which the training set is 991 images and the remainder is the testing set. The result of the recognition rate achieves an average F-score of 63.36%.

show abstract

“…Image retrieval for e-commerce is an emerging field of research, which because of a huge commercial potential has gradually attracted attention. Some enterprises are turning to e-commerce-oriented image retrieval, such as Hitachi's GazoPa [10] system, and part of the systems have even extended to mobile platform [11] Image retrieval technology combined with commerce can better play its inherent advantages, mainly because:…”

Section: Research Backgroundmentioning

confidence: 99%

Design of Shopping Guide System with Image Retrieval Based on Mobile Platform

Zhou¹,

Hu²,

Wang³

et al. 2013

Proceedings of the 2nd International Symposium on Computer, Communication, Control and Automation

View full text Add to dashboard Cite

with the continued rapid growth of Smartphone user group and rapid development of e-commerce, shopping guide system with image retrieval based on mobile platform is increasingly attracting attention. The portability and convenient camera feature of mobile phone allow mobile phone to have a natural advantage in e-commerce shopping. In order to adapt to the future trends of e-commerce, this paper studied mobile platform-based image retrieval technology and constructed an e-commerce-oriented shopping guide platform with commodity retrieval based on mobile devices. The platform supports the simple and convenient interaction methods and cutout design, and can provide effective retrieval results to make up for the deficiencies of the existing image retrieval system, thus has good practical value and significance of reference.

show abstract

A mobile visual search application for content based image retrieval in the fashion domain

Cited by 12 publications

References 18 publications

Classification of Segmented Objects through a Multi-net Approach

Classification of Segmented Objects through a Multi-net Approach

Predicting types of clothing using SURF and LDP based on Bag of Features

Design of Shopping Guide System with Image Retrieval Based on Mobile Platform

Contact Info

Product

Resources

About