Shape from Shading Using Wavelets
Dongbin Chan,Feng Dong +1 more
- 17 Dec 2007
- pp 86-91
TL;DR: A new algorithm that allows us to generate 3D geometry from a single monocular image through the optimisation of an objective function by using wavelet to recover geometry from the input image.
read more
Abstract: This paper presents a new algorithm that allows us to generate 3D geometry from a single monocular image through the optimisation of an objective function. Weighted smoothness constraint is designed and added to the objective function to provide adequate smooth restraints in accordance with local image gradients. By using wavelet, the objective function is minimised to recover geometry from the input image. Results and comparisons with those from existing methods are provided in the paper. These results demonstrate the better performance of the proposed method over the existing methods.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Figures
Table 4. Evaluation Results for the detection of objects in the test set. 
Figure 1. Schematic diagram of the detection and classification process 
Figure 2. A high jump image with the detected horizontal bar, body and face. 
Table 1. Example of spatial rules 
Table 2. Evaluation Results for the detection of objects. The first three columns correspond to the number of occurrences of instances of each object class, the recall and precision of the object detection method. The following three columns are percentages in respect to the object correctly identified, conveying information about the area matching: mean area Recall (MAR), mean area precision (MAP) and Mean Area Match between annotations (MAM). 
Table 3. Evaluation results for image classification – Confusion matrix
Citations
Human action annotation, modeling and analysis based on implicit user interaction
TL;DR: This work sets a new and ambitious goal: to recognize, model and properly use “average user’s” selections, preferences and perception, for dynamically extracting content semantics in video streams.
15
Assessing the role of spatial relations for the object recognition task
Annette Morales-González,Edel García-Reyes +1 more
- 08 Nov 2010
TL;DR: This work proposes a spatial descriptor to represent topological and orientation/directional relationships, which are obtained by means of combinatorial pyramids, and runs an experiment to evaluate the expressiveness of this representation.
Automatic annotation of image databases based on implicit crowdsourcing, visual concept modeling and evolution
TL;DR: A novel approach for automatically annotating image databases that properly combines several innovative modules for semantically annotating images, providing an intelligent way to even annotate completely non-annotated content or correct wrongly annotated images.
References
Color indexing
Michael J. Swain,Dana H. Ballard +1 more
TL;DR: In this paper, color histograms of multicolored objects provide a robust, efficient cue for indexing into a large database of models, and they can differentiate among a large number of objects.
6.1K
Texture analysis and classification with tree-structured wavelet transform
T. Chang,C.-C.J. Kuo +1 more
TL;DR: A progressive texture classification algorithm which is not only computationally attractive but also has excellent performance is developed and is compared with that of several other methods.
Unsupervised segmentation of color-texture regions in images and video
Y. Deng,B.S. Manjunath +1 more
TL;DR: The focus of this work is on spatial segmentation, where a criterion for "good" segmentation using the class-map is proposed and applying the criterion to local windows in theclass-map results in the "J-image," in which high and low values correspond to possible boundaries and interiors of color-texture regions.
A method for enforcing integrability in shape from shading algorithms
Robert T. Frankot,Rama Chellappa +1 more
TL;DR: An approach for enforcing integrability, a particular implementation of the approach, an example of its application to extending an existing shape-from-shading algorithm, and experimental results showing the improvement that results from enforcingIntegrability are presented.
1.1K
•Dissertation
Shape from shading: a method for obtaining the shape of a smooth opaque object from one view
Berthold K. P. Horn
- 01 Nov 1970
TL;DR: A method will be described for finding the shape of a smooth opaque object from a monocular image, given a knowledge of the surface photometry, the position of the light-source and certain auxiliary information to resolve ambiguities, complementary to the use of stereoscopy.
717