Real-time Lexicon-free Scene Text Retrieval

Mining text from natural scene and video images: A survey

“…Despite the complexity of handwritten word spotting, deep CNNs have been tuned using transfer learning to provide efficient word‐spotting (Benabdelaziz et al, 2020). In addition, Mafla et al (2020) have proposed a single shot CNN architecture for scene text retrieval to obtain word bounding boxes as a compact representation of spotted words. The problem has been modeled as a nearest neighbor search of the textual representation of the input query over the outputs of the CNN obtained from an image database.…”

“…The problem has been modeled as a nearest neighbor search of the textual representation of the input query over the outputs of the CNN obtained from an image database. The proposed is fast and suitable for multilingual and real‐time text spotting in videos (Mafla et al, 2020).…”

“…Compared with feature and learning based methods, the hybrid or combination approach for text spotting from videos has received less attention from researchers. Recently, Mafla et al (2020) have proposed a real‐time word spotting method based on a fully convolutional neural network to detect and recognize text in a single pass. The PHOC descriptor has been used to universally encode the presence of a specific character in a visual region of the proposed bounding box of a language‐specific text string using a CNN based model (YOLOv2 object detection network).…”

“…The proposed PHOC version is a binary vector of size 820 dimensions constructed by concatenating the L2 to the L6 unigram levels along with 2 levels of the 50 most common English language bigrams. As the proposed network uses a smaller filter size in the model's last filter, it can perform in real‐time (Mafla et al, 2020). Moreover, using a bigger PHOC along with more unigram and bigram levels can provide superior scene text retrieval results compared with the state of the art results on different datasets, including multilingual datasets (Mafla et al, 2020).…”

“…As the proposed network uses a smaller filter size in the model's last filter, it can perform in real‐time (Mafla et al, 2020). Moreover, using a bigger PHOC along with more unigram and bigram levels can provide superior scene text retrieval results compared with the state of the art results on different datasets, including multilingual datasets (Mafla et al, 2020). However, this method is language‐specific and may not be easily applicable to other scripts.…”