We propose an example-based super-resolution (SR) framework, which uses a single input image and, unlike most of the SR methods does not need an external high resolution (HR) dataset. Our SR approach is based in spars...
详细信息
ISBN:
(纸本)1595930361
We propose an example-based super-resolution (SR) framework, which uses a single input image and, unlike most of the SR methods does not need an external high resolution (HR) dataset. Our SR approach is based in sparse representation framework, which depends on a dictionary, learned from the given test image across different scales. In addition, our sparse coding focuses on the detail information of the image patches. Furthermore, in the above process we have considered non-local combination of similar patches in the input image, which assist us to improve the quality of the SR result. We demonstrate the effectiveness of our approach for intensity images as well as range images. Contemplating the importance of edges in images of both these modalities, we have added an edge preserving constraint that will maintain the continuity of edge related information to the input low resolution image. We investigate the performance of our approach by rigorous experimental analysis and it shows to perform better than some state-of-the-art SR approaches. Copyright 2014 ACM.
This paper proposes a novel algorithm for object tracking using Approximate Nearest Neighbour Fields (ANNF). ANNF maps have been previously used to address several problems like denoising, image completion, re-targeti...
详细信息
ISBN:
(纸本)1595930361
This paper proposes a novel algorithm for object tracking using Approximate Nearest Neighbour Fields (ANNF). ANNF maps have been previously used to address several problems like denoising, image completion, re-targeting and medical image analysis. In this paper, we deal with the challenging problem of visual object tracking, using patch flow. The proposed method uses FeatureMatch to find patch corre- spondence between successive frames, enabling the tracker to find the best match for the object in the next frame. Based on the flow, each patch is labeled as either foreground or background. The proportion of FG/BG/border patches contributing to each pixel determines its final label. We show that objects can be successfully tracked across videos, under challenging conditions such as scale variations, illumination changes and occlusion using the proposed technique. Copyright 2014 ACM.
Action recognition from 3D depth maps/skeleton has been an active research area in computervision in the recent past. In this paper, we propose a method for action recognition by learning the sequence of various pose...
详细信息
ISBN:
(纸本)1595930361
Action recognition from 3D depth maps/skeleton has been an active research area in computervision in the recent past. In this paper, we propose a method for action recognition by learning the sequence of various poses involved while performing an action. Each pose in the sequence is represented as a set of 3D edge vectors connecting important joint points in the skeleton and 3D trajectory vectors connecting the joint point locations in the previous frame with that in the current frame. The training samples of each action class, represented as sequences of poses, are time normalized using Dynamic Time Warping(DTW) and average pooled to construct the model sequence representing the action. Action recognition on a test sequence is achieved by finding its nearest model sequence in terms of a proposed distance measure. The effectiveness of the proposed algorithm is evaluated on two challenging datasets: Berkeley Multimodal Human Action Database and MSR Action 3D dataset. Copyright 2014 ACM.
In this paper, we propose a framework for recognizing the group dynamics embedded in social gathering videos. We aim to identify interacting sub-groups present in a scene. In particular we are interested in identifyin...
详细信息
ISBN:
(纸本)1595930361
In this paper, we propose a framework for recognizing the group dynamics embedded in social gathering videos. We aim to identify interacting sub-groups present in a scene. In particular we are interested in identifying the participants converging to form a group, the participants dispersing from a group and the ones in static groups. We use the linear cyclic pursuit (LCP) based framework to model the collective motion. The proposed algorithm employs trajectories of individuals over a period of time to estimate the model parameters. We show that the details of group dynamics are hidden in the eigenvalues and eigenvectors of the pursuit matrix. The experiments are done on the simulated data as well as on the real gathering videos. The results show a promising scope of the proposed approach. Copyright 2014 ACM.
This paper presents a method for segmentation of human brain magnetic resonance (MR) image sequences based on a 3D human brain model (triangulated mesh). The brain model is composed of four components, namely, cerebru...
详细信息
ISBN:
(纸本)1595930361
This paper presents a method for segmentation of human brain magnetic resonance (MR) image sequences based on a 3D human brain model (triangulated mesh). The brain model is composed of four components, namely, cerebrum, cerebellum, brain stem and pituitary gland. Synthesized image sequences are extracted from the model at regular intervals for sagittal and coronal views as done in MR imaging. To align a series of real MR images with these synthesized cross-sections, an efficient dynamic programming based computational technique has been used that obtains the optimal synthesized cross-section sequence corresponding to the series of MR images. For automatic segmentation of anatomical structures from the MR images, each aligned synthesized cross-section is overlaid on the corresponding physical MR image by carrying out appropriate geometric transformation. This transformation produces model guided boundaries for four segments corresponding to cerebrum, cerebellum, brain stem and pituitary gland. Subsequently, these initial contours are further refined by the method of active contouring, which provides segmentation of 3D MR images into the above mentioned four parts. The proposed method compares well with the recently proposed Charged Fluid Model (CFM) based approach and level set segmentation method in terms of accuracy at a significantly lower computational cost. Copyright 2014 ACM.
