Search

In April 2016, a massive earthquake with a magnitude of 7.3 struck Kumamoto region, Japan, causing major devastation. One of the structures that were damaged in Kumamoto was Kumamoto Castle, a cultural asset of great significance in Japan. The stone retaining wall “ishigaki” that formed the foundation of the castle collapsed, and the superstructure was destroyed. The number of stones is estimated to be more than 70,000, and restoration work is anticipated to take more than 20 years. Since each of the stones is an important cultural asset, the broken stone structure needed to be restored to its original state in order not to lose its cultural value forever. In addition, the fallen stones need to be returned to their original positions in the ishigakis. In similar cases, non-automatic visual verification was used. However, for Kumamoto Castle, this would have been impossible because a large number of stones were displaced as a result of the collapse. The purpose of this project is to provide support for the restoration work by matching the stones that fell down after the collapse with those before the collapse using information technology, such as computer vision and optimization technologies. Specifically, we captured photographic images of the stones before and after the collapse to match them. The technical contributions of this study are as follows: (a) To estimate the scale and surface orientation of the stones, we exploit 3D model construction from the images. (b) To solve the jigsaw-puzzle-like problem of reassembling the stone fragments, we exploit the combination of a customized iterative closest point (ICP) algorithm for shape position matching and an assignment algorithm to find the best pairs of stones before and after the collapse by using the matching degree obtained from ICP. Here, only the 2D shape of the stones before the collapse can be used due to the small number of photos available. In contrast, a detailed 3D shape can be obtained from the stones after their collapse. We matched these asymmetric data in 2D and 3D to enable a comprehensive reconstruction. (c) We developed a user-friendly graphical user interface system that was used by actual masons without special knowledge. The developed system was used to match the ishigaki of a turret, Iidamaru. As a result, we succeeded in identifying 337 stones, or approximately 90% of the 370 images. These results are expected to be useful for and were used as a blueprint during actual restoration work.

This paper proposes multi-view display using a digital light processing (DLP) projector and new active shutter glasses. In conventional stereoscopic active shutter systems, active shutter glasses have a 0--1 (open and closed) state, and the right and left frames are temporally divided. However, this causes the display to flicker because the human eye perceives the appearance of black frames when the other shutter is closing. Furthermore, it is difficult to increase the number of views because the number of frames representing images is also divided. We solve these problems by extending the active shutter beyond the use of the 0--1 state to a continuous range of states [0, 1] instead. This relaxation leads to the formulation of a new DLP imaging model and an optimization problem. The special structure of DLP binary imaging and the continuous transmittance of the new active shutter glasses require the solution of a binary continuous image decomposition problem. Although it contains NP-hard problems, the proposed algorithm can efficiently solve the problem. The implementation of our imaging system requires the development of an active shutter device with continuous transmittance. We implemented the control of the transmittance of the liquid crystal display (LCD) shutter by using a pulse-width modulation (PWM). A simulation and the developed multi-view display system were used to show that our model can represent multi-view images more accurately than the conventional time-division 0-1 active shutter system.

Projectors using digital mirror devices (DMDs) are widely used in consumer electronics. DMDs can switch between the ON and OFF states. Light is reflected by the DMDs, and a binary image is projected onto a screen. Full-color images can be represented by switching 24-binary images rapidly. To increase the frame rate, it is necessary to speed up the DMD switching. However, this is difficult because the switching time is limited by the mechanical constraints of the DMD. One solution is reducing the number of binary images to represent a full-color image. This paper proposes a framework for optimizing the color quantization and light-emitting diode (LED) luminance. The constructed system was evaluated by using a projector and complementary metal–oxide–semiconductor (CMOS) camera. The experimental results indicated that the proposed method improves the total luminance of a projected image approximately 122% compared to previous models and produces better image quality1.

In recent years, many researchers have shown increasing interest in music information retrieval (MIR) applications, with automatic chord recognition being one of the popular tasks. Many studies have achieved/demonstrated considerable improvement using deep learning based models in automatic chord recognition problems. However, most of the existing models have focused on simple chord recognition, which classifies the root note with the major, minor, and seventh chords. Furthermore, in learning-based recognition, it is critical to collect high-quality and large amounts of training data to achieve the desired performance. In this paper, we present a multi-task learning (MTL) model for a guitar chord recognition task, where the model is trained using a relatively large-vocabulary guitar chord dataset. To solve data scarcity issues, a physical data augmentation method that directly records the chord dataset from a robotic performer is employed. Deep learning based MTL is proposed to improve the performance of automatic chord recognition with the proposed physical data augmentation dataset. The proposed MTL model is compared with four baseline models and its corresponding single-task learning model using two types of datasets, including a human dataset and a human combined with the augmented dataset. The proposed methods outperform the baseline models, and the results show that most scores of the proposed multi-task learning model are better than those of the corresponding single-task learning model. The experimental results demonstrate that physical data augmentation is an effective method for increasing the dataset size for guitar chord recognition tasks.

