A new feature selection method for reliable tracking is presented. In this paper, it is assumed that features are tracked by template matching where small regions around the features are defined as templates. The proposed method selects features based on the upper bound of the average template matching error. This selection criterion is directly related to the reliability of tracking and hence,...

In order to improve the recognition accuracy of seed cotton foreign fibers, a study on identification method in hyper-spectral images based on Minimum Noise Fraction (MNF) was proposed ,which was applied to feature extraction to reduce the dimension of hyper-spectral images. This method reduced the numbers of hyper-spectral data, lessened the images noise to the minimum , but also decreased the...

We present a robust method for automatically matching points over two images for image mosaicing: after extracting feature points using a feature detector, we progressively estimate the rotation, the scale change, and the projective distortion between the two images by random voting and variable template matching. Using real images, we demonstrate that our method allows accurate image mosaicing...

Matching precision of scale-invariant feature transform (SIFT) is evaluated and improved in this paper. The aim of the paper is not to invent a new feature detector more invariant than the others. Instead, we focus on SIFT method and evaluate and improve the matching precision, defined as the root mean square error (RMSE) under ground truth geometric transform. Matching precision reflects to so...

This paper presents an empirical study of affine invariant feature detectors to perform matching on video sequences of people with non-rigid surface deformation. Recent advances in feature detection and wide baseline matching have focused on static scenes. Video frames of human movement captures highly non-rigid deformation such as loose hair, cloth creases, skin stretching and free flowing clo...

Recently, digital stereo microscopes have been becoming increasingly popular in fields such as biomedicine and biotechnology. As such, being able to precisely match left/right feature pairs is critical, which is an important step in stereo matching. We hereby propose a dynamic interpolation method that combines two dimensional calibration and depth information to achieve stereo matching. In thi...

In a two-dimensional pattern matching problem, a known template image has be located in another image, irrespective of the template's position, orientation and size in the image. One way to accomplish invariance to the changes in the template is by forming a set of feature vectors that encompass all the variations in the template. Matching is then performed by finding the best similarity betwee...

This paper presents computationally efficient object detection, matching and categorization via Agglomerative Correspondence Clustering (ACC). We implement ACC for feature correspondence and object-based image matching exploiting both photometric similarity and geometric consistency from local invariant features. Objectbased image matching is formulated here as an unsupervised multi-class clust...

Deformable objects have changeable shapes and they require a different method of matching algorithm compared to rigid objects. This paper proposes a fast and robust deformable object matching algorithm. First, robust feature points are selected using a statistical characteristic to obtain the feature points with the extraction method. Next, matching pairs are composed by the feature point match...