Detection of local features which are distinctive, invariant and discriminative is used to construct compact image representations in many computer vision applications. Achieving robustness against viewpoint change motivated the development of affine invariant detectors responding to image gradient or contrast changes, edges or corners. We focus on the Maximally Stable Extremal Regions (MSER) d...

In this paper, we describe a system for Android smartphones which detects and extracts Chinese text, and translates it into English. Most of the processing is done on a server; the user simply takes a picture with no other input. In this project we are mainly concerned about the text detection part, for which we use the MSER algorithm; the Optical Character Recognition (OCR) is based on Tessera...

The wide-baseline stereo problem, i.e. the problem of establishing correspondences between a pair of images taken from different viewpoints is studied. A new set of image elements that are put into correspondence, the so called extremal regions, is introduced. Extremal regions possess highly desirable properties: the set is closed under 1. continuous (and thus projective) transformation of imag...

We describe an implementation of the Maximally Stable Extremal Region ([3], Sect. 2, MSER) feature detector and an immediate multi-dimensional generalization ([1], Sect. 2). We propose an algorithm (Sect. 3) that is essentially uniontree with path-compression and union-by-rank (see for instance [4]). However we do not use the N-tree graph of [4] as for the purpose of fitting ellipses to the MSE...

[1] Thomas Cormen, Charles Leiserson, Ronald Rivest, and Cli ord Stein. Introduction to Algorithms. MIT Press and McGraw-Hill Book Co., second edition, 2001. [2] Zvi Galil. Data structures and algorithms for disjoint set union problems. ACM Computing Surveys, 23(3):320–344, 1991. [3] David Lowe. Distinctive image features from scale-invariant keypoints. Int’l J. Computer Vision, 60(2):91–110, 2...

The authors address, in this study, a new adaptive binarisation method on images captured by smartphones. This work is part of an application for visually impaired people assistance, which aims at making text information accessible to people who cannot read it. The main advantage of the proposed method is that the windows underlying the local thresholding process are automatically adapted to th...

We propose a novel distinguished region detector called Maximally Stable Corner Cluster detector (MSCC). It is complementary to existing approaches like Harris-corner detectors, Difference of Gaussian detectors (DoG) or Maximally Stable Extremal Regions (MSER). The basic idea is to find distinguished regions by looking at clusters of interest points and using the concept of maximal stableness a...

Two of multiple view object reconstruction approaches are inspected in this work. The goal is to create and test several functions for processing of two input images of the scene to uncover geometry of the scene. A new algorithm for Maximally Stable Extremal Regions correspondence detection is presented – True Tentative Correspondences employing the Sideness constraint. The input to the algorit...

This paper presents a novel framework for 3D full body reconstruction of human motion from uncalibrated monocular video data. We first detect and track feature sets from video sequences by employing MSER and SURF feature detection techniques together with prior information obtained from the motion capture database. By deriving suitable feature sets from both video and motion capture data, we ar...

For learning an object representation a huge amount of labeled data is needed. To minimize the labeling effort this paper proposes a new approach for learning from unlabeled data. The main idea is to combine a tracker and a learning method by directly feeding the learning algorithm with patches obtained by the tracker. In particular we apply an MSER based tracker and batch PCA for learning. But...