scispace - formally typeset
Search or ask a question
Author

Rim Walha

Other affiliations: University of Lyon
Bio: Rim Walha is an academic researcher from University of Sfax. The author has contributed to research in topics: Deep learning & Sparse approximation. The author has an hindex of 6, co-authored 14 publications receiving 122 citations. Previous affiliations of Rim Walha include University of Lyon.

Papers
More filters
Journal ArticleDOI
TL;DR: Significant improvements in visual quality and character recognition rates are achieved using the proposed approach, confirmed by a detailed comparative study with state-of-the-art upscaling approaches.
Abstract: Resolution enhancement has become a valuable research topic due to the rapidly growing need for high-quality images in various applications. Various resolution enhancement approaches have been successfully applied on natural images. Nevertheless, their direct application to textual images is not efficient enough due to the specificities that distinguish these particular images from natural images. The use of insufficient resolution introduces substantial loss of details which can make a text unreadable by humans and unrecognizable by OCR systems. To address these issues, a sparse coding-based approach is proposed to enhance the resolution of a textual image. Three major contributions are presented in this paper: (1) Multiple coupled dictionaries are learned from a clustered database and selected adaptively for a better reconstruction. (2) An automatic process is developed to collect the training database, which contains writing patterns extracted from high-quality character images. (3) A new local feature descriptor well suited for writing specificities is proposed for the clustering of the training database. The performance of these propositions is evaluated qualitatively and quantitatively on various types of low-resolution textual images. Significant improvements in visual quality and character recognition rates are achieved using the proposed approach, confirmed by a detailed comparative study with state-of-the-art upscaling approaches.

27 citations

Proceedings ArticleDOI
25 Aug 2013
TL;DR: Experimental results on character recognition illustrate that the proposed method outperforms the other methods, involved in this study, by providing better recognition rates.
Abstract: This paper addresses the problem of generating a super-resolved version of a low-resolution textual image by using Sparse Coding (SC) which suggests that image patches can be sparsely represented from a suitable dictionary. In order to enhance the learning performance and improve the reconstruction ability, we propose in this paper a multiple learned dictionaries based clustered SC approach for single text image super resolution. For instance, a large High-Resolution/Low-Resolution (HR/LR) patch pair database is collected from a set of high quality character images and then partitioned into several clusters by performing an intelligent clustering algorithm. Two coupled HR/LR dictionaries are learned from each cluster. Based on SC principle, local patch of a LR image is represented from each LR dictionary generating multiple sparse representations of the same patch. The representation that minimizes the reconstruction error is retained and applied to generate a local HR patch from the corresponding HR dictionary. The performance of the proposed approach is evaluated and compared visually and quantitatively to other existing methods applied to text images. In addition, experimental results on character recognition illustrate that the proposed method outperforms the other methods, involved in this study, by providing better recognition rates.

22 citations

Proceedings ArticleDOI
16 Dec 2012
TL;DR: The performance of the proposed Super-Resolution method is evaluated and compared visually and quantitatively to other existing SR methods applied to text images, and the influence of text image resolution on automatic recognition performance is examined.
Abstract: This paper addresses the problem of generating a super-resolved text image from a single low-resolution image. The proposed Super-Resolution (SR) method is based on sparse coding which suggests that image patches can be well represented as a sparse linear combination of elements from a suitably chosen learned dictionary. Toward this strategy, a High-Resolution/Low-Resolution (HR/LR) patch pair data base is collected from high quality character images. To our knowledge, it is the first generic database allowing SR of text images may be contained in documents, signs, labels, bills, etc. This database is used to train jointly two dictionaries. The sparse representation of a LR image patch from the first dictionary can be applied to generate a HR image patch from the second dictionary. The performance of such approach is evaluated and compared visually and quantitatively to other existing SR methods applied to text images. In addition, we examine the influence of text image resolution on automatic recognition performance and we further justify the effectiveness of the proposed SR method compared to others.

20 citations

Journal ArticleDOI
TL;DR: This study surveys methods that are mainly designed for enhancing low-resolution textual images in super-resolution (SR) task and criticises these methods and discusses areas which promise improvements in such task.
Abstract: Super-resolution (SR) task has become an important research area due to the rapidly growing interest for high quality images in various computer vision and pattern recognition applications. This has led to the emergence of various SR approaches. According to the number of input images, two kinds of approaches could be distinguished: single or multi-input based approaches. Certainly, processing multiple inputs could lead to an interesting output, but this is not the case mainly for textual image processing. This study focuses on single image-based approaches. Most of the existing methods have been successfully applied on natural images. Nevertheless, their direct application on textual images is not enough efficient due to the specificities that distinguish these particular images from natural images. Therefore, SR approaches especially suited for textual images are proposed in the literature. Previous overviews of SR methods have been concentrated on natural images application with no real application on the textual ones. Thus, this study aims to tackle this lack by surveying methods that are mainly designed for enhancing low-resolution textual images. The authors further criticise these methods and discuss areas which promise improvements in such task. To the best of the authors’ knowledge, this survey is the first investigation in the literature.

20 citations

Proceedings ArticleDOI
24 Aug 2014
TL;DR: A coupled dictionary learning approach is proposed to generate dual dictionaries representing coupled feature spaces to reduce computational complexity and improve image quality improvements.
Abstract: Sparse coding is widely known as a methodology where an input signal can be sparsely represented from a suitable dictionary. It was successfully applied on a wide range of applications like the textual image Super-Resolution. Nevertheless, its complexity limits enormously its application. Looking for a reduced computational complexity, a coupled dictionary learning approach is proposed to generate dual dictionaries representing coupled feature spaces. Under this approach, we optimize the training of a first dictionary for the high-resolution image space and then a second dictionary is simply deduced from the latter for the low-resolution image space. In contrast with the classical dictionary learning approaches, the proposed approach allows a noticeable speedup and a major simplification of the coupled dictionary learning phase both in terms of algorithm architecture and computational complexity. Furthermore, the resolution enhancement results achieved by applying the proposed approach on poorly resolved textual images lead to image quality improvements.

