Logo detection in real-world scene

Logo detection in real-world scene images is an important problem with applications in advertisement and marketing. Existing general-purpose object detection methods require large training data with annotations for every logo class. These methods do not satisfy the incremental demand of logo classes necessary for practical deployment since it is practically impossible to have such annotated data for new unseen logo. In this work, we develop an easy-to-implement query-based logo detection and localization system by employing a one-shot learning technique using off the shelf neural network components. Given an image of a query logo, our model searches for logo within a given target image and predicts the possible location of the logo by estimating a binary segmentation mask. The proposed model consists of a conditional branch and a segmentation branch. The former gives a conditional latent representation of the given query logo which is combined with feature maps of the segmentation branch at multiple scales in order to obtain the matching location of the query logo in a target image. Feature matching between the latent query representation and multi-scale feature maps of segmentation branch using simple concatenation operation followed by 1 × 1 convolution layer makes our model scale-invariant. Despite its simplicity, our query-based logo retrieval framework achieved superior performance in FlickrLogos-32 and TopLogos-10 dataset over different existing baseline methods.

Results (English) 2:

Logo detection in Real-world scene images is an important problem with applications in advertisement and marketing. Existing general-purpose object detection methods require large training data with annotations for every logo class. This methods do not satisfy the incremental demand of logo classes necessary for practical deployment since it is practically impossible to have such annotated data for new unseen logo. In This work, we develop an easy-to-implement query-based logo detection and localization system by employing a one-shot learning technique using off the shelf neural network components. Given an image of a query logo, our model searches for logo within a Given target image and predicts the possible location of the logo by estimating a binary segmentation mask. The proposed model consists of a conditional branch and a segmentation branch. The former gives a conditional latent representation of the Given query logo which is combined with feature maps of the segmentation branch at multiple scales in order to obtain the matching location of the query logo in a target image. Feature matching between the latent query representation and Multi-scale feature maps of segmentation branch using simple concatenation operation followed by 1 × 1 convolution layer makes our model scale-invariant. Despite its simplicity, our query-based logo retrieval framework achieved a superior performance in FlickrLogos-32 and TopLogos-10 dataset over different Existing baseline methods.

Results (English) 3:

In the real world, image detection is an important issue in advertising and marketing. The general target detection method requires large training data for all logo methods. The actual needs of logical classes that do not meet the growing needs, because it is impossible. For example, in this work, we developed an easy to implement query based log detection. Using a-shot learning technology of hierarchical neural network component based on GIS to realize system localization In the given target image and predicted possible position Through the estimation of binary segmentation, a segmentation model based on condition is proposed. The branch table provides a condition to represent a given query log, which is combined with attribute mapping. In order to get the matching position of the query in the target image, the segmentation branches are classified on multi-scale. Recent query representation and simple branches of multiscale feature mapping The connection operation follows The query based logo retrieval framework achieves excellent performance in different aspects of flickr-logos-32 and toplogo-10 datasets. Existing baseline methods.