Multi-Modal Image Captioning for the Visually Impaired
This addresses a critical need for blind people who rely on image descriptions, as up to 21% of their questions involve text in images, though it is an incremental improvement over existing methods.
The paper tackled the problem of image captioning for the visually impaired by incorporating textual data from images, which is often ignored in current systems, and achieved a 35% improvement in CIDEr and 16.2% in SPICE scores on the VizWiz dataset.
One of the ways blind people understand their surroundings is by clicking images and relying on descriptions generated by image captioning systems. Current work on captioning images for the visually impaired do not use the textual data present in the image when generating captions. This problem is critical as many visual scenes contain text. Moreover, up to 21% of the questions asked by blind people about the images they click pertain to the text present in them. In this work, we propose altering AoANet, a state-of-the-art image captioning model, to leverage the text detected in the image as an input feature. In addition, we use a pointer-generator mechanism to copy the detected text to the caption when tokens need to be reproduced accurately. Our model outperforms AoANet on the benchmark dataset VizWiz, giving a 35% and 16.2% performance improvement on CIDEr and SPICE scores, respectively.