Object (computer science)

About: Object (computer science) is a research topic. Over the lifetime, 106024 publications have been published within this topic receiving 1360115 citations. The topic is also known as: obj & Rq.

3-D Object Retrieval and Recognition With Hypergraph Analysis

Abstract: View-based 3-D object retrieval and recognition has become popular in practice, e.g., in computer aided design. It is difficult to precisely estimate the distance between two objects represented by multiple views. Thus, current view-based 3-D object retrieval and recognition methods may not perform well. In this paper, we propose a hypergraph analysis approach to address this problem by avoiding the estimation of the distance between objects. In particular, we construct multiple hypergraphs for a set of 3-D objects based on their 2-D views. In these hypergraphs, each vertex is an object, and each edge is a cluster of views. Therefore, an edge connects multiple vertices. We define the weight of each edge based on the similarities between any two views within the cluster. Retrieval and recognition are performed based on the hypergraphs. Therefore, our method can explore the higher order relationship among objects and does not use the distance between objects. We conduct experiments on the National Taiwan University 3-D model dataset and the ETH 3-D object collection. Experimental results demonstrate the effectiveness of the proposed method by comparing with the state-of-the-art methods.

One-Shot Video Object Segmentation

Abstract: This paper tackles the task of semi-supervised video object segmentation, i.e., the separation of an object from the background in a video, given the mask of the first frame. We present One-Shot Video Object Segmentation (OSVOS), based on a fully-convolutional neural network architecture that is able to successively transfer generic semantic information, learned on ImageNet, to the task of foreground segmentation, and finally to learning the appearance of a single annotated object of the test sequence (hence one-shot). Although all frames are processed independently, the results are temporally coherent and stable. We perform experiments on two annotated video segmentation databases, which show that OSVOS is fast and improves the state of the art by a significant margin (79.8% vs 68.0%).

Contour-based object tracking with occlusion handling in video acquired using mobile cameras

Abstract: We propose a tracking method which tracks the complete object regions, adapts to changing visual features, and handles occlusions. Tracking is achieved by evolving the contour from frame to frame by minimizing some energy functional evaluated in the contour vicinity defined by a band. Our approach has two major components related to the visual features and the object shape. Visual features (color, texture) are modeled by semiparametric models and are fused using independent opinion polling. Shape priors consist of shape level sets and are used to recover the missing object regions during occlusion. We demonstrate the performance of our method in real sequences with and without object occlusions.

Electronic document verification system and method

Abstract: The integrity or the signator of an electronic document can be verified by embedding a security object, for example, supported by an object linking and embedding (OLE) capability, in the electronic document at a location selected by the signator. The embedded security object includes security information and an identifier for invoking the processing of the security information. The security information may include a document digest that characterizes the electronic document at the time the security object was embedded, a signature digest that identifies the signator and that characterizes the instance of the embedded security object, and the signator's electronic chop, which may be the signator's digitized signature or other graphic image. In addition, the security information can be encrypted using either private key encryption or public key encryption. When the electronic document is later displayed, the identifier invokes processing that decrypts the security information and calculates the document digest based on the current state of the electronic document. The signator of the electronic document can be verified based upon the result of the decryption. The integrity of the electronic document can be verified if the decrypted document digest matches the calculated document digest. If the signator and the document integrity are confirmed, the electronic chop is displayed in the document. If, however, the signator or document integrity are not verified, the electronic chop is not displayed. In addition, a warning message may be displayed if verification fails.