Abstract: In this paper, we address two complex issues: 1) Text frame classification and 2) Multi-oriented text detection in video text frame. We first divide a video frame into 16 blocks and propose a combination of wavelet and median-moments with k-means clustering at the block level to identify probable text blocks. For each probable text block, the method applies the same combination of feature with k-means clustering over a sliding window running through the blocks to identify potential text candidates. We introduce a new idea of symmetry on text candidates in each block based on the observation that pixel distribution in text exhibits a symmetric pattern. The method integrates all blocks containing text candidates in the frame and then all text candidates are mapped on to a Sobel edge map of the original frame to obtain text representatives. To tackle the multi-orientation problem, we present a new method called Angle Projection Boundary Growing (APBG) which is an iterative algorithm and works based on a nearest neighbor concept. APBG is then applied on the text representatives to fix the bounding box for multi-oriented text lines in the video frame. Directional information is used to eliminate false positives. Experimental results on a variety of datasets such as non-horizontal, horizontal, publicly available data (Hua’s data) and ICDAR-03 competition data (camera images) show that the proposed method outperforms existing methods proposed for video and the state of the art methods for scene text as well.

Abstract: This paper presents a new model for the task of scene text visual question answering. In this task questions about a given image can only be answered by reading and understanding scene text. Current state of the art models for this task make use of a dual attention mechanism in which one attention module attends to visual features while the other attends to textual features. A possible issue with this is that it makes difficult for the model to reason jointly about both modalities. To fix this problem we propose a new model that is based on an single attention mechanism that attends to multi-modal features conditioned to the question. The output weights of this attention module over a grid of multi-modal spatial features are interpreted as the probability that a certain spatial location of the image contains the answer text to the given question. Our experiments demonstrate competitive performance in two standard datasets with a model that is faster than previous methods at inference time. Furthermore, we also provide a novel analysis of the ST-VQA dataset based on a human performance study. Supplementary material, code, and data is made available through this link.

Abstract: 0,624 JCR
Word spotting is the process of retrieving all instances of a queried keyword from a digital library of document images. In this paper we evaluate the performance of different word descriptors to assess the advantages and disadvantages of statistical and structural models in a framework of query-by-example word spotting in historical documents. We compare four word representation models, namely sequence alignment using DTW as a baseline reference, a bag of visual words approach as statistical model, a pseudo-structural model based on a Loci features representation, and a structural approach where words are represented by graphs. The four approaches have been tested with two collections of historical data: the George Washington database and the marriage records from the Barcelona Cathedral. We experimentally demonstrate that statistical representations generally give a better performance, however it cannot be neglected that large descriptors are difficult to be implemented in a retrieval scenario where word spotting requires the indexation of data with million word images.