Abstract
Many Computer Vision problems arise from information processing of data sources with nuisance variances like scale, orientation, contrast, perspective foreshortening or - in medical imaging - staining and local warping. In most cases these variances can be stated a priori and can be used to improve the generalization of recognition algorithms. We propose a novel supervised feature learning approach, which efficiently extracts information from these constraints to produce interpretable, transformation-invariant features. The proposed method can incorporate a large class of transformations, e.g., shifts, rotations, change of scale, morphological operations, non-linear distortions, photometric transformations, etc. These features boost the discrimination power of a novel image classification and segmentation method, which we call Transformation-Invariant Convolutional Jungles (TICJ). We test the algorithm on two benchmarks in face recognition and medical imaging, where it achieves state of the art results, while being computationally significantly more efficient than Deep Neural Networks.
Keywords
Artificial intelligenceComputer scienceConvolutional neural networkImage warpingPattern recognition (psychology)Invariant (physics)Transformation (genetics)Computer visionFeature extractionSegmentationA priori and a posterioriDeep learningGeneralizationMathematics
Related Publications
Modeling scenes with local descriptors and latent aspects
We present a new approach to model visual scenes in image collections, based on local invariant features and probabilistic latent space models. Our formulation provides answers ...
Face Description with Local Binary Patterns: Application to Face Recognition
This paper presents a novel and efficient facial image representation based on local binary pattern (LBP) texture features. The face image is divided into several regions from w...
Multi-Image Matching Using Multi-Scale Oriented Patches
This paper describes a novel multi-view matching framework based on a new type of invariant feature. Our features are located at Harris corners in discrete scale-space and orien...
Reliable feature matching across widely separated views
We present a robust method for automatically matching features in images corresponding to the same physical point on an object seen from two arbitrary viewpoints. Unlike convent...
Multiresolution histograms and their use for recognition
The histogram of image intensities is used extensively for recognition and for retrieval of images and video from visual databases. A single image histogram, however, suffers fr...
Publication Info
- Year
- 2015
- Type
- article
- Pages
- 3043-3051
- Citations
- 26
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
26
OpenAlex
Cite This
Dmitry Laptev,
Joachim M. Buhmann
(2015).
Transformation-Invariant Convolutional Jungles.
, 3043-3051.
https://doi.org/10.1109/cvpr.2015.7298923
Identifiers
- DOI
- 10.1109/cvpr.2015.7298923