A robust algorithm for text region detection in natural scene images

In this paper, a new method for detecting text regions in natural scene images is presented. The proposed algorithm is based on the segmentation of objects in a scene, followed by the identification of text objects by a support vector machine (SVM). First, to segment objects in the scene, the input image is separated into chromatic and achromatic regions according to the distribution of red, green and blue (RGB) elements, and different clustering algorithms are applied. Second, each object is transformed into the wavelet domain for multi-resolution analysis, and moment features of the wavelet coefficients are used in the SVM for the classification of text objects. The proposed approach provides robustness to non-uniform illumination by using different clustering algorithms according to the characteristics of the colour components in the segmentation. Also, moment features, used for classification, are invariant to the size, direction, shape and other properties of texts. Experimental results demonstrate the effectiveness of this approach.     

Prediction and quality control of the melt index during production of high-density polyethylene

In polyolefin processes the melt index (MI) is the most important control variable indicating product quality. Because of the difficulty in the on-line measurement of MI, a lot of MI estimation and correlation methods have been proposed. In this work a new dynamic MI estimation scheme is developed based on system identification techniques. The empirical MI estimation equation proposed in the present study is derived from the 1 ^st -order dynamic models. Effectiveness of the present estimation scheme was illustrated by numerical simulations based on plant operation data including grade change operations in high density polyethylene (HDPE) processes. From the comparisons with other estimation methods it was found that the proposed estimation scheme showed better performance in MI predictions. The virtual sensor model developed based on the estimation scheme was combined with the virtual on-line analyzer (VOA) to give a quality control system to be implemented in the actual HDPE plant. From the application of the present control system, significant reduction of transition time and the amount of off-spec during grade changes was achieved     

Effect of Wall Surface Properties at Different Drying Kinetics on the Deposition Problem in Spray Drying

Current methods in alleviating the wall deposition problem in spray drying emphasize mainly controlling the stickiness of the drying particles and less attention is placed on the properties of the dryer wall. In this experimental study, the effect of wall surface properties on the deposition mechanism has been investigated. Properties considered in classifying different wall materials were surface energy, roughness, and dielectric properties. The model solution contained sucrose, representing low-molecular-weight sugars commonly encountered in spray drying of fruit and vegetable juices. The effect of wall properties on deposition was explored at different drying rates producing particles of different surface rigidity. Larger surface roughness produced higher deposition fluxes for particles with high impact velocity and moisture. Surface energy and surface roughness were found to have no significant effect for dry rigid particles at the middle and bottom elevation of the drying chamber. However, material with lower surface energy (Teflon) exhibited less deposition for rubbery particles at such elevations. Analysis shows that dielectric wall material (Teflon) tends to enhance deposition of dry particles because of attrition at the surface. Higher wall temperature was found to produce slightly more deposition. The results of this work give a general indication of the effect of wall material on the deposition problem and provide the fundamental understanding for further studies along this line. Proper selection of dryer wall material will provide potential alternatives for reducing the deposition problem.     

Recrystallization of phenylbutazone using supercritical fluid antisolvent process

Phenylbutazone was recrystallized from its solutions by using a supercritical fluid antisolvent process. It was dissolved in acetone and supercritical carbon dioxide was injected into the solution, thereby inducing supersaturation and particle formation. Variation in the physical properties of the recrystallized phenylbutazone was investigated as a function of the crystallizing temperature and the carbon dioxide injection rate. The recrystallized particles showed cleaner surfaces and more ordered morphology compared to the particles obtained by other methods such as solvent evaporation. X-ray diffraction patterns indicated that the crystallinity of the particles had been modified upon the recrystallization. Differential scanning calorimetry measurement revealed that the crystallizing temperature influenced the thermal stability of the resulting crystals. Larger crystals were produced when the carbon dioxide injection rate was reduced.     

