Arbitrarily-Oriented Text Detection in Low Light Natural Scene Images

• Published in: IEEE transactions on multimedia 2021, Vol.23, p.2706-2720
• Main Authors: Xue, Minglong, Shivakumara, Palaiahnakote, Zhang, Chao, Xiao, Yao, Lu, Tong, Pal, Umapada, Lopresti, Daniel, Yang, Zhibo
• Format: Article
• Language: English
• Subjects: arbitrarily-oriented text detection; Artificial neural networks; COLD features; convolutional neural network; Convolutional neural networks; Datasets; Daylight; Feature extraction; gaussian pyramid filter; Homomorphic filter; Image contrast; Image enhancement; Image quality; Image segmentation; Licenses; Machine learning; Proposals
• ISSN: 1520-9210; 1941-0077
• DOI: 10.1109/TMM.2020.3015037

Text detection in low light natural scene images is challenging due to poor image quality and low contrast. Unlike most existing methods that focus on well-lit (normally daylight) images, the proposed method considers much darker natural scene images. For this task, our method first integrates spatial and frequency domain features through fusion to enhance fine details in the image. Next, we use Maximally Stable Extremal Regions (MSER) for detecting text candidates from the enhanced images. We then introduce Cloud of Line Distribution (COLD) features, which capture the distribution of pixels of text candidates in the polar domain. The extracted features are sent to a Convolution Neural Network (CNN) to correct the bounding boxes for arbitrarily oriented text lines by removing false positives. Experiments are conducted on a dataset of low light images to evaluate the proposed enhancement step. The results show our approach is more effective compared to existing methods in terms of standard quality measures, namely, BRISQE, NIQE and PIQE. In addition, experimental results on a variety of standard benchmark datasets, namely, ICDAR 2013, ICDAR 2015, SVT, Total-Text, ICDAR 2017-MLT and CTW1500, show that the proposed approach not only produces better results for low light images, at the same time it is also competitive for daylight images.