Image Reconstruction by Multilabel Propagation
نویسندگان
چکیده
This work presents a non-convex variational approach to joint image reconstruction and labeling. Our regularization strategy, based on the KL-divergence, takes into account the smooth geometry on the space of discrete probability distributions. The proposed objective function is efficiently minimized via DC programming which amounts to solving a sequence of convex programs, with guaranteed convergence to a critical point. Each convex program is solved by a generalized primal dual algorithm. This entails the evaluation of a proximal mapping, evaluated efficiently by a fixed point iteration. We illustrate our approach on few key scenarios in discrete tomography and image deblurring.
منابع مشابه
The Study of Variation of Photon Intensity Inside Biological Phantom by Green Theorem
The Image reconstruction is an important problem in optical tomography. The process of the image processing requires the study of photon migration in biological tissue. There are several approaches to study and simulate propagation of photons in biological tissues. These approaches are categorized into stochastic and analytical groups. The Monte Carlo method as a stochastic method is widely use...
متن کاملDeep Convolutional Ranking for Multilabel Image Annotation
Multilabel image annotation is one of the most important challenges in computer vision with many real-world applications. While existing work usually use conventional visual features for multilabel annotation, features based on Deep Neural Networks have shown potential to significantly boost performance. In this work, we propose to leverage the advantage of such features and analyze key compone...
متن کاملLearning Image Conditioned Label Space for Multilabel Classification
This work addresses the task of multilabel image classification. Inspired by the great success from deep convolutional neural networks (CNNs) for single-label visualsemantic embedding, we exploit extending these models for multilabel images. Specifically, we propose an imagedependent ranking model, which returns a ranked list of labels according to its relevance to the input image. In contrast ...
متن کاملBlock-Based Compressive Sensing Using Soft Thresholding of Adaptive Transform Coefficients
Compressive sampling (CS) is a new technique for simultaneous sampling and compression of signals in which the sampling rate can be very small under certain conditions. Due to the limited number of samples, image reconstruction based on CS samples is a challenging task. Most of the existing CS image reconstruction methods have a high computational complexity as they are applied on the entire im...
متن کاملReconstruction of Lambertian surfaces by discrete equal height contours and regions propagation
This paper describes two new methods for the reconstruction of discrete surfaces from shading images. Both approaches are based on the reconstruction of a discrete surface by mixing photometric and geometric techniques. The processing of photometric information is based on reflectance maps, which are classic tools of Shape from Shading. The geometric features are extracted from the discrete sur...
متن کامل