Search

Over the recent years, a number of deep learning approaches are successfully introduced to tackle the problem of image in-painting for achieving better perceptual effects. However, there still exist obvious hole-edge artifacts in these deep learning-based approaches, which need to be rectified before they become useful for practical applications. In this article, we propose an iteration-driven in-painting approach, which combines the deep context model with the backpropagation mechanism to fine-tune the learning-based in-painting process and hence, achieves further improvement over the existing state of the arts. Our iterative approach fine tunes the image generated by a pretrained deep context model via backpropagation using a weighted context loss. Extensive experiments on public available test sets, including the CelebA, Paris Streets, and PASCAL VOC 2012 dataset, show that our proposed method achieves better visual perceptual quality in terms of hole-edge artifacts compared with the state-of-the-art in-painting methods using various context models. [ABSTRACT FROM AUTHOR]

Being able to predict the salient object is of fundamental importance in image processing and computer vision. With numerous approaches proposed for automatic image and video salient object detection, much less work has been dedicated to detecting and segmenting salient objects from light fields. In this article, based on the intrinsic characteristics of light fields, we carefully explore the complementary coherence among multiple cues including spatial, edge and depth information, and elaborately design a multi-task collaborative network for light field salient object detection. More specifically, the correlation mechanisms among edge detection, depth inference and salient object detection are carefully investigated to facilitate the representative saliency features. We first model the coherence among low-level features and heuristic semantic priors, as well as the edge information. Subsequently, the depth-oriented saliency features are derived from the geometry of light fields, in which the 3D convolution operation is leveraged with powerful representation capability to model the disparity correlations among multiple viewpoint images. Finally, a feature-enhanced salient object generator is developed to integrate these complementary saliency features, leading to the final salient object predictions for light fields. Quantitative and qualitative experiments demonstrate the superiority of our proposed model against the state-of-the-art methods over the public light field salient object detection datasets. [ABSTRACT FROM AUTHOR]

This paper describes a novel system for mobile robot localization in an indoor environment, using concepts like homography and matching borrowed from the context of stereo and content-based image retrieval techniques (CBIR). To deal with variations with respect to viewpoint and camera positions, a group of points of interest (POI) is extracted to represent the image for robust matching. To cope with illumination changes, we propose to produce a contrast image for each video frame by using the root mean square strategy, thus all the POIs are extracted from the corresponding contrast images to provide perceptually consistent measurement of image content. To achieve effective image matching, modeling of robot behavior for model constrained matching is proposed, where normalized cross correlation is employed for local matching to determine corresponding POI pairs followed by homography based global optimization using RANSAC. Meanwhile, application of specific constraints also helps to exclude irrelevant frames in the training set to further improve the efficiency and robustness. The proposed approach has been successfully applied to the Robot Vision task for the ImageCLEF workshop, and the experimental results have fully demonstrated the high-quality performance of our approaches in terms of both precision and robustness. The system and approach outlined in this paper was ranked the second best in the optional task group in ImageCLEF 2009. In addition to demonstrating the merits of our approach in isolation, we also illustrate the benefits of our proposed approach in comparison with other submissions. [ABSTRACT FROM AUTHOR]

As existing video processing technology is primarily developed in the pixel domain yet digital video is stored in compressed format, any application of those techniques to compressed videos would require decompression. For discrete cosine transform (DCT)-based MPEG compressed videos, the computing cost of standard row-by-mw and column-by-column inverse DCT (LDCT) transforms for a block of 8 × 8 elements requires 4096 multiplications and 4032 additions, although practical implementation only requires 1024 multiplications and 896 additions. In this paper, we propose a new algorithm to extract videos directly from MPEG compressed domain (DCT domain) without full LDCT, which is described in three extraction schemes: 1) video extraction in 2 × 2 blocks with four coefficients; 2) video extraction in 4 x 4 blocks with four DCT coefficients; and 3) video extraction in 4 × 4 blocks with nine DCT coefficients. The computing cost incurred only requires 8 additions and no multiplication for the first scheme, 2 multiplication and 28 additions for the second scheme, and 47 additions (no multiplication) for the third scheme. Extensive experiments were carried out, and the results reveal that: 1) the extracted video maintains competitive quality in terms of visual perception and inspection and 2) the extracted videos preserve the content well in comparison with those fully decompressed ones in terms of histogram measurement. As a result, the proposed algorithm will provide useful tools in bridging the gap between pixel domain and compressed domain to facilitate content analysis with low latency and high efficiency such as those applications in surveillance videos, interactive multimedia, and image processing. [ABSTRACT FROM AUTHOR]

To improve efficiency of compressed image retrieval, we propose a novel statistical feature extraction algorithm in this paper to characterize the image content directly in its compressed domain. The statistical feature extracted is mainly through computing a set of moments directly from DCT coefficients without involving full decompression or inverse DCT. Following the algorithm design, a content-based image retrieval system is implemented especially targeting retrieving joint picture expert group compressed images. Theoretical analysis and experimental results support that the system is robust to translation, rotation and scale transform with minor disturbance, and the system achieves good performances in terms of retrieval efficiency and effectiveness. [Copyright &y& Elsevier]

Presents information on a study which proposed a content adaptive information loss distribution scheme for designing a low-cost and rate-controllable image codec. Description of a content adaptive information loss distribution scheme; Low-cost approach for rate control design; Conclusions.

Abstract: This paper presents a comparative study of two machine learning techniques for recognizing handwritten Arabic words, where hidden Markov models (HMMs) and dynamic Bayesian networks (DBNs) were evaluated. The work proposed is divided into three stages, namely preprocessing, feature extraction and classification. Preprocessing includes baseline estimation and normalization as well as segmentation. In the second stage, features are extracted from each of the normalized words, where a set of new features for handwritten Arabic words is proposed, based on a sliding window approach moving across the mirrored word image. The third stage is for classification and recognition, where machine learning is applied using HMMs and DBNs. In order to validate the techniques, extensive experiments were conducted using the IFN/ENIT database which contains 32,492 Arabic words. Experimental results and quantitative evaluations showed that HMM outperforms DBN in terms of higher recognition rate and lower complexity. [Copyright &y& Elsevier]