Location-Aware Feature Selection for Scene Text Detection

04/23/2020
by   Zengyuan Guo, et al.
3

Direct regression-based natural scene text detection methods have already achieved promising performances. However, for the bounding box prediction, they usually utilize a fixed feature selection way to select features used to predict different components, such as the distance to the boundary or the rotation angle, which may limit selection flexibility of each component prediction and thus degrades the performance of the algorithm. To address this issue, we propose a novel method called Location-Aware Feature Selection (LAFS). It separately learns the confidence of different locations' features for each component and then selects the features with the highest confidence to form a combination of the most suitable features. In other words, LAFS uses a learnable feature selection way to flexibly pinpoint feature combinations used to predict more accurate bounding boxes. After adding LAFS, our network has a large performance improvement without efficiency loss. It achieved state-of-the-art performance with single-model and single-scale testing, outperforming all existing regression-based detectors.

READ FULL TEXT

page 1

page 2

page 4

page 7

page 8

research
03/14/2018

Rotation-Sensitive Regression for Oriented Scene Text Detection

Text in natural images is of arbitrary orientations, requiring detection...
research
06/06/2019

Omnidirectional Scene Text Detection with Sequential-free Box Discretization

Scene text in the wild is commonly presented with high variant character...
research
05/07/2021

Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections

Model ensembles are becoming one of the most effective approaches for im...
research
09/07/2016

Object Tracking via Dynamic Feature Selection Processes

DFST proposes an optimized visual tracking algorithm based on the real-t...
research
02/02/2022

Decoupled IoU Regression for Object Detection

Non-maximum suppression (NMS) is widely used in object detection pipelin...
research
06/15/2018

Crime Event Embedding with Unsupervised Feature Selection

We present a novel event embedding algorithm for crime data that can joi...
research
04/21/2021

A windowed correlation based feature selection method to improve time series prediction of dengue fever cases

The performance of data-driven prediction models depends on the availabi...

Please sign up or login with your details

Forgot password? Click here to reset