A Large Benchmark for Fabric Image Retrieval

Shen, Fei; Lin, Luxin; Wei, Mengwan; Liu, Jiajun; Zhu, Jianqing; Zeng, Huanqiang; Cai, Canhui; Zheng, Lixin

doi:10.1109/icivc47709.2019.8981065

Cited by 19 publications

(22 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dataset newly constructed by [34] consisted of 46,656 fabric images of 972 subjects, with multiple images from the front and back sides. The dataset was tested using BoF and three types of deep learning methods, namely LeNet, AlexNet, and VGGNet.…”

Section: Feature Extraction Based On Cnn Methodsmentioning

confidence: 99%

“…CNN's extraction features globally require large amounts of data, therefore, training it on large datasets provides a sufficient knowledge base to identify objects. CNNs are more sensitive to color features, with the main advantage of automatically identifying essential features without human supervision [34]. CNNs have the ability to reduce the semantic gap in image representation [44].…”

Section: Feature Extraction Based On Cnn Methodsmentioning

confidence: 99%

“…Global features Suitable for large datasets and both supervised and unsupervised learning [8], [10], [11], [13], [15], [16], [19] Reduces the semantic gap in comparison with traditional methods [8], [15], [16], [21] Can adapt to illumination and background interference [29], [36] Not suitable for sketch or grayscale images [28] Low accuracy for images with many patterns, such as printed fabric or clothing with complex shapes [2], [34], [39] Large feature dimensions [48], [54] High computation time [31], [36], [41] 6. CONCLUSION Feature selection and extraction methods are critical aspects of fabric image retrieval.…”

Section: Cnn Methodsmentioning

confidence: 99%

“…First, fabric images comprise many latticed and striped fabrics [2], [8]. Second, it contains complex textures that are more critical than color features for fabric image retrieval [34]. Third, it has repetitive patterns and creamy textures [9], [14].…”

Section: Comparison Of Traditional and Cnn Feature Extrationmentioning

confidence: 99%

See 3 more Smart Citations

Content-based image retrieval for fabric images: A survey

Tena

Hartanto

Ardiyanto

2021

IJEECS

View full text Add to dashboard Cite

In <span>recent years, a great deal of research has been conducted in the area of fabric image retrieval, especially the identification and classification of visual features. One of the challenges associated with the domain of content-based image retrieval (CBIR) is the semantic gap between low-level visual features and high-level human perceptions. Generally, CBIR includes two main components, namely feature extraction and similarity measurement. Therefore, this research aims to determine the content-based image retrieval for fabric using feature extraction techniques grouped into traditional methods and convolutional neural networks (CNN). Traditional descriptors deal with low-level features, while CNN addresses the high-level, called semantic features. Traditional descriptors have the advantage of shorter computation time and reduced system requirements. Meanwhile, CNN descriptors, which handle high-level features tailored to human perceptions, deal with large amounts of data and require a great deal of computation time. In general, the features of a CNN's fully connected layers are used for matching query and database images. In several studies, the extracted features of the CNN's convolutional layer were used for image retrieval. At the end of the CNN layer, hash codes are added to reduce </span>search time.

show abstract

Section: Feature Extraction Based On Cnn Methodsmentioning

confidence: 99%

Section: Feature Extraction Based On Cnn Methodsmentioning

confidence: 99%

Section: Cnn Methodsmentioning

confidence: 99%

Section: Comparison Of Traditional and Cnn Feature Extrationmentioning

confidence: 99%

See 2 more Smart Citations

Content-based image retrieval for fabric images: A survey

Tena

Hartanto

Ardiyanto

2021

IJEECS

View full text Add to dashboard Cite

show abstract

“…To validate the proposed GiT method's superiority, it is compared with multiple state-of-the-art vehicle reidentification approaches on three large-scale datasets, namely, VeRi776 [32], VehicleID [33] and VeRi-Wild [34]. The rank-1 identification rate (R1) [32,33,54] and mean average precision (mAP) [12,[55][56][57] are used to assess the accuracy performance.…”

Section: Experiments and Analysismentioning

confidence: 99%

GiT: Graph Interactive Transformer for Vehicle Re-identification

Shen¹,

Xie²,

Zhu³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Transformers are more and more popular in computer vision, which treat an image as a sequence of patches and learn robust global features from the sequence. However, a suitable vehicle re-identification method should consider both robust global features and discriminative local features. In this paper, we propose a graph interactive transformer (GiT) for vehicle re-identification. On the whole, we stack multiple GiT blocks to build a competitive vehicle re-identification model, in where each GiT block employs a novel local correlation graph (LCG) module to extract discriminative local features within patches and uses a transformer layer to extract robust global features among patches. In detail, in the current GiT block, the LCG module learns local features from local and global features resulting from the LCG module and transformer layer of the previous GiT block. Similarly, the transformer layer learns global features from the global features generated by the transformer layer of the previous GiT block and the new local features outputted via the LCG module of the current GiT block. Therefore, LCG modules and transformer layers are in a coupled status, bringing effective cooperation between local and global features. This is the first work to combine graphs and transformers for vehicle re-identification to the best of our knowledge. Extensive experiments on three large-scale vehicle reidentification datasets demonstrate that our method is superior to state-of-the-art approaches. The code will be available soon.

show abstract