Related papers: Query by String word spotting based on character b…

In large-scale image retrieval, many indexing methods have been proposed to narrow down the searching scope of retrieval. The features extracted from images usually are of high dimensions or unfixed sizes due to the existence of key points.…

In this dissertation we report results of our research on dense distributed representations of text data. We propose two novel neural models for learning such representations. The first model learns representations at the document level,…

Unlabeled data is often used to learn representations which can be used to supplement baseline features in a supervised learner. For example, for text applications where the words lie in a very high dimensional space (the size of the…

In this paper, we describe our end-to-end content-based image retrieval system built upon Elasticsearch, a well-known and popular textual search engine. As far as we know, this is the first time such a system has been implemented in…

End-to-end text spotting is a vital computer vision task that aims to integrate scene text detection and recognition into a unified framework. Typical methods heavily rely on Region-of-Interest (RoI) operations to extract local features and…

Image search systems based on local descriptors typically achieve orientation invariance by aligning the patches on their dominant orientations. Albeit successful, this choice introduces too much invariance because it does not guarantee…

We propose Hierarchical Text Spotter (HTS), a novel method for the joint task of word-level text spotting and geometric layout analysis. HTS can recognize text in an image and identify its 4-level hierarchical structure: characters, words,…

This paper presents a novel method for efficient image retrieval, based on a simple and effective hashing of CNN features and the use of an indexing structure based on Bloom filters. These filters are used as gatekeepers for the database of…

In this work, we present a unified model that can handle both Keyword Spotting and Word Recognition with the same network architecture. The proposed network is comprised of a non-recurrent CTC branch and a Seq2Seq branch that is further…

In this paper, we propose a novel approach for text classification based on clustering word embeddings, inspired by the bag of visual words model, which is widely used in computer vision. After each word in a collection of documents is…

Scene Text Recognition (STR) is the problem of recognizing the correct word or character sequence in a cropped word image. To obtain more robust output sequences, the notion of bidirectional STR has been introduced. So far, bidirectional…

We have benchmarked the maximum obtainable recognition accuracy on various word image datasets using manual segmentation and a currently available commercial OCR. We have developed a Matlab program, with graphical user interface, for…

Document alignment and registration play a crucial role in numerous real-world applications, such as automated form processing, anomaly detection, and workflow automation. Traditional methods for document alignment rely on image-based…

Despite recent advances in end-to-end speech recognition methods, the output tends to be biased to the training data's vocabulary, resulting in inaccurate recognition of proper nouns and other unknown terms. To address this issue, we…

We revisit a self-supervised method that segments unlabelled speech into word-like segments. We start from the two-stage duration-penalised dynamic programming method that performs zero-resource segmentation without learning an explicit…

Unconstrained handwritten text recognition remains challenging for computer vision systems. Paragraph text recognition is traditionally achieved by two models: the first one for line segmentation and the second one for text line…

This paper addresses the problem of learning word image representations: given the cropped image of a word, we are interested in finding a descriptive, robust, and compact fixed-length representation. Machine learning techniques can then be…

Large-scale data is of crucial importance for learning semantic segmentation models, but annotating per-pixel masks is a tedious and inefficient procedure. We note that for the topic of interactive image segmentation, scribbles are very…

This paper proposes a novel privacy-preserving semantic segmentation method that can use independent keys for each client and image. In the proposed method, the model creator and each client encrypt images using locally generated keys, and…

This paper presents a deep learning approach for image retrieval and pattern spotting in digital collections of historical documents. First, a region proposal algorithm detects object candidates in the document page images. Next, deep…