Soo-Hyung Kim

Analysis and recognition of Asian scripts-the state of the art

This paper summarizes the research activities of the pastdecade on the recognition of handwritten scripts used inChina, Japan, and Korea. It presents the recognitionmethodologies, features explored, databases used, andclassification schemes investigated. In addition, it includes adescription of the performance of numerous recognitionsystems found in both academic and industrial researchlaboratories. Recent achievements and applications are alsopresented. A list of relevant references is attached togetherwith our remarks on this subject.

Efficient skew estimation and correction algorithm for document images

Abstract In this paper, we propose a fast skew estimation and correction algorithm for English and Korean documents based on a BAG (Block Adjacency Graph) representation. BAG is one of the most efficient data structures for extracting various information concerning connected components; the image rotation for skew correction is performed rapidly using the block information in the BAG. The proposed skew estimation algorithm uses a coarse/refine strategy based on the Hough transformation of connected components in the image. The skew correction algorithm then generates a non-skew image by rotating the blocks, rather than the individual pixels. An experiment using 2016 images from various English and Korean documents demonstrates how the proposed method is superior to conventional ones.

Automatic detection and recognition of Korean text in outdoor signboard images

In this paper, an automatic translation system for Korean signboard images is described. The system includes detection and extraction of text for the recognition and translation of shop names into English. It deals with impediments caused by different font styles and font sizes, as well as illumination changes and noise effects. Firstly, the text region is extracted by an edge-histogram, and the text is binarized by clustering. Secondly, the extracted text is divided into individual characters, which are recognized by using a minimum distance classifier. A shape-based statistical feature is adopted, which is adequate for Korean character recognition, and candidates of the recognition results are generated for each character. The final translation step incorporates the database of shop names, to obtain the most probable result from the list of candidates. The system has been implemented in a mobile phone and is demonstrated to show acceptable performance.

Computer-aided detection of early interstitial lung diseases using low-dose CT images

This study aims to develop a new computer-aided detection (CAD) scheme to detect early interstitial lung disease (ILD) using low-dose computed tomography (CT) examinations. The CAD scheme classifies each pixel depicted on the segmented lung areas into positive or negative groups for ILD using a mesh-grid-based region growth method and a multi-feature-based artificial neural network (ANN). A genetic algorithm was applied to select optimal image features and the ANN structure. In testing each CT examination, only pixels selected by the mesh-grid region growth method were analyzed and classified by the ANN to improve computational efficiency. All unselected pixels were classified as negative for ILD. After classifying all pixels into the positive and negative groups, CAD computed a detection score based on the ratio of the number of positive pixels to all pixels in the segmented lung areas, which indicates the likelihood of the test case being positive for ILD. When applying to an independent testing dataset of 15 positive and 15 negative cases, the CAD scheme yielded the area under receiver operating characteristic curve (AUC = 0.884 ± 0.064) and 80.0% sensitivity at 85.7% specificity. The results demonstrated the feasibility of applying the CAD scheme to automatically detect early ILD using low-dose CT examinations.

Text locating from natural scene images using image intensities

In this paper, we propose three text extraction methods based on intensity information for natural scene images. The first method is composed of gray value stretching and binarization by an average intensity of the image. This method is appropriate to extract texts from complex backgrounds. The second method is a split and merge approach which is one of well-known algorithms for image segmentation. The third one is a combination of the two. Experimental results show that the proposed approaches are superior to conventional methods both in simple and complex images.

Word segmentation of printed text lines based on gap clustering and special symbol detection

This paper proposes a word segmentation method for machine-printed text lines. It utilizes gaps and special symbols as delimiters between words. A gap clustering technique is used to identify the gaps between words regardless of the gap-size variations among different document images. Next a special symbol detection technique is applied to find two types of special symbols lying between words. An experiment with 1,675 text lines in 100 different English and Korean documents shows that the proposed method achieves a high accuracy of word segmentation.

Segmentation of Brain MR Images Using an Ant Colony Optimization Algorithm

In this paper, we describe a segmentation method for brain MR images using an ant colony optimization (ACO) algorithm. This is a relatively new meta-heuristic algorithm and a successful paradigm of all the algorithms which take advantage of the insect’s behavior. It has been applied to solve many optimization problems with good discretion, parallel, robustness and positive feedback. As an advanced optimization algorithm, only recently, researchers began to apply ACO to image processing tasks. Hence, we segment the MR brain image using ant colony optimization algorithm. Compared to traditional meta-heuristic segmentation methods, the proposed method has advantages that it can effectively segment the fine details.

Separated role of on-chip and on-PCB decoupling capacitors for reduction of radiated emission on printed circuit board

The power/ground fluctuation is known as a significant source of radiated emission. We discuss the separated functions of on-PCB and on-chip decoupling capacitors on the suppression of electromagnetic radiated emission. Due to the different ranges of parasitic inductance and the different locations of the on-chip current drivers, on-PCB and on-chip decoupling capacitors exhibit separated frequency characteristics in terms of suppression efficiency of radiation. The roles of on-PCB and on-chip decoupling capacitors are estimated by circuit simulation and a simple antenna model, and are confirmed by experiments. It is found that the on-chip decoupling capacitors are mainly effective for the suppression of radiated emission over 100 MHz frequency. Increase of the on-chip decoupling capacitance and decrease of the parasitic inductance of the package produce an improved suppression ratio at high frequency range. Combined placement and sizing of the decoupling capacitors have achieved more than 10 dB suppression of the electromagnetic radiated emission over a wide spectrum range.

Recognition of logic diagrams by identifying loops and rectilinear polylines

Proposed is a system that recognizes logic symbols and their interconnections on logic diagrams. The input diagram, digitized by scanner, is converted into a set of line segments through a sequence of picture processing operations. Then symbols and connections are extracted by identifying loops and rectilinear polylines utilizing a model-base in which symbols are graphically described. Experiment with a number of logic diagrams shows that the system correctly recognizes more than 96% of logic symbols and connections on an A4-size diagram with an average complexity within 15 s on a workstation.<<ETX>>

English to Spanish translation of signboard images from mobile phone camera

We propose a whole architecture for English to Spanish translation of the texts present on JPEG natural scene images taken with a mobile phone camera. We detect the text using the frequency information of the DCT coefficients, binarize it using a clustering-based algorithm, recognize it by the use of an OCR algorithm and translate and phonetically transcribe it from English to Spanish. The result is a useful, simple, affordable and robust system that can handle problems like lighting distortion, out of focus, low resolution and foreground-background color variations in a very short amount of processing time, which makes its implementation very attractive on portable devices.