We apply a biologically inspired model of visual object recognition to the multiclass object categorization problem. Our model modifies that of Serre, Wolf, and Poggio. As in that work, we first apply Gabor filters at...
详细信息
We present a novel interactive system and its user interface for removing objects in digital pictures. Our system consists of two components: (i) (partially supervised/automatic) image segmentation (2], and (ii) (guid...
详细信息
ISBN:
(纸本)0769523722
We present a novel interactive system and its user interface for removing objects in digital pictures. Our system consists of two components: (i) (partially supervised/automatic) image segmentation (2], and (ii) (guided) texture synthesis [3].
This paper presents a generative model based approach to deal with occlusions in vision problems which can be formulated as MAP-estimation problems. The approach is generic and targets applications in diverse domains ...
详细信息
This paper presents a robust and accurate vision-based augmented reality system for surgical navigation. The key point of our system is a robust and real-time monocular vision algorithm to estimate the 3D pose of surg...
详细信息
This paper presents a robust and accurate vision-based augmented reality system for surgical navigation. The key point of our system is a robust and real-time monocular vision algorithm to estimate the 3D pose of surgical tools, utilizing specially designed code markers and Kalman filter-based position updating. The vision system is not impaired by occlusion and rapid change of illumination. The augmented reality system superimposes the 3D object wireframe onto the live viewing image taken from the surgical microscope as well as displaying other useful navigation information, while allowing the surgeons to freely change its room and focus for viewing. The experimental results verified the robustness and usefulness of the system, and acquired the image registration error less than 2 mm.
In this paper we present an efficient hierarchical approach to structure from motion for long image sequences. There are two key elements to our approach: accurate 3D reconstruction for each segment and efficient bund...
详细信息
In this paper we present an efficient hierarchical approach to structure from motion for long image sequences. There are two key elements to our approach: accurate 3D reconstruction for each segment and efficient bundle adjustment for the whole sequence. The image sequence is first divided into a number of segments so that feature points can be reliably tracked across each segment. Each segment has a long baseline to ensure accurate 3D reconstruction. To efficiently bundle adjust 3D structures from all segments, we reduce the number of frames in each segment by introducing `virtual key frames'. The virtual frames encode the 3D structure of each segment along with its uncertainty but they form a small subset of the original frames. Our method achieves significant speedup over conventional bundle adjustment methods.
We propose human action detection based on a successive convex matching scheme. Human actions are represented as sequences of postures and specific actions are detected in video by matching the time-coupled posture se...
详细信息
Nonnegative tensor factorization (NTF) is a recent multiway (multilinear) extension of nonnegative matrix factorization (NMF), where nonnegativity constraints are imposed on the CANDECOMP/PARAFAC model. In this paper ...
详细信息
ISBN:
(纸本)9781424411795
Nonnegative tensor factorization (NTF) is a recent multiway (multilinear) extension of nonnegative matrix factorization (NMF), where nonnegativity constraints are imposed on the CANDECOMP/PARAFAC model. In this paper we consider the Tucker model with nonnegativity constraints and develop a new tensor factorization method, referred to as nonnegative Tucker decomposition (NTD). The main contributions of this paper include: (1) multiplicative updating algorithms for NTD;(2) an initialization method for speeding up convergence;(3) a sparseness control method in tensor factorization. Through several computervision examples, we show the useful behavior of the NTD, over existing NTF and NMF methods.
This paper presents a new technique for modelling object classes (such as laces) and matching the model to novel images from the object class. The technique can be used for a variety of image analysis applications inc...
详细信息
ISBN:
(纸本)0818684976
This paper presents a new technique for modelling object classes (such as laces) and matching the model to novel images from the object class. The technique can be used for a variety of image analysis applications including face recognition, object verification and facial expression analysis. The model, called a hierarchical morphable model, is "learned" from example images (partioned into components) and their correspondences. This is an extension to the work on morphable models described in previous papers ([6] [5], [12]). Hierarchical morphable models are shown to find good matches to novel lace images and are also robust to partial occlusion.
We introduce in this paper two probabilistic reasoning models (PRM-I and PRM-2) which combine the Principal Component Analysis (PCA) technique and the Bayes classifier and show their feasibility on the face recognitio...
详细信息
ISBN:
(纸本)0818684976
We introduce in this paper two probabilistic reasoning models (PRM-I and PRM-2) which combine the Principal Component Analysis (PCA) technique and the Bayes classifier and show their feasibility on the face recognition problem. The conditional probability density function for each class is modeled using the within class scatter and the Maximum A Posteriori (MAP) classification rule is implemented in the reduced PCA subspace. Experiments carried out using 1107 facial images corresponding to 369 subjects (with 169 subjects having duplicate images) from the FERET database show that the PRM approach compares favorably against the two well-known methods for face recognition the Eigenfaces and Fisherfaces.
An approach for analysis and representation of facial dynamics for recognition of facial expressions from image sequences is proposed. The algorithms we develop utilize optical flow computation to identify the directi...
详细信息
ISBN:
(纸本)0818658258
An approach for analysis and representation of facial dynamics for recognition of facial expressions from image sequences is proposed. The algorithms we develop utilize optical flow computation to identify the direction of rigid and non-rigid motions that are caused by human facial expressions. A mid-level symbolic representation that is motivated by linguistic and psychological considerations is developed. recognition of six facial expressions, as well as eye blinking, on a large set of image sequences is reported.
暂无评论