• Journal of KIISE
• /
• v.42 no.1
• /
• pp.33-43
• /
• 2015

Recently, patent images are growing importance and thus patent image retrieval is a growing area of research. However, most existing patent image retrieval systems use edges extracted in the images, whose performance is affected by the quality of edge detection in the image pre-processing step. To overcome this disadvantage, we propose a SURF-based patent image retrieval method which uses the morphological characteristics of the images. The proposed method detects SURF interest points with directions and computes regional histograms. We apply the proposed method to a patent image database with 2000 binary images and we show the proposed retrieval system achieves excellent results, even when the images have some loss or degradation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.3
• /
• pp.894-907
• /
• 2022

The features extracted by convolutional neural networks are more descriptive of images than traditional features, and their convolutional layers are more suitable for retrieving images than are fully connected layers. The convolutional layer features will consume considerable time and memory if used directly to match an image. Therefore, this paper proposes a feature weighting and region integration method for convolutional layer features to form global feature vectors and subsequently use them for image matching. First, the 3D feature of the last convolutional layer is extracted, and the convolutional feature is subsequently weighted again to highlight the edge information and position information of the image. Next, we integrate several regional eigenvectors that are processed by sliding windows into a global eigenvector. Finally, the initial ranking of the retrieval is obtained by measuring the similarity of the query image and the test image using the cosine distance, and the final mean Average Precision (mAP) is obtained by using the extended query method for rearrangement. We conduct experiments using the Oxford5k and Paris6k datasets and their extended datasets, Paris106k and Oxford105k. These experimental results indicate that the global feature extracted by the new method can better describe an image.

• International Journal of Computer Science & Network Security
• /
• v.23 no.7
• /
• pp.61-70
• /
• 2023

Image segmentation is a very crucial step in effective digital image processing. In the past decade, several research contributions were given related to this field. However, a general segmentation algorithm suitable for various applications is still challenging. Among several image segmentation approaches, graph-based approach has gained popularity due to its basic ability which reflects global image properties. This paper proposes a methodology to partition the image with its pixel, region and texture along with its intensity. To make segmentation faster in large images, it is processed in parallel among several CPUs. A way to achieve this is to split images into tiles that are independently processed. However, regions overlapping the tile border are split or lost when the minimum size requirements of the segmentation algorithm are not met. Here the contributions are made to segment the image on the basis of its pixel using min-cut/max-flow algorithm along with edge-based segmentation of the image. To segment on the basis of the region using a homogenous optimum cut algorithm with boundary segmentation. On the basis of texture, the object type using spectral partitioning technique is identified which also minimizes the graph cut value.

• Journal of Broadcast Engineering
• /
• v.12 no.2
• /
• pp.185-192
• /
• 2007

The interpolation is used in many image processing applications such as image enhancement, de-interlacing/scan-rate conversion, wavelet transforms based on the lifting scheme, and so on. Among these, de-interlacing and scan-rate conversion are proposed for the digital TV applications. The de-interlacing algorithm can be classified into two categories. The first one uses only one field, called intra-field de-interlacing, and the other uses multiple field, called inter-field de-interlacing. In this paper, an efficient de-interlacing algorithm using spatial domain information is proposed far the interpolation of interlaced images. By efficiently estimating the directional correlations, improved interpolation accuracy has been achieved. In addition, the proposed method is simply structured and is easy to implement. Extensive simulations conducted for various images and video sequences have shown the efficacy of the proposed method with significant improvement over the previous intra-field do-interlacing methods in terms of the objective image quality as well as the subjective image quality.

• Journal of the Korean Society for information Management
• /
• v.25 no.2
• /
• pp.49-68
• /
• 2008

In many information retrieval experiments, the data fusion techniques have been used to achieve higher effectiveness in comparison to the single evidence-based retrieval. However, there had not been many image retrieval studies using the data fusion techniques especially in combining retrieval results based on multiple retrieval methods. In this paper, we describe how the image retrieval effectiveness can be improved by combining two sets of the retrieval results using the Sobel operator-based edge detection and the Self Organizing Map(SOM) algorithms. We used the clip art images from a commercial collection to develop a test data set. The main advantage of using this type of the data set was the clear cut relevance judgment, which did not require any human intervention.

