Leveraging Smart Devices for Scene Text Preserved Image Stylization: A Deep Gaming Approach

Bagi, Randheer; Mohanty, Sabyasachi; Dutta, Tanima; Gupta, Hari Prabhat

doi:10.1109/mmul.2020.2988394

Cited by 6 publications

(1 citation statement)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Unlike the characters in printed documents, scene texts are more difficult to recognize due to the large variations in backgrounds, textures, fonts, and illumination conditions. Scene images have attracted importance largely due to its various practical applications, such as robot navigation, autonomous vehicles, human-computer interaction, and multilingual translation [1], [3]- [7]. Multi-language text spotting is an essential but challenging task.…”

Section: Introductionmentioning

confidence: 99%

Cluttered TextSpotter: An End-to-End Trainable Light-Weight Scene Text Spotter for Cluttered Environment

2020

Self Cite

View full text Add to dashboard Cite

Scene text spotting aims at simultaneously localizing and recognizing text instances, symbols, and logos in natural scene images. Scene text detection and recognition approaches have received immense attention in computer vision research community. The presence of partial occlusion or truncation artifact due to the cluttered background of scene images creates an obstacle in perceiving the text instances, which makes the process of spotting very complex. In this paper, we propose a lightweight scene text spotter that can address the issue of cluttered environment of scene images. It is an end-to-end trainable deep neural network that uses local part information, global structural features, and context cue information of oriented region proposals for spotting text instances. It helps to localize in scene images with background clutters, where partially occluded text parts, truncation artifacts, and perspective distortions are present. We mitigate the problem of misclassification caused by inter-class interference by exploring inter-class separability and intra-class compactness. We also incorporate multi-language character segmentation and word-level recognition in a lightweight recognition module. We have used six publicly available benchmark datasets in different smart devices to illustrate the efficacy of the network.

show abstract

Section: Introductionmentioning

confidence: 99%