# A Masked Bounding-Box Selection Based ResNet Predictor for Text Rotation Prediction

arXiv: https://arxiv.org/abs/2209.09198 · HTML: https://mlsanity.com/paper/2209.09198/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 18 references that are in the map.
- First posted on arXiv 6 Sep 2022.

## Builds on (most cited first, 10 of 10)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards](https://mlsanity.com/paper/2008.02693/) (2020)
- [ReFormer: The Relational Transformer for Image Captioning](https://mlsanity.com/paper/2107.14178/) (2021)
- [Journalistic Guidelines Aware News Image Captioning](https://mlsanity.com/paper/2109.02865/) (2021)
- [Crossing-Domain Generative Adversarial Networks for Unsupervised Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/2008.11882/) (2020)
- [Latent Part-of-Speech Sequences for Neural Machine Translation](https://mlsanity.com/paper/1908.11782/) (2019)
- [Adaptive Activation Network and Functional Regularization for Efficient and Flexible Deep Multi-Task Learning](https://mlsanity.com/paper/1911.08065/) (2019)
- [Learning Tuple Compatibility for Conditional OutfitRecommendation](https://mlsanity.com/paper/2008.08189/) (2020)
- [Recognizing License Plates in Real-Time](https://mlsanity.com/paper/1906.04376/) (2019)
- [A Novel Approach to Skew-Detection and Correction of English Alphabets for OCR](https://mlsanity.com/paper/1801.00824/) (2018)

## Abstract (arXiv)

The existing Optical Character Recognition (OCR) systems are capable of recognizing images with horizontal texts. However, when the rotation of the texts increases, it becomes harder to recognizing these texts. The performance of the OCR systems decreases. Thus predicting the rotations of the texts and correcting the images are important. Previous work mainly uses traditional Computer Vision methods like Hough Transform and Deep Learning methods like Convolutional Neural Network. However, all of these methods are prone to background noises commonly existing in general images with texts. To tackle this problem, in this work, we introduce a new masked bounding-box selection method, that incorporating the bounding box information into the system. By training a ResNet predictor to focus on the bounding box as the region of interest (ROI), the predictor learns to overlook the background noises. Evaluations on the text rotation prediction tasks show that our method improves the performance by a large margin.