In this paper, we propose a learning-based supervised discrete hashing method. Binary hashing is widely used for large-scale image retrieval as well as video and document searches because the compact binary code representation is essential for data storage and reasonable for query searches using bit-operations. The recently proposed supervised discrete hashing (SDH) method efficiently solves mixed-integer programming problems by alternating optimization and the discrete cyclic coordinate descent (DCC) method. Based on some preliminary experiments, we show that the SDH method can be simplified without performance degradation. We analyze the simplified model and provide a mathematically exact solution thereof; we reveal that the exact binary code is provided by a "Hadamard matrix." Therefore, we named our method Hadamard codedsupervised discrete hashing (HC-SDH). In contrast to SDH, our model does not require an alternating optimization algorithm and does not depend on initial values. HC-SDH is also easier to implement than iterative quantization (ITQ). Experimental results involving a large-scale database show that Hadamard coding outperforms conventional SDH in terms of precision, recall, and computational time. On the large datasets SUN-397 and ImageNet, HC-SDH provides a superior mean average of precision (mAP) and top-accuracy compared to the conventional SDH methods with the same code length and FastHash. The training time of HC-SDH is 170 times faster than conventional SDH and the testing time including the encoding time is seven times faster than FastHash which encodes using a binary-tree.

A strategy to optimize traffic light signal parameters is presented for solving traffic congestion problem using modification of the Multielement Genetic Algorithm (MEGA). The aim of this method is to improve the lack of vehicle throughput (FF ) of the works called as traffic light signal parameters optimization using the MEGA and Particle Swarm Optimization (PSO). In this case, the modification of MEGA is done by adding Hash-Table for saving some best populations for accelerating the recombination process of MEGA which is shortly called as H-MEGA. The experimental results show that the H-MEGA based optimization provides better performance than MEGA and PSO based methods (improving the FF of both MEGA and PSO based optimization methods by about 10.01% (from 82,63% to 92.64%) and 6.88% (from 85.76% to 92.64%), respectively). In addition, the H-MEGA improve significantly the real FF of Ooe Toroku road network of Kumamoto City, Japan about 21.62%.

Developed shogi robot system The authors developed a low-cost, safety shogi robot system. A Web camera installed on the lower frame is used to recognize pieces and their positions on the board, after which the game program is played. A robot arm moves a selected piece to the position used in playing a human player. A fast, robust image processing algorithm is needed because a low-cost wide-angle Web camera and robot are used. The authors describe image processing and robot systems, then discuss experiments conducted to verify the feasibility of the proposal, showing that even a low-cost system can be highly reliable.

Batik is one of the cultural heritages of Indonesia that have many different motifs in each region as well as in its usage. However, the Indonesians sometimes not knowing the batik motif that they’re wearing every day, and sometimes they have a batik image without knowing batik information contained in their batik image. With the growing number of images of batik and batik motifs, a classification method that can classify various motifs of batik is required to automatically detect the motif from the batik image. Image processing using the Deep Learning especially for image classification is widely used recently because it has good results. The most popular method in deep learning is Convolutional Neural Network (CNN) which has been proved robust in natural images. This study offers a batik motif image classification system using CNN method with new network architecture developed by combining GoogLeNet and Residual Networks named IncRes. IncRes merges the Inception Module with Residual Network structure. With the 70.84% accuracy, the system can be used to classify the batik image motif accurately.

In this study, we propose the application of principal components analysis (PCA) to scale-spaces. PCA is a standard method used in computer vision. The translation of an input image into scale-space is a continuous operation, which requires the extension of conventional finite matrix- based PCA to an infinite number of dimensions. In this study, we use spectral decomposition to resolve this infinite eigenproblem by integration and we propose an approximate solution based on polynomial equations. To clarify its eigensolutions, we apply spectral decomposition to the Gaussian scale-space and scale-normalized Laplacian of Gaussian (LoG) space. As an application of this proposed method, we introduce a method for generating Gaussian blur images and scale-normalized LoG images, where we demonstrate that the accuracy of these images can be very high when calculating an arbitrary scale using a simple linear combination. We also propose a new Scale Invariant Feature Transform (SIFT) detector as a more practical example.

This paper proposes an image enlargement method that produces proportional salient content of image magnification. To obtain the proportional salient image content: first, we enlarge the source image to the high size of the target image using uniform enlarging. Second, we slice the image into sections from top to bottom following the minimum energy and detect the salient feature of the image. Third, we enlarge the slice of the image region that does not containthe salient feature of the image to the full size of the target image. The proposed method has been tested in several images, such as akiyo, butterfly, cameraman, canoe, dolphin, and parrot. The experimental results show that the proposed method results in a proportional content for image enlargement in the different ratios compared with the comparison method.