Approaches to articulated kinematic chain analysis suffer from a lack of robustness in segmentation which affects all upstream tasks. In this work, we consider revolute chains (all joints are hinges, or ball-and-socke...
详细信息
ISBN:
(纸本)1595930361
Approaches to articulated kinematic chain analysis suffer from a lack of robustness in segmentation which affects all upstream tasks. In this work, we consider revolute chains (all joints are hinges, or ball-and-socket), and show that Sparse Spectral Clustering (SSC) is more likely to agree on tracked data points that are far from the joint. We then develop two variants of consensual clustering which marks tracks as outliers if different classifiers do not agree. This leaves a large set of points in each link, and enables robust segmentation for many real-life situations. In addition to results on Hopkins-155 [18] and Yan-Pollefeys [21, 22, 23] datasets, we also release additional datasets involving revolute chains. Copyright is held by the authors.
Registration of partially overlapping 3D point clouds of an object is the initial phase in the 3D modeling pipeline. The automatic coarse alignment of a pair of 3D images is usually performed by 3D feature matching. R...
详细信息
ISBN:
(纸本)1595930361
Registration of partially overlapping 3D point clouds of an object is the initial phase in the 3D modeling pipeline. The automatic coarse alignment of a pair of 3D images is usually performed by 3D feature matching. Robust estimators like RANSAC are employed for 3D transformation estimation from point correspondences obtained by feature matching, in the presence of outliers. The number of RANSAC iterations required depends directly on the number of correspondences and inliers. Many variants of RANSAC have been proposed for the computervision tasks like stereo matching, structure and motion estimation, image retrieval etc. This paper presents a study on the potential of two widely stated RANSAC variants - PROSAC and LoSAC - for 3D registration. Further, a new algorithm -ProLoSAC - which combines the relative merits of the two is proposed. The proposed algorithm has been evaluated on different pairs of partially overlapping 3D views of three different 3D models. The results indicate that the proposed algorithm finds the best transformation in less iteration compared to the other algorithms. Copyright 2014 ACM.
We present an approach for learning low- and high-level fingerprint structures in an unsupervised manner, which we use for enhancement of fingerprint images and estimation of orientation fields, frequency images, and ...
详细信息
ISBN:
(纸本)1595930361
We present an approach for learning low- and high-level fingerprint structures in an unsupervised manner, which we use for enhancement of fingerprint images and estimation of orientation fields, frequency images, and region masks. We incorporate the use of a convolutional deep belief network to learn features from greyscale, clean fingerprint images. We also show that reconstruction performed by the learnt network works as a suitable enhancement of the fingerprint, and hierarchical probabilistic inference is able to estimate overall fingerprint structures as well. Our approach performs better than Gabor-based enhancement and short time Fourier transform-assisted enhancement on images it was trained on. We further use information from the learnt features in first layer, which are short and oriented ridge structures, to extract the orientation field, frequency image, and region mask of input fingerprints. Copyright 2014 ACM.
Magnetic resonance imaging (MRI) is an essential soft tissue imaging technique. Major limitation of this imaging technique is due to its slow acquisition. MR image reconstruction using the compressed sensing (CS) has ...
详细信息
ISBN:
(纸本)1595930361
Magnetic resonance imaging (MRI) is an essential soft tissue imaging technique. Major limitation of this imaging technique is due to its slow acquisition. MR image reconstruction using the compressed sensing (CS) has mainly two research areas, one, how efficiently MRI data can be acquired and the other is how fast the reconstruction can be done without degrading the quality of the reconstructed images. From the recent study, it is observed that the TV-1 -2 model for MR image reconstruction from random under-sampled data gives the best result. In this paper, we propose a novel high throughput MR image reconstruction algorithm without compromising the quality. The experimental results show that the proposed method is quite efficient compared to the state-of-the-art MR image reconstruction techniques based on compressed sensing in terms of the cpu time and the quality of the reconstructed images. Copyright 2014 ACM.
In this paper a novel method to address the problem of enhancement and binarization of historic inscription images is presented. Inscription images in general have no distinction between the text layer and background ...
详细信息
ISBN:
(纸本)1595930361
In this paper a novel method to address the problem of enhancement and binarization of historic inscription images is presented. Inscription images in general have no distinction between the text layer and background layer due to absence of color difference and possess highly correlated signals and noise. The proposed technique provides a suitable method to separate the text layer from the historic inscription images by considering the problem as blind source separation which aims to calculate the independent components from a linear mixture of source signals, by maximizing a contrast function based on higher order cumulants. Further, the results are compared with existing ICA based techniques like NGFICA and Fast-ICA. Copyright 2014 ACM.
暂无评论