[신간의 별자리x] 우리/미술, 그리고 ‘슬픔의 박물관’

“Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks”の学習報告

An overview of the self-organizing map algorithm, on which the papers in this issue are based, is presented in this article.

The Self-Organizing Map

A computer-implemented method for use in conjunction with a computing device with a touch screen display comprises: detecting one or more finger contacts with the touch screen display, applying one or more heuristics to the one or more finger contacts to determine a command for the device, and processing the command. The one or more heuristics comprise: a heuristic for determining that the one or more finger contacts correspond to a one- dimensional vertical screen scrolling command, a heuristic for determining that the one or more finger contacts correspond to a two-dimensional screen translation command, and a heuristic for determining that the one or more finger contacts correspond to a command to transition from displaying a respective item in a set of items to displaying a next item in the set of items.

Touch screen device, method, and graphical user interface for determining commands by applying heuristics

A portable electronic device displays a plurality of icons (e.g., graphical objects) in a region in a touch-sensitive display; detects a predefined user action, with respect to the touch-sensitive display, for initiating a predefined user interface reconfiguration process; and varies positions of one or more icons in the plurality of icons in response to detecting the predefined user action. The varying includes varying the positions of the one or more icons about respective average positions.

Portable electronic device with interface reconfiguration mode

A simple and fast segmentation of text and line drawings which exploits the characteristics of online handwritten patterns is presented. Many attempts have been made on text/figure segmentation in offline research, but none in online. In online environment, mode selection is easily employed to input characters and drawings commongly. But it disturbs the user's thought. The authors propose online but delayed processing of handwritten patterns after they are written. Because the input patterns consists of characters and line drawings, there is a need to discriminate input patterns into characters and line drawings. An analysis of 17 handwritten patterns shows that the logarithmic distribution of character stroke length and that of the length of the longer side of rectangles circumscribing character strokes have similarity to the normal distribution. This finding, the contact frequency of character strokes and drawing strokes, and stroke input order have been used to perform the segmentation. In the testing of 18 patterns, 88% of all strokes were correctly judged. >

On-line text/drawings segmentation of handwritten patterns

Inspired by recent successes in neural machine translation and image caption generation, we present an attention based encoder decoder model (AED) to recognize Vietnamese Handwritten Text. The model composes of three parts: a convolution neural network (CNN) for extracting invariant features, a Bidirectional Long Short-Term Memory network (BLSTM) for encoding extracted features (BLSTM encoder), and a Long Short-Term Memory network (LSTM) with an attention model incorporated for generating output text (LSTM decoder), which are connected from the CNN part to the BLSTM encoder and finally the LSTM decoder. The input of the CNN part is a handwritten text image and the target of the LSTM decoder is the corresponding text of the input image. Our model is trained end-to-end to predict the text from a given input image since all the parts are differential components. In the experiment section, we evaluate our proposed AED model on the VNOnDB-Word database to verify its efficiency. The experiential results show that our model achieves 12.30% of word error rate without using language model. This result is competitive with the handwriting recognition system provided by Google in the Vietnamese Online Handwritten Text Recognition competition.

Recognizing Unconstrained Vietnamese Handwriting By Attention Based Encoder Decoder Model

This paper describes a Markov random field
(MRF) model with weighting parameters optimized by
conditional random field (CRF) for on-line
recognition of handwritten Japanese characters. The
model extracts feature points along the pen-tip trace
from pen-down to pen-up and sets each feature point
from an input pattern as a site and each state from a
character class as a label. It employs the coordinates
of feature points as unary features and the differences
in coordinates between the neighboring feature points
as binary features. The weighting parameters are
estimated by CRF or the minimum classification error
(MCE) method. In experiments using the TUAT
Kuchibue database, the method achieved a character
recognition rate of 92.77%, which is higher than the
previous model's rate, and the method of estimating
the weighting parameters using CRF was more
accurate than using MCE.

/pdf/a-mrf-model-with-parameter-optimization-by-crf-for-on-line-2iwgwf5ay9.pdf

A MRF model with parameter optimization by CRF for on-line recognition of handwritten Japanese characters

This paper presents the results of the VOHTR 2018 competition on Vietnamese Online Handwritten Text Recognition. The goal of this competition is to evaluate and compare recent online handwritten text recognition systems on Vietnamese online handwritten text which contains many delayed strokes caused by the diacritic marks. Besides, the general objective is to encourage the studies on Vietnamese online handwritten text recognition based on the large Vietnamese handwriting database collected from 200 writers. In this competition, we introduce three tasks consisting of word recognition (task 1), text-line recognition (task 2) and paragraph recognition (task 3) which are described in details. Subsequently, we describe the evaluation metrics and give comparative results of competitors along with the brief descriptions of the respective methods.

ICFHR 2018 – Competition on Vietnamese Online Handwritten Text Recognition using HANDS-VNOnDB (VOHTR2018)

This paper reviews some prototype learning algorithms for nearest neighbor (NN) classifier design land evaluates their performances in handwritten character recognition. The algorithms include the well-known LVQ and those that globally optimize an objective function, as well as some newly derived variants. Experimental results of handwritten numeral recognition and Chinese character recognition show that the global optimization algorithms generally outperform LVQ. Particularly, the generalized LVQ of Sato and Yamada (1998) and a new algorithm MAXP2 yield best results.

Masaki Nakagawa

Papers

On-line text/drawings segmentation of handwritten patterns

Recognizing Unconstrained Vietnamese Handwriting By Attention Based Encoder Decoder Model

A MRF model with parameter optimization by CRF for on-line recognition of handwritten Japanese characters

ICFHR 2018 – Competition on Vietnamese Online Handwritten Text Recognition using HANDS-VNOnDB (VOHTR2018)

Prototype learning algorithms for nearest neighbor classifier with application to handwritten character recognition