This paper concentrates on developing an effective approach for decompressing JPEG document images. Our main goal is targeted to time-critical applications, especially to those situated on mobile network infrastructures. To this aim, the proposed approach is designed to work either in the transform domain or image spatial plane. Specifically, the image blocks are first classified into smooth blocks (e.g., background and uniform regions) and non-smooth blocks (e.g., text, graphics, and line-drawings). Next, the smooth blocks are fully decoded in the transform domain by minimizing the total block boundary variation, which is very efficient to compute. For decoding non-smooth blocks, a novel text model is presented that accounts for the specifics of document content. In addition, an efficient optimization algorithm is introduced to reconstruct the non-smooth blocks. The proposed approach has been validated by extensive experiments, demonstrating a significant improvement of visual quality, assuming that document images have been encoded at low bit rates and thus are subject to severe distortion.

This paper presents a new approach for symbol localization in line-drawing images using junction features and geometry consistency checking. The proposed system first detects junction points, and then characterizes them by very compact, distinctive, and varying-length descriptors. The detected junctions are used to decompose a document image into a set of smooth primitives composing of isolated shapes (e.g., isolated circles and straight lines) and curve segments bounded between either two junctions or a junction and an end-point. These primitives are then associated with a new set of key points to form a complete and compact representation of a graphical document. Next, key point matching is performed to find the correspondences among the key points of the query and those of database documents. The obtained matches are finally refined by a new and efficient algorithm to deal with the problem of geometry consistency checking. Our experiments showed that the proposed system is very time- and memory-efficient, and provides high accuracy rate of symbol localization.

In this paper, we propose a new method to detect local interest points as junctions in line-drawing images. Our approach takes advantages of different aspects. Firstly, we extract skeleton of image and then construct a Skeleton Connective Graph with the expectation that it provides a first level of junction detection from shapes. Secondly, instead of employing low-level operators to detect junctions as described in many traditional techniques, our method works at path level taking different skeleton branches into account to gain robustness. Thirdly, we exploit the benefits of wavelet transform (e.g. multi-resolution analysis, discontinuity detection, fast computation, less sensitive to noises) to efficiently detect the dominant points from 1D representations of the paths. Finally, a post-process of pruning and connecting the skeleton segments is performed to discard false detected points and to refine the skeleton. We present in experiments interesting results compared to different methods.

This paper presents a new approach for logo detection exploiting contour based features. At first stage, pre-processing, contour detection and line segmentation are done. These processes result in set of Outer Contour Strings (OCSs) describing each graphics and text parts of the documents. Then, the logo detection problem is defined as a region scoring problem. Two types of features, coarse and finer ones, are computed from each OCS. Coarse features catch graphical and domain information about OCSs, such as logo positions and aspect ratios. Finer features characterize the contour regions using a gradient based representation. Using these features, we employ regression fitting to score how likely an OCS takes part of a logo region. A final step of correction helps with the wrong segmentation cases. We present experiments done on the Tobacco-800 dataset, and compare our results with the literature. We obtain interesting results compared to the best systems.