The Experts below are selected from a list of 33 Experts worldwide ranked by ideXlab platform
Subhashis Banerjee - One of the best experts on this subject based on the ideXlab platform.
-
Recognition of partially occluded Objects using neural network based Indexing
Pattern Recognition, 1999Co-Authors: Navin Rajpal, Santanu Chaudhury, Subhashis BanerjeeAbstract:In this paper, a new neural network based Indexing scheme has been proposed for recognition of planar shapes. Local contour segment-based-invariants have been used for Indexing. Object contours have been obtained using a new algorithm which combines advantages of region growing and edge detection. Neighbourhood constraints have been applied on the results of Indexing for combining hypotheses generated through the Indexing scheme. Composite hypotheses have been verified using a distance transform based algorithm. Experimental results, on real images of varying complexity of a reasonably large database of Objects have established the robustness of the method.
Jaekyu Lee - One of the best experts on this subject based on the ideXlab platform.
-
THREE DIMENSIONAL PATTERN RECOGNITION USING FEATURE-BASED Indexing AND RULE-BASED SEARCH
2003Co-Authors: Jaekyu LeeAbstract:Three Dimensional Pattern Recognition using Feature-Based Indexing and Rule-Based Search by Jae-Kyu Lee Dr. Georg Mauer, Examination Committee Chair Professor of Mechanical Engineering University of Nevada, Las Vegas In flexible automated manufacturing, robots can perform routine operations as well as recover from atypical events, provided that process-relevant information is available to the robot controller. Real time vision is among the most versatile sensing tools, yet the reliability of machine-based scene interpretation can be questionable. The effort described here is focused on the development of machine-based vision methods to support autonomous nuclear fuel manufacturing operations in hot cells. This thesis presents a method to efficiently recognize 3D Objects from 2D images based on feature-based Indexing. Object recognition is the identification of correspondences between parts of a current scene and stored views of known Objects, using chains of segments or Indexing vectors. To create indexed Object models, characteristic model image features are extracted during preprocessing. Feature vectors representing model Object contours are acquired from several points of view around each Object and stored. Recognition is the process of matching stored views with features or patterns detected in a test scene.
-
Feature-based pattern recognition and Object identification for telerobotics
IEEE International Conference on Mechatronics 2005. ICM '05., 1Co-Authors: Jaekyu Lee, G.f. MauerAbstract:This paper presents a method to efficiently recognize 3D Objects from 2D images based on feature-based Indexing. Object recognition is the identification of correspondences between parts of a current scene and stored views of known Objects, using chains of segments or Indexing vectors. To create indexed Object models, the characteristic model image features are extracted during preprocessing. Feature vectors representing model Object contours from several points of view around each Object are acquired and stored. At recognition time, the Indexing vectors with the highest match probability are retrieved from the model image database, using a search strategy that employs knowledge-based (KB) search criteria. The knowledge-based simplifies the recognition process and minimizes the number of iterations and memory usage. Candidate Objects in camera images are matched with the stored set of reference views by probabilistic viewing interpolation. The experimental results indicate that feature-based Indexing in combination with a knowledge-based system will be a useful methodology for automatic target recognition (ATR).
Navin Rajpal - One of the best experts on this subject based on the ideXlab platform.
-
Recognition of partially occluded Objects using neural network based Indexing
Pattern Recognition, 1999Co-Authors: Navin Rajpal, Santanu Chaudhury, Subhashis BanerjeeAbstract:In this paper, a new neural network based Indexing scheme has been proposed for recognition of planar shapes. Local contour segment-based-invariants have been used for Indexing. Object contours have been obtained using a new algorithm which combines advantages of region growing and edge detection. Neighbourhood constraints have been applied on the results of Indexing for combining hypotheses generated through the Indexing scheme. Composite hypotheses have been verified using a distance transform based algorithm. Experimental results, on real images of varying complexity of a reasonably large database of Objects have established the robustness of the method.
Dave G. Mumby - One of the best experts on this subject based on the ideXlab platform.
-
Systemic and intra-rhinal-cortical 17-β estradiol administration modulate Object-recognition memory in ovariectomized female rats.
Hormones and behavior, 2013Co-Authors: Nicole J. Gervais, Sofia Jacob, Wayne G. Brake, Dave G. MumbyAbstract:Abstract Previous studies using the novel-Object-preference (NOP) test suggest that estrogen (E) replacement in ovariectomized rodents can lead to enhanced novelty preference. The present study aimed to determine: 1) whether the effect of E on NOP performance is the result of enhanced preference for novelty, per se, or facilitated Object-recognition memory, and 2) whether E affects NOP performance through actions it has within the perirhinal cortex/entorhinal cortex region (PRh/EC). Ovariectomized rats received either systemic chronic low 17-β estradiol (E2; ~ 20 pg/ml serum) replacement alone or in combination with systemic acute high administration of estradiol benzoate (EB; 10 μg), or in combination with intracranial infusions of E2 (244.8 pg/μl) or vehicle into the PRh/EC. For one of the intracranial experiments, E2 was infused either immediately before, immediately after, or 2 h following the familiarization (i.e., learning) phase of the NOP test. In light of recent evidence that raises questions about the internal validity of the NOP test as a method of Indexing Object-recognition memory, we also tested rats on a delayed nonmatch-to-sample (DNMS) task of Object recognition following systemic and intra-PRh/EC infusions of E2. Both systemic acute and intra-PRh/EC infusions of E enhanced novelty preference, but only when administered either before or immediately following familiarization. In contrast, high E (both systemic acute and intra-PRh/EC) impaired performance on the DNMS task. The findings suggest that while E2 in the PRh/EC can enhance novelty preference, this effect is probably not due to an improvement in Object-recognition abilities.
Santanu Chaudhury - One of the best experts on this subject based on the ideXlab platform.
-
Recognition of partially occluded Objects using neural network based Indexing
Pattern Recognition, 1999Co-Authors: Navin Rajpal, Santanu Chaudhury, Subhashis BanerjeeAbstract:In this paper, a new neural network based Indexing scheme has been proposed for recognition of planar shapes. Local contour segment-based-invariants have been used for Indexing. Object contours have been obtained using a new algorithm which combines advantages of region growing and edge detection. Neighbourhood constraints have been applied on the results of Indexing for combining hypotheses generated through the Indexing scheme. Composite hypotheses have been verified using a distance transform based algorithm. Experimental results, on real images of varying complexity of a reasonably large database of Objects have established the robustness of the method.