Electrical Engineeringhttp://repository.iitgn.ac.in/handle/123456789/4872017-07-23T02:46:22Z2017-07-23T02:46:22ZObject proposals based significance map for image retargetingPatel, DiptibenRaman, Shanmuganathanhttp://repository.iitgn.ac.in/handle/123456789/30292017-07-13T10:46:51Z2017-09-09T00:00:00ZObject proposals based significance map for image retargeting
Patel, Diptiben; Raman, Shanmuganathan
2017-09-09T00:00:00ZIterative spectral clustering for unsupervised object localizationVora, AdityaRaman, Shanmuganathanhttp://repository.iitgn.ac.in/handle/123456789/30192017-07-04T06:07:53Z2017-06-01T00:00:00ZIterative spectral clustering for unsupervised object localization
Vora, Aditya; Raman, Shanmuganathan
This paper addresses the problem of unsupervised object localization in an image. Unlike previous supervised and weakly supervised algorithms that require bounding box or image level annotations for training classifiers in order to learn features representing the object, we propose a simple yet effective technique for localization using iterative spectral clustering. This iterative spectral clustering approach along with appropriate cluster selection strategy in each iteration naturally helps in searching of object region in the image. In order to estimate the final localization window, we group the proposals obtained from the iterative spectral clustering step based on the perceptual similarity, and average the coordinates of the proposals from the top scoring groups. We benchmark our algorithm on challenging datasets like Object Discovery and PASCAL VOC 2007, achieving an average CorLoc percentage of 51% and 35% respectively which is comparable to various other weakly supervised algorithms despite being completely unsupervised.
2017-06-01T00:00:00ZFlow-free video object segmentationVora, AdityaRaman, Shanmuganathanhttp://repository.iitgn.ac.in/handle/123456789/30182017-07-04T06:03:23Z2017-06-01T00:00:00ZFlow-free video object segmentation
Vora, Aditya; Raman, Shanmuganathan
Segmenting foreground object from a video is a challenging task because of the large deformations of the objects, occlusions, and background clutter. In this paper, we propose a frame-by-frame but computationally efficient approach for video object segmentation by clustering visually similar generic object segments throughout the video. Our algorithm segments various object instances appearing in the video and then perform clustering in order to group visually similar segments into one cluster. Since the object that needs to be segmented appears in most part of the video, we can retrieve the foreground segments from the cluster having maximum number of segments, thus filtering out noisy segments that do not represent any object. We then apply a track and fill approach in order to localize the objects in the frames where the object segmentation framework fails to segment any object. Our algorithm performs comparably to the recent automatic methods for video object segmentation when benchmarked on DAVIS dataset while being computationally much faster.
2017-06-01T00:00:00ZApproximate reflection symmetry in a point set: theory and algorithm with an applicationNagar, RajendraRaman, Shanmuganathanhttp://repository.iitgn.ac.in/handle/123456789/30172017-07-04T05:56:42Z2017-06-01T00:00:00ZApproximate reflection symmetry in a point set: theory and algorithm with an application
Nagar, Rajendra; Raman, Shanmuganathan
We propose an algorithm to detect approximate reflection symmetry present in a set of volumetrically distributed points belonging to Rd containing a distorted reflection symmetry pattern. We pose the problem of detecting approximate reflection symmetry as the problem of establishing the correspondences between the points which are reflections of each other and determining the reflection symmetry transformation. We formulate an optimization framework in which the problem of establishing the correspondences amounts to solving a linear assignment problem and the problem of determining the reflection symmetry transformation amounts to an optimization problem on a smooth Riemannian product manifold. The proposed approach estimates the symmetry from the distribution of the points and is descriptor independent. We evaluate the robustness of our approach by varying the amount of distortion in a perfect reflection symmetry pattern where we perturb each point by a different amount of perturbation. We demonstrate the effectiveness of the method by applying it to the problem of 2-D reflection symmetry detection along with relevant comparisons.
2017-06-01T00:00:00Z