Face Sketch Matching via Coupled Deep Transform Learning
Shruti Nagpal,Maneet Singh,Richa Singh,Mayank Vatsa,Afzel Noore,Angshul Majumdar +5 more
- pp 5429-5438
Reads0
Chats0
TLDR
DeepTransformer as mentioned in this paper learns a transformation and mapping function between the features of two domains, which can be applied with any existing learned or hand-crafted feature and can be used for sketch-to-sketch matching.Abstract:
Face sketch to digital image matching is an important challenge of face recognition that involves matching across different domains. Current research efforts have primarily focused on extracting domain invariant representations or learning a mapping from one domain to the other. In this research, we propose a novel transform learning based approach termed as DeepTransformer, which learns a transformation and mapping function between the features of two domains. The proposed formulation is independent of the input information and can be applied with any existing learned or hand-crafted feature. Since the mapping function is directional in nature, we propose two variants of DeepTransformer: (i) semi-coupled and (ii) symmetrically-coupled deep transform learning. This research also uses a novel IIIT-D Composite Sketch with Age (CSA) variations database which contains sketch images of 150 subjects along with age-separated digital photos. The performance of the proposed models is evaluated on a novel application of sketch-to-sketch matching, along with sketch-to-digital photo matching. Experimental results demonstrate the robustness of the proposed models in comparison to existing state-of-the-art sketch matching algorithms and a commercial face recognition system.read more
Citations
More filters
Posted Content
Deep Learning for Free-Hand Sketch: A Survey
TL;DR: A comprehensive survey of the deep learning techniques oriented at free-hand sketch data, and the applications that they enable can be found in this article, where the authors highlight the essential differences between sketch data and other data modalities, e.g., natural photos.
Posted Content
Learning Structure and Strength of CNN Filters for Small Sample Size Training
TL;DR: SSF-CNN is proposed which focuses on learning the "structure" and "strength" of filters and significantly reduces the number of parameters required for training while providing high accuracies on the test databases.
Proceedings ArticleDOI
Learning Structure and Strength of CNN Filters for Small Sample Size Training
TL;DR: SSF-CNN as discussed by the authors uses dictionary-based filter learning to learn the structure and strength of the filter for small sample size problems such as newborn face recognition and Omniglot.
Posted Content
Deep Learning for Free-Hand Sketch: A Survey and A Toolbox
TL;DR: A comprehensive survey of the deep learning techniques oriented at free-hand sketch data, and the applications that they enable.
Journal ArticleDOI
Learning Structural Representations via Dynamic Object Landmarks Discovery for Sketch Recognition and Retrieval
TL;DR: A novel architecture to dynamically discover the object landmarks and learn the discriminative structural representations is proposed and compared with several state-of-the-art methods on two challenging datasets, TU-Berlin and Sketchy.
References
More filters
Proceedings ArticleDOI
Orthogonal matching pursuit: recursive function approximation with applications to wavelet decomposition
TL;DR: A modification to the matching pursuit algorithm of Mallat and Zhang (1992) that maintains full backward orthogonality of the residual at every step and thereby leads to improved convergence is proposed.
Journal ArticleDOI
Sparse Coding with an Overcomplete Basis Set: A Strategy Employed by V1 ?
TL;DR: These deviations from linearity provide a potential explanation for the weak forms of non-linearity observed in the response properties of cortical simple cells, and they further make predictions about the expected interactions among units in response to naturalistic stimuli.
Proceedings ArticleDOI
Image Classification using Random Forests and Ferns
TL;DR: It is shown that selecting the ROI adds about 5% to the performance and, together with the other improvements, the result is about a 10% improvement over the state of the art for Caltech-256.
Journal ArticleDOI
Iterative thresholding for sparse approximations
Thomas Blumensath,Michael Davies +1 more
TL;DR: This paper studies two iterative algorithms that are minimising the cost functions of interest and adapts the algorithms and shows on one example that this adaptation can be used to achieve results that lie between those obtained with Matching Pursuit and those found with Orthogonal Matching pursuit, while retaining the computational complexity of the Matching pursuit algorithm.