Learning user preferences of route choice behaviour for adaptive route guidance

As the use of navigation systems becomes more widespread, the demand for advanced functions of navigation systems also increases. In the light of user satisfaction, personalisation of route guidance by incorporating user preferences is one of the most desired features. A user model applied to personalised route guidance is presented. The user model adaptively updates route selection rules when it discovers the predicted choice differs from the actual choice of the driver. This study employs a decision tree learning algorithm, the C4.5 algorithm, which has advantages over other data mining methods in terms of its comprehensible model structure. Simulation experiments with a real-world network were conducted to analyse the applicability of the model to adaptive route guidance and the accuracy of its prediction     

Contributions of Metaknowledge to Retrieval of Natural Categories in Semantic Memory.

Retrieving the answer to a general knowledge question has been shown to involve two metacognitive processes--a feeling-of-knowing that initiates the search of long-term memory and a willingness to continue searching until an answer can be confidently stated. To extend this model, college students were asked to retrieve as many members of 2 natural categories as they could in 1 min. Examination of the points at which they switched categories revealed that they searched longer in categories of higher potency, and they switched earlier when the other category was of higher potency. They also searched the first category longer when they were allowed to switch only once during a trial rather than as often as they wished. It was concluded that feeling-of-knowing maintained search of a category and also contributed to the willingness to continue searching, and the constraint on switching impacted the willingness to continue. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The evolving patterns of inter-industrial knowledge structure: Case of Korean manufacturing in the 1980s

The notion of knowledge-based economy premises that technological knowledge be created, accumulated and disseminated through the interactive learning among principal actors in the national system. This paper analyzes, from a dynamic perspective, the structure of inter-industrial technological knowledge. Both human-driven disembodied channel and capital-driven embodied channel are investigated based on network analysis. The set of empirical data covers the Korean manufacturing sector during the 1980s. Overall, density of network tends to be increasing over time, implying that knowledge network becomes expanded and intensified. A number of distinctive features are identified between knowledge types and industrial categories. The findings in turn render important policy implications that should be addressed when developing technology policy. Clearly, the policy framework needs to be industry-specific and country-specific in accordance with the development stage and industrial structure of reference time. This revised version was published online in August 2006 with corrections to the Cover Date.     

Using classification techniques for informal requirements in the requirements analysis-supporting system

In order to efficiently develop large-scale and complicated software, it is important for system engineers to correctly understand users’ requirements. Most requirements in large-scale projects are collected from various stakeholders located in various regions, and they are generally written in natural language. Therefore, the initial collected requirements must be classified into various topics prior to analysis phases in order to be usable as input in several requirements analysis methods. If this classification process is manually done by analysts, it becomes a time-consuming task. To solve this problem, we propose a new bootstrapping method which can automatically classify requirements sentences into each topic category using only topic words as the representative of the analysts’ views. The proposed method is verified through experiments using two requirements data sets: one written in English and the other in Korean. The significant performances were achieved in the experiments: the 84.28 and 87.91 F1 scores for the English and Korean data sets, respectively. As a result, the proposed method can provide an effective function for an Internet-based requirements analysis-supporting system so as to efficiently gather and analyze requirements from various and distributed stakeholders by using the Internet.     

A slotted post-wall waveguide array with interdigital structure for 45/spl deg/ linear and dual polarization

This work proposes a dual-polarized planar antenna; two post-wall slotted waveguide arrays with orthogonal 45/spl deg/ linearly-polarized waves interdigitally share the aperture on a single layer substrate. Uniform excitation of the two-dimensional slot array is confirmed by experiment in the 25 GHz band. The isolation between two slot arrays is also investigated in terms of the relative displacement along the radiation waveguide axis in the interdigital structure. The isolation is 33.0 dB when the relative shift of slot position between the two arrays is -0.5/spl lambda//sub g/, while it is only 12.8 dB when there is no shift. The cross-polarization level in the far field is -25.2 dB for a -0.5/spl lambda//sub g/ shift, which is almost equal to that of the isolated single polarization array. It is degraded down to -9.6 dB when there is no shift.