In this paper, the algorithm for thinning of greyscale images is proposed that is based on a pseudodistance map (PDM). The PDM is a simplified distance map of gray-scale image and uses only that features of image and objects that are necessary to build a skeleton. The algorithm works fast for large gray-scale images and allows constructing a high quality skeleton.
Piecewise linear two-dimensional warping (PL2DW) is a practical elastic image matching technique where the pixel-to-pixel correspondence function between a pair of image patterns is defined as a piecewise linear 2D-2D mapping. For accurate matching, the boundary points of linearization, called “pivots”, should be placed at the bending and stretching points of image patterns. In conventional PL2DW, it is assumed that the pivots are properly placed by users before their mapping is optimized. This assumption, however, is acceptable only when the a priori knowledge about the deformation characteristics of the image patterns is available. In this paper. an improved PL2DW technique is proposed. In this technique, along with the mapping of pivots, their placement is simultaneously optimized. As a result, pivots are placed automatically at the bending and stretching points of the target and therefore accurate matching is obtained without any a priori knowledge.
In documents and graphics, contours are a popular format to describe specific shapes. For example, in the True Type Font (TTF) file format, contours describe vector outlines of typeface shapes. Each contour is often defined as a sequence of points. In this paper, we tackle the contour completion task. In this task, the input is a contour sequence with missing points, and the output is a generated completed contour. This task is more difficult than image completion because, for images, the missing pixels are indicated. Since there is no such indication in the contour completion task, we must solve the problem of missing part detection and completion simultaneously. We propose a Transformer-based method to solve this problem and show the results of the typeface contour completion.
This paper proposes a dynamic programming (DP) matching method with global features for online character recognition. Many online character recognition methods have utilized the ability of DP matching on compensating temporal fluctuation. On the other hand, DP requires the Markovian property on its matching process. Consequently, most traditional DP matching methods have utilized local information of strokes such as xy-coordinates or local directions as features, because it is easy to satisfy the Markovian property with those features. Unfortunately, these local features cannot represent global structure of character shapes. Although global features that extract global structures of characters have high potential to represent various key characteristics of character shapes, conventional DP matching methods cannot handle global features. This is because the incorporation of global features is not straightforward due to the Markovian property of DP. In this paper we propose a new scheme for DP matching using global features. Our method first selects global features which not only satisfy the Markovian property but also have sufficient discrimination ability. By embedding the selected global features into DP matching process, we can compensate temporal fluctuation while considering the global structure of the pattern. Experimental results show that our methods can enhance the recognition accuracy for online numeral characters.
Temporal pattern recognition is challenging because temporal patterns require extra considerations over other data types, such as order, structure, and temporal distortions. Recently, there has been a trend in using large data and deep learning, however, many of the tools cannot be directly used with temporal patterns. Convolutional Neural Networks (CNN) for instance are traditionally used for visual and image pattern recognition. This paper proposes a method using a neural network to classify isolated temporal patterns directly. The proposed method uses dynamic time warping (DTW) as a kernel-like function to learn dissimilarity-based feature maps as the basis of the network. We show that using the proposed DTW-NN, efficient classification of on-line handwritten digits is possible with accuracies comparable to state-of-the-art methods.