14 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: The proposed mixture of experts (MoE) method to jointly learn the feature space partition and local regression models can use much less local models and time to achieve comparable or superior results to state-of-the-art SISR methods, providing a highly practical solution to real applications.
Abstract: Using a global regression model for single image super-resolution (SISR) generally fails to produce visually pleasant output. The recently developed local learning methods provide a remedy by partitioning the feature space into a number of clusters and learning a simple local model for each cluster. However, in these methods the space partition is conducted separately from local model learning, which results in an abundant number of local models to achieve satisfying performance. To address this problem, we propose a mixture of experts (MoE) method to jointly learn the feature space partition and local regression models. Our MoE consists of two components: gating network learning and local regressors learning. An expectation-maximization (EM) algorithm is adopted to train MoE on a large set of LR/HR patch pairs. Experimental results demonstrate that the proposed method can use much less local models and time to achieve comparable or superior results to state-of-the-art SISR methods, providing a highly practical solution to real applications.

50 citations

Proceedings ArticleDOI
23 Aug 2015
TL;DR: The main conclusion of this competition is that SR systems may improve OCR performances by up to 16.55 points in accuracy compared with bicubic interpolation for the proposed low resolution images.
Abstract: This paper presents the first international competition on Text Image Super-Resolution (SR) and the ICDAR2015-TextSR dataset. We describe the core of the competition: interest, dataset generation and evaluation procedure, together with participating teams and their respective methods. The obtained results, along with baseline image upscaling schemes and state-of-the-art SR approaches are reported and commented. The main conclusion of this competition is that SR systems may improve OCR performances by up to 16.55 points in accuracy compared with bicubic interpolation for the proposed low resolution images.

33 citations

Posted Content
TL;DR: It is reported that the winning entry of text image super-resolution framework has largely improved the OCR performance with low-resolution images used as input, reaching an OCR accuracy score of 77.19%, which is comparable with that of using the original high- resolution images.
Abstract: Text image super-resolution is a challenging yet open research problem in the computer vision community. In particular, low-resolution images hamper the performance of typical optical character recognition (OCR) systems. In this article, we summarize our entry to the ICDAR2015 Competition on Text Image Super-Resolution. Experiments are based on the provided ICDAR2015 TextSR dataset (3) and the released Tesseract-OCR 3.02 system (1). We report that our winning entry of text image super-resolution framework has largely improved the OCR performance with low-resolution images used as input, reaching an OCR accuracy score of 77.19%, which is comparable with that of using the original high-resolution images (78.80%). Index Terms—super resolution; optical character recogni- tion.

33 citations

Journal ArticleDOI
TL;DR: Theoretical analysis show that the dictionary trained by deep learning features can improve in the ability to express image complex structure and texture, and it has more advantage than traditional artificial features dictionary.
Abstract: In traditional single image super-resolution (SR) methods based on dictionary model, a large number of image features are needed to train the SR dictionary. In general, these features are extracted by artificial rules, such as pixel gray, gradient, and texture structure. But, the dictionary model trained by these artificial features or their combinations has exhibited poor expression especially for the images with complex and rich structures. Therefore, how to improve the dictionary expression ability and make the dictionary have more accurate description of the image features is a problem worthy of further study. In this paper, based on the advantage of dictionary training and deep learning, a new method of single image SR based on deep learning features and dictionary model is proposed. The new algorithm contains three steps. First, the features of high-resolution and low-resolution training images are extracted by a Kernel deep learning network. Second, in the sparse representation of SR framework, the dictionary model is trained by these deep learning features. Finally, an LR image SR is completed. Theoretical analysis show that the dictionary trained by deep learning features can improve in the ability to express image complex structure and texture, and it has more advantage than traditional artificial features dictionary. The experimental results indicate that the proposed algorithm can produce good SR visual results than the comparison algorithm, such as Bicubic, sparse coding super-resolution, and super-resolution convolutional neural network. And the peak signal to noise ratio and structural similarity index measurement are improved, the Computation Time is also reasonable.

31 citations

Proceedings ArticleDOI
10 Dec 2015
TL;DR: The core idea of the proposed method is to recast the super-resolution task as a missing pixel problem, where the low-resolution image is considered as its high-resolution counterpart with many pixels missing in a structured manner.
Abstract: In this work, we have proposed a single face image super-resolution approach based on solo dictionary learning. The core idea of the proposed method is to recast the super-resolution task as a missing pixel problem, where the low-resolution image is considered as its high-resolution counterpart with many pixels missing in a structured manner. A single dictionary is therefore sufficient for recovering the super-resolved image by filling the missing pixels. In order to fill in 93.75% of the missing pixels when super-resolving a 16 × 16 low-resolution image to a 64 × 64 one, we adopt a whole image-based solo dictionary learning scheme. The proposed procedure can be easily extended to low-resolution input images with arbitrary dimensions, as well as high-resolution recovery images of arbitrary dimensions. Also, for a fixed desired super-resolution dimension, there is no need to retrain the dictionary when the input low-resolution image has arbitrary zooming factors. Based on a large-scale fidelity experiment on the FRGC ver2 database, our proposed method has outperformed other well established interpolation methods as well as the coupled dictionary learning approach.

31 citations