The Principle Component Analysis (PCA) and its variations are the most popular approach for features clustering, which is mostly implemented for face recognition. The optimum projection matrix of the PCA is typically obtained by eigenanalysis of global covariance matrix. However, the projection data using the PCA are lack of discriminatory power. This problem is caused by removing the null space of data scatter that contains much discriminant information. To solve this problem, we present alternative strategy to the PCA called alternative PCA, which obtains the optimum projection matrix from within class scatter instead of global covariance matrix. This algorithm not only provides better features clustering than that of common PCA (CPCA) but also can overcome the retraining problem of the CPCA. In this paper, this algorithm is applied for face recognition with the holistic features of face image, which has compact size and powerful energy compactness as dimensional reduction of the raw face image. From the experimental results, the proposed method provides better performance for both recognition rate and accuracy parameters than those of CPCA and its variations when the tests were carried out using data from several databases such as ITS-LAB., INDIA, ORL, and FERET.

As relics of history, ancient copper inscriptions are found in many countries. Information in the image or letter forms contained on copper ancient inscription has a very high value. The age and environmental factors caused damage to the surface of the inscription and also reduced the appearances of the image and letter. In this paper, we describe a novel segmentation methodology based on multi-texture features for ancient copper inscriptions which were severely damaged. The segmentation results of letters on ancient copper inscriptions by using the proposed method have an average accuracy of 90%. Based on these results, the proposed method is suitable for letter segmentation of the ancient copper inscriptions.

In urban areas, the main disadvantage of an aerial photo for road extraction is the shadow cast by buildings and the complexity of the road network. For this case, we used Digital Surface Model (DSM) data, which are based on the elevation of land surfaces. However, one of the problems associated with DSM data is the non-road area with the same road elevations, like parking places, parks, empty ground and so on. In this paper, we propose the Mixed ART clustering on histogram followed by region growing to extract the initial road and perform the road filter by opening operation with a line shape structuring element, where the line orientation is obtained from the Radon Transform. Finally, the road networks are constructed based on B-Spline curve from the skeleton of the extracted road. The experimental result shows that the proposed method improved the quality and the accuracy average within an acceptable time.

This paper proposes an image enlargement method with proportional content magnification by implementing the different scale factor for image slice region. We use window-kernel image magnification to enlarge the image slice. The enlarged image to target image size has three steps. The first step, source image is enlarged to the same size with high of the target image. The second step, the enlarged image in the first step is sliced from top to bottom following the minimum energy from the image. The third step, the image slices with non salient image content are selected to enlarge to the full-size image. The proposed method has been evaluated using peak signal-to-noise ratio (PSNR). The PSNR value on a uniform enlarged image using a scale factor equal to four has highest value compared with the comparison method. The image enlargement in the different ratio is also presented.

This paper proposes an alternative approach to face recognition algorithm that is based on global/holistic features of face image and simplified linear discriminant analysis (LDA). The proposed method can overcome main problems of the conventional LDA in terms of large processing time for retraining when a new class data is registered into the training data set. The holistic features of face image are proposed as dimensional reduction of raw face image. While, the simplified LDA which is the redefinition of between class scatter using constant global mean assignment is proposed to decrease time complexity of retraining process. To know the performance of the proposed method, several experiments were performed using several challenging face databases: ORL, YALE, ITS-Lab, INDIA, and FERET database. Furthermore, we compared the developed algorithm experimental results to the best traditional subspace methods such as DLDA, 2DLDA, (2D)2DLDA, 2DPCA, and (2D)22DPCA. The experimental results show that the proposed method can be solve the retraining problem of the conventional LDA indicated by requiring shorted retraining time and stable recognition rate.

This paper proposed an alternative approach to face recognition algorithm that is based on global/holistic features of face image and simplified Linear Discriminant Analysis (LDA). The proposed method can overcome main problems of the conventional LDA in terms of large processing time for retraining when a new class data was registered into the training data set. The holistic features of face image were proposed as dimensional reduction of raw face image. While, the simplified LDA which is the redefinition of between class scatter using constant global mean assignment was proposed to decrease time complexity of retraining process. In order to know the performance of the proposed method, several experiments were performed using several challenging face databases: ORL, YALE, ITS-Lab, INDIA, and FERET database. Furthermore, we compared the developed algorithm experimental results to the best traditional subspace methods such as DLDA, 2DLDA, (2D) 2 DLDA, 2DPCA, and (2D) 2 2DPCA. The experimental results show that the proposed method can solve the retraining problem of the conventional LDA indicated by requiring short retraining time and stable recognition rate. DOI: http://dx.doi.org/10.11591/telkomnika.v10i4.1258