The Technique of Shape-Based Multi-Feature Combination of TradeMark Image Retrieval

Zhang, Cong; You, Fu Cheng

doi:10.4028/www.scientific.net/amr.429.287

Cited by 5 publications

(4 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Early attempts applied low/medium level global features, including graphic feature vectors [27], Fourier descriptors [16,21,66], image moments [12,16,22,66], Zernike moments [29,63,70] as well as simpler and lower-cost shape features such as aspect ratio [16], circularity [16], Rosin descriptor [16], angular radial transform [16], gray level projection [66], gradient orientation histogram [12,22], wavelets [12], triangle area representation [2,3] -see Table 1 for an overview. In addition to shape and texture related features, color-feature based approaches have also been applied for trademark retrieval [32,45,48,50,69].…”

Section: Checking Trademark Similarity Using Automated Methodsmentioning

confidence: 99%

See 1 more Smart Citation

A Large-scale Dataset and Benchmark for Similar Trademark Retrieval

Tursun,

Aker,

Kalkan

2017

Preprint

View full text Add to dashboard Cite

Trademark retrieval (TR) has become an important yet challenging problem due to an ever increasing trend in trademark applications and infringement incidents. There have been many promising attempts for the TR problem, which, however, fell impracticable since they were evaluated with limited and mostly trivial datasets. In this paper, we provide a large-scale dataset with benchmark queries with which different TR approaches can be evaluated systematically. Moreover, we provide a baseline on this benchmark using the widely-used methods applied to TR in the literature. Furthermore, we identify and correct two important issues in TR approaches that were not addressed before: reversal of contrast, and presence of irrelevant text in trademarks severely affect the TR methods. Lastly, we applied deep learning, namely, several popular Convolutional Neural Network models, to the TR problem. To the best of the authors, this is the first attempt to do so.

show abstract

Section: Checking Trademark Similarity Using Automated Methodsmentioning

confidence: 99%

“…In trademark retrieval, fusion of features has been applied successfully already [17,47,48,63,70]. In this study, we have also fused the best performing methods.…”

Section: Fusion Of Featuresmentioning

confidence: 99%

A Large-scale Dataset and Benchmark for Similar Trademark Retrieval

Tursun,

Aker,

Kalkan

2017

Preprint

View full text Add to dashboard Cite

show abstract

“…Multiple methods have been proposed in TIR; some of them utilize global features such as shape features [5] and color features [6,7]. In some studies a combination of global features is utilized, like the integration of shape and textures features in [8] and shape and color features in [7].…”

Section: Introductionmentioning

confidence: 99%

Indexing Techniques in Trademark Image Retrieval Systems

Taileb*

2020

IJITEE

View full text Add to dashboard Cite

The development of automatic trademark image retrieval systems becomes a necessity because of the increasing number of registered trademarks in all countries. The goal is to protect the registered trademarks from counterfeiting and infringement. This paper introduces a trademark image retrieval system using indexing techniques. The proposed system is described by giving an overview about its architecture and describing in details all its components. The goal is to allow researchers and developers in image retrieval to build their own trademark retrieval system using the indexing techniques. Each part of the proposed system is considered as a component that can be improved or replaced. The reader can have a clear idea on: (1) the type of visual features to extract from the trademark images, (2) the indexing technique that can be used to organize the extracted features and speed-up the search and (3) how to perform a similar search for a new trademark image. The proposed system has been evaluated using several global features and the best performance is obtained when using Zernike moments coefficients with order 12.

show abstract

“…Advanced Manufacturing and Automation must be detected. The object size and shape features can be combined to recognize the target object [11].…”

mentioning

confidence: 99%

A Target Recognition Algorithm Based on the Object’s Color and Size Features

Guo

Xie

et al. 2014

AMR

View full text Add to dashboard Cite

The problem being faced is that the current target recognition method based on color feature can’t filter objects that have the same color as the target object. In this paper, a new target recognition algorithm based on the object’s color and size is introduced. To achieve the goal of object recognition, the HSV color space conversion, the threshold method and seed growth method are used together to implement image segmentation. The size feature has been used to filter the image regions that have been extracted by image segmentation. The method is proved by experimentation to be effective in regular shape object recognition.

show abstract

The Technique of Shape-Based Multi-Feature Combination of TradeMark Image Retrieval

Cited by 5 publications

References 3 publications

A Large-scale Dataset and Benchmark for Similar Trademark Retrieval

A Large-scale Dataset and Benchmark for Similar Trademark Retrieval

Indexing Techniques in Trademark Image Retrieval Systems

A Target Recognition Algorithm Based on the Object’s Color and Size Features

Contact Info

Product

Resources

About