[신간의 별자리x] 우리/미술, 그리고 ‘슬픔의 박물관’

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

“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

IEEE Transactions on Pattern Analysis and Machine Intelligence

The paper deals with an optical character recognition system for printed Oriya, a popular Indian script. The development of OCR for this script is difficult because a large number of characters have to be recognized. In the proposed system, the digitized document image is first passed through preprocessing modules like skew correction, line segmentation, zone detection, word and character segmentation, etc. These modules have been developed by combining some conventional techniques with some newly proposed ones. Next, individual characters are recognized using a combination of stroke and run-number based features, along with features obtained from the concept of a water reservoir. The feature detection methods are simple and robust. A prototype of the system has been tested on a variety of printed Oriya material, and currently achieves 96.3% character level accuracy on average.

Automatic recognition of printed Oriya script

HMM-based Indic handwritten word recognition using zone segmentation

This paper deals with an Optical Character Recognitionsystem for printed Urdu, a popular Indian script. Thedevelopment of OCR for this script is difficult because (i) alarge number of characters have to be recognized (ii) thereare many similar shaped characters. In the proposedsystem individual characters are recognized using acombination of topological, contour and water reservoirconcept based features. The feature detection methods aresimple and robust. A prototype of the system has beentested on printed Urdu characters and currently achieves97.8% character level accuracy on average.

Recognition of printed Urdu script

Recognition of handwritten characters of Indian script is difficult because of the presence of many complex shaped compound characters (cluster characters) as well as variability involved in the writing style of different individuals. This paper deals with recognition of off-line Bangla handwritten compound characters using modified quadratic discriminant function (MQDF). The features used for recognition purpose are mainly based on directional information obtained from the arc tangent of the gradient. To get the feature, at first, a 2 times 2 mean filtering is applied 4 times on the gray level image and a non-linear size normalization is done on the image. A Roberts filter is then applied on the normalized image to obtain gradient image. Next, the arc tangent of the gradient (direction of gradient) is initially quantized into 32 directions and the strength of the gradient is accumulated with each of the quantized direction. Finally, the frequencies of these directions are down sampled using Gaussian filter to get 392 dimensional feature vectors. Using 5-fold cross validation technique we obtained 85.90% accuracy from a dataset of Bangla compound characters containing 20,543 samples.

Handwritten Bangla Compound Character Recognition Using Gradient Feature

In this paper we present a system towards the recognition of off-line handwritten characters of Devnagari, the most popular script in India. The features used for recognition purpose are mainly based on directional information obtained from the arc tangent of the gradient. To get the feature, at first, a 2times2 mean filtering is applied 4 times on the gray level image and a non-linear size normalization is done on the image. The normalized image is then segmented to 49times49 blocks and a Roberts filter is applied to obtain gradient image. Next, the arc tangent of the gradient (direction of gradient) is initially quantized into 32 directions and the strength of the gradient is accumulated with each of the quantized direction. Finally, the blocks and the directions are down sampled using Gaussian filter to get 392 dimensional feature vector. A modified quadratic classifier is applied on these features for recognition. We used 36172 handwritten data for testing our system and obtained 94.24% accuracy using 5-fold cross-validation scheme.

Umapada Pal

Papers

Automatic recognition of printed Oriya script

HMM-based Indic handwritten word recognition using zone segmentation

Recognition of printed Urdu script

Handwritten Bangla Compound Character Recognition Using Gradient Feature

Off-Line Handwritten Character Recognition of Devnagari Script