Region-based Discriminative Feature Pooling for Scene Text Recognition

2014-06-01 · CVPR 2014 6 · Chen-Yu Lee, Anurag Bhardwaj, Wei Di, Vignesh Jagadeesh, Robinson Piramuthu

We present a new feature representation method for scene text recognition problem, particularly focusing on improving scene character recognition. Many existing methods rely on Histogram of Oriented Gradient (HOG) or part-based models, which do not span the feature space well for characters in natural scene images, especially given large variation in fonts with cluttered backgrounds. In this work, we propose a discriminative feature pooling method that automatically learns the most informative sub-regions of each scene character within a multi-class classification framework, whereas each sub-region seamlessly integrates a set of low-level image features through integral images. The proposed feature representation is compact, computationally efficient, and able to effectively model distinctive spatial structures of each individual character class. Extensive experiments conducted on challenging datasets (Chars74K, ICDAR'03, ICDAR'11, SVT) show that our method significantly outperforms existing methods on scene character classification and scene text recognition tasks.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

General Classification Multi-class Classification Scene Text Recognition

Learning Important Spatial Pooling Regions for Scene Classification

2014-06-01 · CVPR 2014 6 · Di Lin, Cewu Lu, Renjie Liao, Jiaya Jia

We address the false response influence problem when learning and applying discriminative parts to construct the mid-level representation in scene classification. It is often caused by the complexity of latent image stru…

Classification General Classification Scene Classification

Harvesting Discriminative Meta Objects with Deep CNN Features for Scene Classification

2015-10-06 · ICCV 2015 12 · Ruobing Wu, Baoyuan Wang, Wenping Wang, Yizhou Yu

Recent work on scene classification still makes use of generic CNN features in a rudimentary manner. In this ICCV 2015 paper, we present a novel pipeline built upon deep CNN features to harvest discriminative visual obje…

Clustering General Classification Region Proposal Scene Classification+1

A Novel Dual-pooling Attention Module for UAV Vehicle Re-identification

2023-06-25 · Xiaoyan Guo, Jie Yang, Xinyu Jia, Chuanyan Zang 외

Vehicle re-identification (Re-ID) involves identifying the same vehicle captured by other cameras, given a vehicle image. It plays a crucial role in the development of safe cities and smart cities. With the rapid growth …

Single Particle Analysis Triplet Vehicle Re-Identification

Context-aware Attentional Pooling (CAP) for Fine-grained Visual Classification

2021-01-17 · Ardhendu Behera, Zachary Wharton, Pradeep Hewage, Asish Bera

Deep convolutional neural networks (CNNs) have shown a strong ability in mining discriminative object pose and parts information for image recognition. For fine-grained recognition, context-aware rich feature representat…

Fine-Grained Image Classification General Classification Informativeness Object

Learning to Recognize Actions on Objects in Egocentric Video with Attention Dictionaries

2021-02-16 · Swathikiran Sudhakaran, Sergio Escalera, Oswald Lanz

We present EgoACO, a deep neural architecture for video action recognition that learns to pool action-context-object descriptors from frame level features by leveraging the verb-noun structure of action labels in egocent…

Action Recognition Object Temporal Action Localization