Scene Text Eraser
This addresses privacy protection for individuals by hiding text like phone numbers in images, but it is incremental as it applies existing inpainting techniques to a specific domain.
The authors tackled the problem of personal information leakage in natural scene images by proposing a scene text erasing method using an inpainting CNN model, which drastically decreased precision, recall, and f-score on the ICDAR2013 benchmark compared to direct text detection.
The character information in natural scene images contains various personal information, such as telephone numbers, home addresses, etc. It is a high risk of leakage the information if they are published. In this paper, we proposed a scene text erasing method to properly hide the information via an inpainting convolutional neural network (CNN) model. The input is a scene text image, and the output is expected to be text erased image with all the character regions filled up the colors of the surrounding background pixels. This work is accomplished by a CNN model through convolution to deconvolution with interconnection process. The training samples and the corresponding inpainting images are considered as teaching signals for training. To evaluate the text erasing performance, the output images are detected by a novel scene text detection method. Subsequently, the same measurement on text detection is utilized for testing the images in benchmark dataset ICDAR2013. Compared with direct text detection way, the scene text erasing process demonstrates a drastically decrease on the precision, recall and f-score. That proves the effectiveness of proposed method for erasing the text in natural scene images.