CNN-SIFT Consecutive Searching and Matching for Wine Label Retrieval

Li, Xiaoqing; Yang, Jiansheng; Ma, Jinwen

doi:10.1007/978-3-030-26763-6_24

Cited by 5 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As for the OR algorithm, the BING detector [54] is firstly implemented to detect potential objects, and then the SIFT features are extracted and aggregated by the VLAD algorithm to form an image representation, while the CNN features are extracted to form another image representation, and finally the two representations are fused together to be indexed into an inverted table and encoded with the Product Quantization (PQ) scheme for the image retrieval. The CSCSM framework in [17] also has a two-phase structure as the CSCFM framework, but utilizes the ResNeXt for learning the main-brands. In order to reduce the interference of background factors in wine label images, all the algorithms firstly use the identically trained FCN to segment the wine label region.…”

Section: B Cscfm Retrieval and Comparison On A General Wine Label Immentioning

confidence: 99%

See 1 more Smart Citation

Large Scale Category-Structured Image Retrieval for Object Identification Through Supervised Learning of CNN and SURF-Based Matching

Yang

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

In the modern era of Internet, mobile and digital information technology, image retrieval for object identification, just as wine label retrieval from a wine bottle image, has become an important and urgent problem in artificial intelligence. In comparison with the general image retrieval, it is rather challenging because there are a huge number of object identification or brand images which are very similar and difficult to discriminate, and the number of different brand images in the given dataset changes greatly, that is, the samples are strongly unbalanced for these brands. In this paper, we propose a CNN-SURF Consecutive Filtering and Matching (CSCFM) framework for this kind of image retrieval, specifically focalizing on wine label retrieval. In particular, Convolutional Neural Network (CNN) is utilized to filter out the impossible main-brands (manufacturers) for narrowing down the range of retrieval and the Speeded Up Robust Features (SURF) matching is improved by adopting the RANdom SAmple Consensus (RANSAC) mechanism and the modified Term Frequency-Inverse Document Frequency (TF-IDF) distance for the accurate retrieval of the sub-brand (item attribute under the manufacture). The experiments are conducted on a dataset containing approximately 548k images of wine labels with 17, 328 main-brands and 260, 579 subbrands. It is demonstrated by the experimental results that our proposed method can solve the wine label retrieval problem effectively and efficiently. Moreover, our proposed method is further evaluated on two pubic benchmarks of the object identification image retrieval tasks, Oxford Buildings Benchmark (Oxford5k) and the University of Kentucky of Indoor Things Benchmark (UKB), and achieves 88.3% mean average precision and 3.92 N-S score in Oxford5k and UKB, respectively. INDEX TERMS Image retrieval, object identification, wine label retrieval, CNN, SURF descriptor, filter out the impossible main-brands.

show abstract

Section: B Cscfm Retrieval and Comparison On A General Wine Label Immentioning

confidence: 99%

“…In order to overcome these difficulties, we recently proposed the framework of CNN-SIFT Consecutive Searching and Matching (CSCSM) [17] for the task of wine label retrieval with a large database. It is a two-phase system with consecutive searching and matching.…”

Section: Introductionmentioning

confidence: 99%

Large Scale Category-Structured Image Retrieval for Object Identification Through Supervised Learning of CNN and SURF-Based Matching

Yang

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…To solve above problem, fusion methods based on conventional feature and CNN began to appear. Li, Yang & Ma (2019) proposed CNN-SIFT Consecutive Searching and Matching (CSCSM) framework ( Li, Yang & Ma, 2020 ) and CNN-SURF Consecutive Filtering and Matching (CSCFM) framework ( Li, Yang & Ma, 2020 ) for wine label image retrieval on large-scale wine label image datasets. Both frameworks are two-phase retrieval frameworks, which can not only retrieve the main-brand but also find out the sub-brand about wine.…”

Section: Introductionmentioning

confidence: 99%

Distributed search and fusion for wine label image retrieval

2022

PeerJ Computer Science

Self Cite

View full text Add to dashboard Cite

With the popularity of wine culture and the development of artificial intelligence (AI) technology, wine label image retrieval becomes more and more important. Taking an wine label image as an input, the goal of this task is to return the wine information that the user hopes to know, such as the main brand and sub-brand of the wine. The main challenge in wine label image retrieval task is that there are a large number of wine brands with the imbalance of their sample images which strongly affects the training of the retrieval system based on deep learning. To solve this problem, this article adopts a distribted strategy and proposes two distributed retrieval frameworks. It is demonstrated by the experimental results on the large scale wine label dataset and the Oxford flowers dataset that both our proposed distributed retrieval frameworks are effective and even greatly outperform the previous state-of-the-art retrieval models.

show abstract