• Journal of the Korean Institute of Telematics and Electronics T
• /
• v.36T no.4
• /
• pp.1-8
• /
• 1999

This paper presents a new algorithm for surface segmentation and feature description. In the first stage of proposed algorithm, the signature of an edge image of object is extracted. The signature technique represents a surface using the distance from the mass center to the boundary of the image as a function of angle rotating counterclockwise. If there exists a range in the angle axis where more than two signatures form a closed curve, we can conclude there is a surface inside the range. Using this feature of the signature, surface can be segmented. The surface features such as number of vertices, number of edges, convex and type of surface can also be extracted from segmented surfaces. This algorithm has distinguished advantages; it can easily recover the lost part in the edge image using the curve fitting method; it extracts surface features correctly regardless of the rotation of the surface in 3-D space.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.8
• /
• pp.2271-2280
• /
• 1999

In this paper, a variable motion estimation scheme based on HBMA(Hierarchical Block Matching Algorithm) to improve the performance and to reduce heavy computational and transmission load, is presented. The proposed algorithm is composed of four steps. First, block activity for each block is defined using the edge information of differential image between two sequential images, and then average block activity of the present image is found by taking the mean of block activity. Secondly, camera pan compensation is carried out, according to the average activity of the image, in the hierarchical pyramid structure constructed by wavelet transform. Next, the LUT classifying each block into one among Moving, No Moving, Semi-Moving Block according to the block activity compensated camera pan is obtained. Finally, as varying the block size and adaptively selecting the initial search layer and the search range referring to LUT, the proposed variable HBMA can effectively carries out fast motion estimation in the hierarchical pyramid structure. The cost function needed above-mentioned each step is only the block activity defined by the edge information of the differential image in the sequential images.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.3
• /
• pp.1718-1723
• /
• 2014

We proposes the method to detect the Hangul and English character region from natural image using structural feature of Hangul and English Characters. First, we extract edge features from natural image, Next, if features are not corresponding to the heuristic rule of character features, extracted features filtered out and select candidates of character region. Next, candidates of Hangul character region are merged into one Hangul character using Hangul character merging algorithm. Finally, we detect the final character region by Hangul character class decision algorithm. English character region detected by edge features of English characters. Experimental result, proposed method could detect a character region effectively in images that contains a complex background and various environments. As a result of the performance evaluation, A proposed method showed advanced results about detection of Hangul and English characters region from natural image.

• Korean Journal of Digital Imaging in Medicine
• /
• v.12 no.2
• /
• pp.127-132
• /
• 2010

In this study, the correlation among the changes of Modulation Transfer Function(MTF) in the noise and high-contrast resolution and the change of Contrast to noise ratio(CNR) in the low-contrast resolution will be examined to investigate the estimation of image quality according to the type of algorithms. The image data obtained by scanning American Association of Physicists in Medicine(AAPM) phantom was applied to each algorithm and the exposure condition of 120 kVp, 250 mAs, and then the CT number and noise were measured. The MTF curved line of the high-contrast resolution was calculated with Point Spread Function(PSF) by using the analysis program by Philips, resulting in 0.5 MTF, 0.1 MTF and 0.02 MTF respectively. The low-contrast resolution was calculated with CNR and the uniformity was measured to each algorithm. Since the measurement value for the uniformity of the equipment was below ${\pm}$ 5 HU, which is the criterion figure, it was found to belong to the normal range. As the algorithm got closer from soft to edge, the standard deviation of CT number increased, which indicates that the noise increased as well. As for MTF, 0.5 MTF, 0.1 MTF and 0.02 MTF were all sharp algorithms, and as the algorithm got closer from soft to edge, it was possible to distinguish more clearly with the naked eye. On the other hand, CNR gradually decreased, because the difference between the contrast hole CT number and the acrylic CT number was the same while the noise of hole increased.

• Journal of Digital Contents Society
• /
• v.18 no.4
• /
• pp.777-785
• /
• 2017

In the modern real world, we can extract and recognize some texts to get a lot of information from the scene containing them, so the techniques for extracting and recognizing text areas from a scene are constantly evolving. They can be largely divided into texture-based method, connected component method, and mixture of both. Texture-based method finds and extracts text based on the fact that text and others have different values such as image color and brightness. Connected component method is determined by using the geometrical properties after making similar pixels adjacent to each pixel to the connection element. In this paper, we propose a method to adaptively change to improve the accuracy of text region extraction, detect and correct the slope of the image using edge and image segmentation. The method only extracts the exact area containing the text by correcting the slope of the image, so that the extracting rate is 15% more accurate than MSER and 10% more accurate than EEMSER.