On the Benefit of Synthetic Data for Company Logo Detection

Eggert, Christian; Winschel, Anton; Lienhart, Rainer

doi:10.1145/2733373.2806407

Cited by 33 publications

(24 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a further comparison, we report the results obtained by our solution using only FlickrLogos-32 for training and keeping all the other training choices unchanged. This results in a drop in F1-measure by 14.7% and by 4.8% in accuracy, giving an idea of the benefit of real data augmentation with respect to a purely synthetic one [14]. As a final analysis, to understand if the major source of error in our method is the Selective Search module that is unable to have a high recall or if its the CNN itself that mispredicts the logo class, we perform an additional test by adding the actual logo ground truth region to the object proposals.…”

Section: Experimental Setup and Resultsmentioning

confidence: 99%

Deep learning for logo recognition

et al. 2017

View full text Add to dashboard Cite

In this paper we propose a method for logo recognition using deep learning. Our recognition pipeline is composed of a logo region proposal followed by a Convolutional Neural Network (CNN) specifically trained for logo classification, even if they are not precisely localized. Experiments are carried out on the FlickrLogos-32 database, and we evaluate the effect on recognition performance of synthetic versus real data augmentation, and image pre-processing. Moreover, we systematically investigate the benefits of different training choices such as class-balancing, sample-weighting and explicit modeling the background class (i.e. no-logo regions). Experimental results confirm the feasibility of the proposed method, that outperforms the methods in the state of the art.

show abstract

Section: Experimental Setup and Resultsmentioning

confidence: 99%

Deep learning for logo recognition

et al. 2017

View full text Add to dashboard Cite

show abstract

“…For this step, the generated charts are overlaid over real document images. Some works used similar approaches, showing results that were at par with the classic approaches [46][47][48].…”

Section: Datasetsmentioning

confidence: 99%

A Real-World Approach on the Problem of Chart Recognition Using Classification, Detection and Perspective Correction

Araújo

Chagas

Alves

et al. 2020

Sensors

View full text Add to dashboard Cite

Data charts are widely used in our daily lives, being present in regular media, such as newspapers, magazines, web pages, books, and many others. In general, a well-constructed data chart leads to an intuitive understanding of its underlying data. In the same way, when data charts have wrong design choices, a redesign of these representations might be needed. However, in most cases, these charts are shown as a static image, which means that the original data are not usually available. Therefore, automatic methods could be applied to extract the underlying data from the chart images to allow these changes. The task of recognizing charts and extracting data from them is complex, largely due to the variety of chart types and their visual characteristics. Other features in real-world images that can make this task difficult are photo distortions, noise, alignment, etc. Two computer vision techniques that can assist this task and have been little explored in this context are perspective detection and correction. These methods transform a distorted and noisy chart in a clear chart, with its type ready for data extraction or other uses. This paper proposes a classification, detection, and perspective correction process that is suitable for real-world usage, when considering the data used for training a state-of-the-art model for the extraction of a chart in real-world photography. The results showed that, with slight changes, chart recognition methods are now ready for real-world charts, when taking time and accuracy into consideration.

show abstract

“…Eggert et.al. [11] utilized CNNs to extract features from logos and determined their brand by classification with a set of Support Vector Machines (SVMs). Fast R-CNN [12] was used for the first time to retrieve logos from images by Iandola et al [20] and achieved superior results on the FlickrLogos-32 dataset [34].…”

Section: Related Workmentioning

confidence: 99%

Open Set Logo Detection and Retrieval

Tüzkö

Herrmann

Manger

et al. 2018

Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Application

View full text Add to dashboard Cite

Current logo retrieval research focuses on closed set scenarios. We argue that the logo domain is too large for this strategy and requires an open set approach. To foster research in this direction, a large-scale logo dataset, called Logos in the Wild, is collected and released to the public. A typical open set logo retrieval application is, for example, assessing the effectiveness of advertisement in sports event broadcasts. Given a query sample in shape of a logo image, the task is to find all further occurrences of this logo in a set of images or videos. Currently, common logo retrieval approaches are unsuitable for this task because of their closed world assumption. Thus, an open set logo retrieval method is proposed in this work which allows searching for previously unseen logos by a single query sample. A two stage concept with separate logo detection and comparison is proposed where both modules are based on task specific Convolutional Neural Networks (CNNs). If trained with the Logos in the Wild data, significant performance improvements are observed, especially compared with state-of-the-art closed set approaches.

show abstract

On the Benefit of Synthetic Data for Company Logo Detection

Cited by 33 publications

References 4 publications

Deep learning for logo recognition

Deep learning for logo recognition

A Real-World Approach on the Problem of Chart Recognition Using Classification, Detection and Perspective Correction

Open Set Logo Detection and Retrieval

Contact Info

Product

Resources

About