ﻻ يوجد ملخص باللغة العربية
-This paper presents a semi automatic method used to segment color documents into different uniform color plans. The practical application is dedicated to administrative documents segmentation. In these documents, like in many other cases, color has a semantic meaning: it is then possible to identify some specific regions like manual annotations, rubber stamps or colored highlighting. A first step of user-controlled learning of the desired color plans is made on few sample documents. An automatic process can then be performed on the much bigger set as a batch. Our experiments show very interesting results in with a very competitive processing time.
Fully-automatic execution is the ultimate goal for many Computer Vision applications. However, this objective is not always realistic in tasks associated with high failure costs, such as medical applications. For these tasks, semi-automatic methods a
We address the problem of soft color segmentation, defined as decomposing a given image into several RGBA layers, each containing only homogeneous color regions. The resulting layers from decomposition pave the way for applications that benefit from
Image co-segmentation is important for its advantage of alleviating the ill-pose nature of image segmentation through exploring the correlation between related images. Many automatic image co-segmentation algorithms have been developed in the last de
In this paper, we present a novel approach to perform deep neural networks layer-wise weight initialization using Linear Discriminant Analysis (LDA). Typically, the weights of a deep neural network are initialized with: random values, greedy layer-wi
In this paper, we propose Augmented Reality Semi-automatic labeling (ARS), a semi-automatic method which leverages on moving a 2D camera by means of a robot, proving precise camera tracking, and an augmented reality pen to define initial object bound