Active shape models—their training and application
Computer Vision and Image Understanding
Object Matching Using Deformable Templates
IEEE Transactions on Pattern Analysis and Machine Intelligence
Deformable template models: a review
Signal Processing - Special issue on deformable models and techniques for image and signal processing
Digital Image Processing
Representation and detection of shapes in images
Representation and detection of shapes in images
Template-based Automatic Segmentation of Masseter Using Prior Knowledge
SSIAI '06 Proceedings of the 2006 IEEE Southwest Symposium on Image Analysis and Interpretation
Straightening Caenorhabditis elegans images
Bioinformatics
Template Matching Techniques in Computer Vision: Theory and Practice
Template Matching Techniques in Computer Vision: Theory and Practice
Grayscale template-matching invariant to rotation, scale, translation, brightness and contrast
PSIVT'07 Proceedings of the 2nd Pacific Rim conference on Advances in image and video technology
Pattern recognition for high throughput zebrafish imaging using genetic algorithm optimization
PRIB'10 Proceedings of the 5th IAPR international conference on Pattern recognition in bioinformatics
Representation and detection of deformable shapes
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Bioscientific data processing and modeling
ISoLA'12 Proceedings of the 5th international conference on Leveraging Applications of Formal Methods, Verification and Validation: applications and case studies - Volume Part II
| Hi-index | 0.00 |
Images with known shapes can be analyzed through template matching and segmentation; in this approach the question is how to represent a known shape. The digital representation to which the shape is sampled, the image, may be subject to noise. If we compare a known and idealized shape to the real-life occurrences, a considerable variation is observed. With respect to the shape, this variation can have affine characteristics as well as non-linear deformations. We propose a method based on a deformable template starting from a low-level vision and proceeding to high-level vision. The latter part is typically application dependent, here the shapes are annotated according to an ideal template and are normalized by a straightening process. The underlying algorithm can deal with a range of deformations and does not restrict to a single instance of a shape in the image. Experimental results from an application of the algorithm illustrate low error rate and robustness of the method. The life sciences are a challenging area in terms of applications in which a considerable variation of the shape of object instances is observed. Successful application of this method would be typically suitable for automated procedures such as those required for biomedical high-throughput screening. As a case study, we, therefore, illustrate our method in this context, i.e. retrieving instances of shapes obtained from a screening experiment.