[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

This paper deals with signature based document retrieval from documents with cluttered background. Here, a signature object is characterized by spatial features computed from recognition result of background blobs. The background blobs are computed by analyzing character holes and water reservoir zones in different directions. For the indexation purpose, a codebook of the background blobs is created using a set of training data. Zernike Moment feature is extracted from each blob and a K-Mean clustering algorithm is used to create the codebook of blobs. During retrieval, Generalized Hough Transform (GHT) is used to detect the query signature and a voting is casted to find possible location of the query signature in a document. The spatial features computed from background blobs found in the target document are used for GHT. The peak of votes in GHT accumulator validates the hypothesis of the query signature. The proposed method is tested on a collection of mixed documents (handwritten/printed) of various scripts and we have obtained encouraging results from the experiments.

Signature Based Document Retrieval Using GHT of Background Information

Conversion of one font to another font is very useful in real life applications. In this paper, we propose a Convolutional Recurrent Generative model to solve the word level font transfer problem. Our network is able to convert the font style of any printed text images from its current font to the required font. The network is trained end-to-end for the complete word images. Thus it eliminates the necessary pre-processing steps, like character segmentations. We extend our model to conditional setting that helps to learn one-to-many mapping function. We employ a novel convolutional recurrent model architecture in the Generator that efficiently deals with the word images of arbitrary width. It also helps to maintain the consistency of the final images after concatenating the generated image patches of target font. Besides, the Generator and the Discriminator network, we employ a Classification network to classify the generated word images of converted font style to their subsequent font categories. Most of the earlier works related to image translation are performed on square images. Our proposed architecture is the first of its kind which can handle images of varying widths. Word images generally have varying width depending on the number of characters present. Hence, we test our model on a synthetically generated font dataset. We compare our method with some of the state-of-the-art methods for image translation. The superior performance of our network on the same dataset proves the ability of our model to learn the font distributions.

Word Level Font-to-Font Image Translation using Convolutional Recurrent Generative Adversarial Networks

This paper presents a two-stage method for multi-oriented video character segmentation. Words segmented from video text lines are considered for character segmentation in the present work. Words can contain isolated or non-touching characters, as well as touching characters. Therefore, the character segmentation problem can be viewed as a two stage problem. In the first stage, text cluster is identified and isolated (non-touching) characters are segmented. The orientation of each word is computed and the segmentation paths are found in the direction perpendicular to the orientation. Candidate segmentation points computed using the top distance profile are used to find the segmentation path between the characters considering the background cluster. In the second stage, the segmentation results are verified and a check is performed to ascertain whether the word component contains touching characters or not. The average width of the components is used to find the touching character components. For segmentation of the touching characters, segmentation points are then found using average stroke width information, along with the top and bottom distance profiles. The proposed method was tested on a large dataset and was evaluated in terms of precision, recall and f-measure. A comparative study with existing methods reveals the superiority of the proposed method.

/pdf/a-new-method-for-character-segmentation-from-multi-oriented-26bkck5bbn.pdf

A New Method for Character Segmentation from Multi-oriented Video Words

There are many video images where hand written text may appear. Therefore handwritten scene text detection in video is essential and useful for many applications for efficient indexing, retrieval etc. Also there are many video frames where text line may be multi-oriented in nature. To the best of our knowledge there is no work on handwritten text detection in video, which is multi-oriented in nature. In this paper, we present a new method based on maximum color difference and boundary growing method for detection of multi-oriented handwritten scene text in video. The method computes maximum color difference for the average of R, G and B channels of the original frame to enhance the text information. The output of maximum color difference is fed to a K-means algorithm with K=2 to separate text and non-text clusters. Text candidates are obtained by intersecting the text cluster with the Sobel output of the original frame. To tackle the fundamental problem of different orientations and skews of handwritten text, boundary growing method based on a nearest neighbor concept is employed. We evaluate the proposed method by testing on our own handwritten text database and publicly available video data (Hua’s data). Experimental results obtained from the proposed method are promising.

A New Method for Handwritten Scene Text Detection in Video

A study showing how the recognition performance of an MLP based classifier varies with variation in the training set size is presented in this paper. The training set for the work is formed with samples of handwritten Bangla numerals. For recognition of handwritten Bangla numerals, we have used directional features extracted from the contour of each numeral. To extract these features, the minimum bounding box containing the image of each numeral is first segmented into few blocks and then the direction code histogram is computed with each of these blocks. Peak values of each such histogram are considered as the feature values of the corresponding blocks. Considering all the blocks a 100 element feature set is formed for representation of each image pattern and a database of 12000 numerals are used for the same.

Umapada Pal

Papers

Signature Based Document Retrieval Using GHT of Background Information

Word Level Font-to-Font Image Translation using Convolutional Recurrent Generative Adversarial Networks

A New Method for Character Segmentation from Multi-oriented Video Words

A New Method for Handwritten Scene Text Detection in Video

A Study on the Effect of Varying Training set Sizes on Recognition Performance with Handwritten Bangla Numerals