A Hybrid Representation of Word Images for Keyword Spotting

Keyword spotting in handwritten document images using supervised and unsupervised representations

“…With the recent advent of deep learning-based KWS methods, a standard solution for example model architectures is to normalize input images to fixed size [69,104,121,166]. For instance, Wei and co-workers propose a normalization by resizing all input images to a standard size of 310 pixel width and 50 height in [121], whereas in [120], they resize all input images so that they have the same width (either pure or by padding white pixels) and aspect ratio. Wicht et al [150,151] normalize the word images to remove the skew and slant of the text using [228].…”

“…Even more promising results have been introduced by the recent bloom of adversarial learning and Generative Adversarial Networks (GANs) [319] which basically employ generative modeling to augment data in limited datasets. In our proposed method, we use a similar strategy to render KWS models such as the PHOCNet, robust [32,34,121,150,180,235]. In several computer vision problems, deep features have often led to superior performance over the standard use of the employed network.…”